From 6725d3b7b56d1b21231d9a7a0de38f5323cd01fc Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Mon, 6 Apr 2026 00:20:09 +0000 Subject: [PATCH] bot: update weekly RSS feed --- feed_weekly.xml | 1394 +++++++++++++++++++++++------------------------ 1 file changed, 697 insertions(+), 697 deletions(-) diff --git a/feed_weekly.xml b/feed_weekly.xml index 9ac6d0e..85fa549 100644 --- a/feed_weekly.xml +++ b/feed_weekly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 30 Mar 2026 00:20:00 +0000 + Mon, 06 Apr 2026 00:20:08 +0000 - MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens - https://arxiv.org/abs/2603.23516 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23516.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Chen, Runkai Chen, Sheng Yi, Xinda Zhao, Xiaohong Li, Jianjin Zhang, Jun Sun, Chuanrui Hu, Yunyun Han, Lidong Bing, Yafeng Deng, Tianqiao Chen</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in the field. Due to the constraints of full-attention architectures, the effective context length of large language models (LLMs) is typically limited to 1M tokens. Existing approaches, such as hybrid linear attention, fixed-size memory states (e.g., RNNs), and external storage methods like RAG or agent systems, attempt to extend this limit. However, they often suffer from severe precision degradation and rapidly increasing latency as context length grows, an inability to dynamically modify memory content, or a lack of end-to-end optimization. These bottlenecks impede complex scenarios like large-corpus summarization, Digital Twins, and long-history agent reasoning, while limiting memory capacity and slowing inference. We present Memory Sparse Attention (MSA), an end-to-end trainable, efficient, and massively scalable memory model framework. Through core innovations including scalable sparse attention and document-wise RoPE, MSA achieves linear complexity in both training and inference while maintaining exceptional stability, exhibiting less than 9% degradation when scaling from 16K to 100M tokens. Furthermore, KV cache compression, combined with Memory Parallel, enables 100M-token inference on 2xA800 GPUs. We also propose Memory Interleaving to facilitate complex multi-hop reasoning across scattered memory segments. MSA significantly surpasses frontier LLMs, state-of-the-art RAG systems, and leading memory agents in long-context benchmarks. These results demonstrate that by decoupling memory capacity from reasoning, MSA provides a scalable foundation to endow general-purpose models with intrinsic, lifetime-scale memory.</p> - https://arxiv.org/abs/2603.23516 - Fri, 06 Mar 2026 02:29:54 +0000 + Learn2Fold: Structured Origami Generation with World Model Planning + https://arxiv.org/abs/2603.29585 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29585.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanjia Huang, Yunuo Chen, Ying Jiang, Jinru Han, Zhengzhong Tu, Yin Yang, Chenfanfu Jiang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> The ability to transform a flat sheet into a complex three-dimensional structure is a fundamental test of physical intelligence. Unlike cloth manipulation, origami is governed by strict geometric axioms and hard kinematic constraints, where a single invalid crease or collision can invalidate the entire folding sequence. As a result, origami demands long-horizon constructive reasoning that jointly satisfies precise physical laws and high-level semantic intent. Existing approaches fall into two disjoint paradigms: optimization-based methods enforce physical validity but require dense, precisely specified inputs, making them unsuitable for sparse natural language descriptions, while generative foundation models excel at semantic and perceptual synthesis yet fail to produce long-horizon, physics-consistent folding processes. Consequently, generating valid origami folding sequences directly from text remains an open challenge. To address this gap, we introduce Learn2Fold, a neuro-symbolic framework that formulates origami folding as conditional program induction over a crease-pattern graph. Our key insight is to decouple semantic proposal from physical verification. A large language model generates candidate folding programs from abstract text prompts, while a learned graph-structured world model serves as a differentiable surrogate simulator that predicts physical feasibility and failure modes before execution. Integrated within a lookahead planning loop, Learn2Fold enables robust generation of physically valid folding sequences for complex and out-of-distribution patterns, demonstrating that effective spatial intelligence arises from the synergy between symbolic reasoning and grounded physical simulation.</p> + https://arxiv.org/abs/2603.29585 + Mon, 02 Feb 2026 11:24:19 +0000 - Qworld: Question-Specific Evaluation Criteria for LLMs - https://arxiv.org/abs/2603.23522 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23522.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shanghua Gao, Yuchang Su, Pengwei Sui, Curtis Ginder, Marinka Zitnik</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context. Binary scores and static rubrics fail to capture these context-dependent requirements. Existing methods define criteria at the dataset level or generate them in a single pass, which limits their ability to explore the evaluation space implied by each question. We introduce One-Question-One-World (Qworld), a method that generates question-specific evaluation criteria using a recursive expansion tree. Given a question, Qworld decomposes it into scenarios, perspectives, and fine-grained binary criteria through structured hierarchical and horizontal expansion. The resulting criteria specify what a high-quality answer must address for that question. On HealthBench, Qworld covers 89% of expert-authored criteria and generates 79% novel criteria validated by human experts. Experts rate Qworld criteria higher in insight and granularity than those produced by prior methods. When applied to 11 frontier LLMs on HealthBench and Humanity's Last Exam, Qworld reveals capability differences in dimensions such as long-term impact, equity, error handling, and interdisciplinary reasoning that coarse rubrics do not distinguish. By formulating criteria generation as structured coverage of question-implied evaluation axes, Qworld enables evaluation that adapts to each question rather than relying on fixed task-level criteria.</p> - https://arxiv.org/abs/2603.23522 - Fri, 06 Mar 2026 15:20:45 +0000 + Dynin-Omni: Omnimodal Unified Large Diffusion Language Model + https://arxiv.org/abs/2604.00007 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00007.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaeik Kim, Woojin Kim, Jihwan Hong, Yejoon Lee, Sieun Hyeon, Mintaek Lim, Yunseok Han, Dogeun Kim, Hoeun Lee, Hyunggeun Kim, Jaeyoung Do</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> We present Dynin-Omni, the first masked-diffusion-based omnimodal foundation model that unifies text, image, and speech understanding and generation, together with video understanding, within a single architecture. Unlike autoregressive unified models that serialize heterogeneous modalities, or compositional unified models that require orchestration with external modality-specific decoders, Dynin-Omni natively formulates omnimodal modeling as masked diffusion over a shared discrete token space, enabling iterative refinement under bidirectional context. Dynin-Omni adopts a multi-stage training strategy with model-merging-based modality expansion and omnimodal alignment. We evaluate Dynin-Omni across 19 multimodal benchmarks spanning language reasoning, image generation and editing, video understanding, and speech recognition and synthesis. Dynin-Omni achieves 87.6 on GSM8K, 1733.6 on MME-P, 61.4 on VideoMME, 0.87 on GenEval, and 2.1 WER on LibriSpeech test-clean, consistently outperforming existing open-source unified models while remaining competitive with strong modality-specific expert systems. These results demonstrate the potential of masked diffusion as a unified paradigm for any-to-any modeling, providing a flexible foundation for real-time omnimodal systems, unified cross-modal retrieval and generation, and embodied multimodal agents.</p> + https://arxiv.org/abs/2604.00007 + Mon, 09 Mar 2026 13:59:02 +0000 - Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck - https://arxiv.org/abs/2603.08462 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08462.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Chain-of-Thought (CoT) prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing "Budget Forcing" methods reducing cost via fine-tuning with heuristic length penalties, suppress both essential reasoning and redundant filler. We recast efficient reasoning as a lossy compression problem under the Information Bottleneck (IB) principle, and identify a key theoretical gap when applying naive IB to transformers: attention violates the Markov property between prompt, reasoning trace, and response. To resolve this issue, we model CoT generation under the Conditional Information Bottleneck (CIB) principle, where the reasoning trace Z acts as a computational bridge that contains only the information about the response Y that is not directly accessible from the prompt X. This yields a general Reinforcement Learning objective: maximize task reward while compressing completions under a prior over reasoning traces, subsuming common heuristics (e.g., length penalties) as special cases (e.g., uniform priors). In contrast to naive token-counting-based approaches, we introduce a semantic prior that measures token cost by surprisal under a language model prior. Empirically, our CIB objective prunes cognitive bloat while preserving fluency and logic, improving accuracy at moderate compression and enabling aggressive compression with minimal accuracy drop.</p> - https://arxiv.org/abs/2603.08462 - Mon, 09 Mar 2026 14:56:57 +0000 + Brevity Constraints Reverse Performance Hierarchies in Language Models + https://arxiv.org/abs/2604.00025 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> MD Azizul Hakim</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger language models underperform smaller ones by 28.4 percentage points despite 10-100x more parameters. Through systematic evaluation of 31 models (0.5B-405B parameters) across 1,485 problems, we identify the mechanism as spontaneous scale-dependent verbosity that introduces errors through overelaboration. Causal intervention experiments demonstrate this reflects correctable prompt design rather than fundamental capability limitations. Constraining large models to produce brief responses improves accuracy by 26 percentage points and reduces performance gaps by up to two-thirds. Most critically, brevity constraints completely reverse performance hierarchies on mathematical reasoning and scientific knowledge benchmarks, with large models achieving 7.7-15.9 percentage point advantages over small models -- direct inversions of the original gaps. These reversals prove large models possess superior latent capabilities that universal prompting masks. We validate findings through three independent contamination tests and demonstrate inverse scaling operates continuously across the full parameter spectrum, with dataset-specific optimal scales ranging from 0.5B to 3.0B parameters. Our results establish that maximizing large model performance requires scale-aware prompt engineering rather than universal evaluation protocols, with immediate implications for deployment: prompt adaptation simultaneously improves accuracy and reduces computational costs.</p> + https://arxiv.org/abs/2604.00025 + Wed, 11 Mar 2026 06:47:41 +0000 - Deep Tabular Research via Continual Experience-Driven Execution - https://arxiv.org/abs/2603.09151 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09151.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Qiufeng Wang, Yinghui Li, Siyu An, Di Yin, Xing Sun, Feiyue Huang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning.</p> - https://arxiv.org/abs/2603.09151 - Tue, 10 Mar 2026 03:42:54 +0000 + SEAR: Schema-Based Evaluation and Routing for LLM Gateways + https://arxiv.org/abs/2603.26728 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26728.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zecheng Zhang, Han Zheng, Yue Xu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Evaluating production LLM responses and routing requests across providers in LLM gateways requires fine-grained quality signals and operationally grounded decisions. To address this gap, we present SEAR, a schema-based evaluation and routing system for multi-model, multi-provider LLM gateways. SEAR defines an extensible relational schema covering both LLM evaluation signals (context, intent, response characteristics, issue attribution, and quality scores) and gateway operational metrics (latency, cost, throughput), with cross-table consistency links across around one hundred typed, SQL-queryable columns. To populate the evaluation signals reliably, SEAR proposes self-contained signal instructions, in-schema reasoning, and multi-stage generation that produces database-ready structured outputs. Because signals are derived through LLM reasoning rather than shallow classifiers, SEAR captures complex request semantics, enables human-interpretable routing explanations, and unifies evaluation and routing in a single query layer. Across thousands of production sessions, SEAR achieves strong signal accuracy on human-labeled data and supports practical routing decisions, including large cost reductions with comparable quality.</p> + https://arxiv.org/abs/2603.26728 + Fri, 20 Mar 2026 04:51:35 +0000 - ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization - https://arxiv.org/abs/2603.09290 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09290.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shimin Di, Xujie Yuan, Hanghui Guo, Chaoqian Ouyang, Zhangze Chen, Ling Yue, Libin Zheng, Jia Zhu, Shaowu Pan, Jian Yin, Min-Ling Zhang, Yong Rui</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Reusing and invoking existing code remains costly and unreliable, as most practical tools are embedded in heterogeneous code repositories and lack standardized, executable interfaces. Although large language models (LLMs) and Model Context Protocol (MCP)-based tool invocation frameworks enable natural language task execution, current approaches rely heavily on manual tool curation and standardization, which fundamentally limits scalability. In this paper, we propose ToolRosetta, a unified framework that automatically translates open-source code repositories and APIs into MCP-compatible tools that can be reliably invoked by LLMs. Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant codebases, and converts them into executable MCP services, enabling end-to-end task completion with minimal human intervention. In addition, ToolRosetta incorporates a security inspection layer to mitigate risks inherent in executing arbitrary code. Extensive experiments across diverse scientific domains demonstrate that ToolRosetta can automatically standardize a large number of open-source tools and reduce the human effort required for code reproduction and deployment. Notably, by seamlessly leveraging specialized open-source tools, ToolRosetta-powered agents consistently improve task completion performance compared to commercial LLMs and existing agent systems.</p> - https://arxiv.org/abs/2603.09290 - Tue, 10 Mar 2026 07:19:43 +0000 + Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models + https://arxiv.org/abs/2603.25750 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25750.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeongoon Kim, Jaegul Choo, Cheonbok Park</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction. However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume. Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations. To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.</p> + https://arxiv.org/abs/2603.25750 + Fri, 20 Mar 2026 09:10:43 +0000 - Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing - https://arxiv.org/abs/2603.12254 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12254.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baifeng Shi, Stephanie Fu, Long Lian, Hanrong Ye, David Eigen, Aaron Reite, Boyi Li, Jan Kautz, Song Han, David M. Chan, Pavlo Molchanov, Trevor Darrell, Hongxu Yin</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Multi-modal large language models (MLLMs) have advanced general-purpose video understanding but struggle with long, high-resolution videos -- they process every pixel equally in their vision transformers (ViTs) or LLMs despite significant spatiotemporal redundancy. We introduce AutoGaze, a lightweight module that removes redundant patches before processed by a ViT or an MLLM. Trained with next-token prediction and reinforcement learning, AutoGaze autoregressively selects a minimal set of multi-scale patches that can reconstruct the video within a user-specified error threshold, eliminating redundancy while preserving information. Empirically, AutoGaze reduces visual tokens by 4x-100x and accelerates ViTs and MLLMs by up to 19x, enabling scaling MLLMs to 1K-frame 4K-resolution videos and achieving superior results on video benchmarks (e.g., 67.0% on VideoMME). Furthermore, we introduce HLVid: the first high-resolution, long-form video QA benchmark with 5-minute 4K-resolution videos, where an MLLM scaled with AutoGaze improves over the baseline by 10.1% and outperforms the previous best MLLM by 4.5%. Project page: https://autogaze.github.io/.</p> - https://arxiv.org/abs/2603.12254 - Thu, 12 Mar 2026 17:58:52 +0000 + FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization + https://arxiv.org/abs/2603.19835 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19835.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chiyu Ma, Shuo Yang, Kexin Huang, Jinda Lu, Haoming Meng, Shangshang Wang, Bolin Ding, Soroush Vosoughi, Guoyin Wang, Jingren Zhou</p><p><b>Upvotes:</b> 317</p><p><b>Summary:</b> We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on outcome-based rewards (ORM) that distribute a global advantage uniformly across every token in a trajectory. We argue that this coarse-grained credit assignment imposes a performance ceiling by failing to distinguish critical logical pivots from trivial tokens. FIPO addresses this by incorporating discounted future-KL divergence into the policy update, creating a dense advantage formulation that re-weights tokens based on their influence on subsequent trajectory behavior. Empirically, FIPO enables models to break through the length stagnation seen in standard baselines. Evaluated on Qwen2.5-32B, FIPO extends the average chain-of-thought length from roughly 4,000 to over 10,000 tokens and increases AIME 2024 Pass@1 accuracy from 50.0% to a peak of 58.0% (converging at approximately 56.0\%). This outperforms both DeepSeek-R1-Zero-Math-32B (around 47.0%) and o1-mini (approximately 56.0%). Our results suggest that establishing dense advantage formulations is a vital path for evolving ORM-based algorithms to unlock the full reasoning potential of base models. We open-source our training system, built on the verl framework.</p> + https://arxiv.org/abs/2603.19835 + Fri, 20 Mar 2026 10:24:50 +0000 - Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs - https://arxiv.org/abs/2603.16932 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16932.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nimrod Shabtay, Moshe Kimhi, Artem Spector, Sivan Haray, Ehud Rivlin, Chaim Baskin, Raja Giryes, Eli Schwartz</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs capture fine details but incur significant computational costs, while low-resolution inputs advocate for efficiency, they potentially miss critical visual information, like small text. We present AwaRes, a spatial-on-demand framework that resolves this accuracy-efficiency trade-off by operating on a low-resolution global view and using tool-calling to retrieve only high-resolution segments needed for a given query. We construct supervised data automatically: a judge compares low- vs.\ high-resolution answers to label whether cropping is needed, and an oracle grounding model localizes the evidence for the correct answer, which we map to a discrete crop set to form multi-turn tool-use trajectories. We train our framework with cold-start SFT followed by multi-turn GRPO with a composite reward that combines semantic answer correctness with explicit crop-cost penalties. Project page: https://nimrodshabtay.github.io/AwaRes</p> - https://arxiv.org/abs/2603.16932 - Sat, 14 Mar 2026 10:11:32 +0000 + Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models + https://arxiv.org/abs/2603.22782 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22782.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyue Chen, Wenjue Chen, Peng Li, Qinghe Wang, Xu Jia, Heliang Zheng, Rongfei Jia, Yuan Liu, Ronggang Wang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity of single-view observations and the lack of robust global structural priors caused by limited 3D training data, the unseen regions generated by existing models are often stochastic and difficult to control, which may sometimes fail to align with user intentions or produce implausible geometries. In this paper, we propose Know3D, a novel framework that incorporates rich knowledge from multimodal large language models into 3D generative processes via latent hidden-state injection, enabling language-controllable generation of the back-view for 3D assets. We utilize a VLM-diffusion-based model, where the VLM is responsible for semantic understanding and guidance. The diffusion model acts as a bridge that transfers semantic knowledge from the VLM to the 3D generation model. In this way, we successfully bridge the gap between abstract textual instructions and the geometric reconstruction of unobserved regions, transforming the traditionally stochastic back-view hallucination into a semantically controllable process, demonstrating a promising direction for future 3D generation models.</p> + https://arxiv.org/abs/2603.22782 + Tue, 24 Mar 2026 04:18:29 +0000 - Representation Alignment for Just Image Transformers is not Easier than You Think - https://arxiv.org/abs/2603.14366 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14366.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaeyo Shin, Jiwook Kim, Hyunjung Shim</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Representation Alignment (REPA) has emerged as a simple way to accelerate Diffusion Transformers training in latent space. At the same time, pixel-space diffusion transformers such as Just image Transformers (JiT) have attracted growing attention because they remove a dependency on a pretrained tokenizer, and then avoid the reconstruction bottleneck of latent diffusion. This paper shows that the REPA can fail for JiT. REPA yields worse FID for JiT as training proceeds and collapses diversity on image subsets that are tightly clustered in the representation space of pretrained semantic encoder on ImageNet. We trace the failure to an information asymmetry: denoising occurs in the high dimensional image space, while the semantic target is strongly compressed, making direct regression a shortcut objective. We propose PixelREPA, which transforms the alignment target and constrains alignment with a Masked Transformer Adapter that combines a shallow transformer adapter with partial token masking. PixelREPA improves both training convergence and final quality. PixelREPA reduces FID from 3.66 to 3.17 for JiT-B/16 and improves Inception Score (IS) from 275.1 to 284.6 on ImageNet 256 times 256, while achieving > 2times faster convergence. Finally, PixelREPA-H/16 achieves FID=1.81 and IS=317.2. Our code is available at https://github.com/kaist-cvml/PixelREPA.</p> - https://arxiv.org/abs/2603.14366 - Sun, 15 Mar 2026 13:08:31 +0000 + LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset + https://arxiv.org/abs/2603.23607 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23607.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Royden Wagner, Omer Sahin Tas, Jaime Villa, Felix Hauser, Yinzhe Shen, Marlon Steiner, Dominik Strutz, Carlos Fernandez, Christian Kinzig, Guillermo S. Guitierrez-Cabello, Hendrik Königshof, Fabian Immel, Richard Schwarzkopf, Nils Alexander Rack, Kevin Rösch, Kaiwen Wang, Jan-Hendrik Pauls, Martin Lauer, Igor Gilitschenski, Holger Caesar, Christoph Stiller</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> In real-world domains such as self-driving, generalization to rare scenarios remains a fundamental challenge. To address this, we introduce a new dataset designed for end-to-end driving that focuses on long-tail driving events. We provide multi-view video data, trajectories, high-level instructions, and detailed reasoning traces, facilitating in-context learning and few-shot generalization. The resulting benchmark for multimodal models, such as VLMs and VLAs, goes beyond safety and comfort metrics by evaluating instruction following and semantic coherence between model outputs. The multilingual reasoning traces in English, Spanish, and Chinese are from domain experts with diverse cultural backgrounds. Thus, our dataset is a unique resource for studying how different forms of reasoning affect driving competence. Our dataset is available at: https://hf.co/datasets/kit-mrt/kitscenes-longtail</p> + https://arxiv.org/abs/2603.23607 + Tue, 24 Mar 2026 18:00:08 +0000 - The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics - https://arxiv.org/abs/2603.14375 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangbo Gao, Mingyang Wu, Siyuan Yang, Jiongze Yu, Pardis Taghavi, Fangzhou Lin, Zhengzhong Tu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> While recent generative video models have achieved remarkable visual realism and are being explored as world models, true physical simulation requires mastering both space and time. Current models can produce visually smooth kinematics, yet they lack a reliable internal motion pulse to ground these motions in a consistent, real-world time scale. This temporal ambiguity stems from the common practice of indiscriminately training on videos with vastly different real-world speeds, forcing them into standardized frame rates. This leads to what we term chronometric hallucination: generated sequences exhibit ambiguous, unstable, and uncontrollable physical motion speeds. To address this, we propose Visual Chronometer, a predictor that recovers the Physical Frames Per Second (PhyFPS) directly from the visual dynamics of an input video. Trained via controlled temporal resampling, our method estimates the true temporal scale implied by the motion itself, bypassing unreliable metadata. To systematically quantify this issue, we establish two benchmarks, PhyFPS-Bench-Real and PhyFPS-Bench-Gen. Our evaluations reveal a harsh reality: state-of-the-art video generators suffer from severe PhyFPS misalignment and temporal instability. Finally, we demonstrate that applying PhyFPS corrections significantly improves the human-perceived naturalness of AI-generated videos. Our project page is https://xiangbogaobarry.github.io/Visual_Chronometer/.</p> - https://arxiv.org/abs/2603.14375 - Sun, 15 Mar 2026 13:29:31 +0000 + GenMask: Adapting DiT for Segmentation via Direct Mask + https://arxiv.org/abs/2603.23906 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23906.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhuan Yang, Xianwei Zhuang, Yuxuan Cai, Chaofan Ma, Shuai Bai, Jiangchao Yao, Ya Zhang, Junyang Lin, Yanfeng Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental misalignment in representation. It also depends heavily on indirect feature extraction pipelines, which complicate the workflow and limit adaptation. In this paper, we argue that instead of indirect adaptation, segmentation tasks should be trained directly in a generative manner. We identify a key obstacle to this unified formulation: VAE latents of binary masks are sharply distributed, noise robust, and linearly separable, distinct from natural image latents. To bridge this gap, we introduce timesteps sampling strategy for binary masks that emphasizes extreme noise levels for segmentation and moderate noise for image generation, enabling harmonious joint training. We present GenMask, a DiT trains to generate black-and-white segmentation masks as well as colorful images in RGB space under the original generative objective. GenMask preserves the original DiT architecture while removing the need of feature extraction pipelines tailored for segmentation tasks. Empirically, GenMask attains state-of-the-art performance on referring and reasoning segmentation benchmarks and ablations quantify the contribution of each component.</p> + https://arxiv.org/abs/2603.23906 + Wed, 25 Mar 2026 03:52:05 +0000 - HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning - https://arxiv.org/abs/2603.17024 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17024.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenzhi Wang, Shixuan Liu, Jing Zhou, Chang Gao, Xiong-Hui Chen, Binghai Wang, An Yang, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin</p><p><b>Upvotes:</b> 105</p><p><b>Summary:</b> VLMs show strong multimodal capabilities, but they still struggle with fine-grained vision-language reasoning. We find that long CoT reasoning exposes diverse failure modes, including perception, reasoning, knowledge, and hallucination errors, which can compound across intermediate steps. However, most existing vision-language data used for RLVR does not involve complex reasoning chains that rely on visual evidence throughout, leaving these weaknesses largely unexposed. We therefore propose HopChain, a scalable framework for synthesizing multi-hop vision-language reasoning data specifically for RLVR training of VLMs. Each synthesized multi-hop query forms a logically dependent chain of instance-grounded hops, where earlier hops establish the instances, sets, or conditions needed for later hops, while the final answer remains a specific, unambiguous number suitable for verifiable rewards. We add the multi-hop data synthesized by HopChain to the original RLVR data used to train Qwen3.5-35B-A3B and Qwen3.5-397B-A17B, and compare against RLVR on the original RLVR data alone across 24 benchmarks spanning STEM and Puzzle, General VQA, Text Recognition and Document Understanding, and Video Understanding. Although this multi-hop data is not synthesized to target any specific benchmark, adding it improves 20 out of 24 benchmarks on both models, indicating broad and generalizable gains. To demonstrate that full chained queries are important, we replace them with half-multi-hop or single-hop variants, reducing the 24-benchmark average accuracy by 5.3 and 7.0 points, respectively. Multi-hop training also strengthens long-CoT vision-language reasoning, with gains peaking at more than 50 accuracy points in the ultra-long-CoT regime. These experiments establish HopChain as an effective, scalable framework for synthesizing multi-hop data that improves generalizable vision-language reasoning.</p> - https://arxiv.org/abs/2603.17024 - Tue, 17 Mar 2026 18:04:58 +0000 + ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers + https://arxiv.org/abs/2603.24414 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songyang Liu, Chaozhuo Li, Chenxu Wang, Jinyu Hou, Zejian Chen, Litian Zhang, Zheng Liu, Qiwei Ye, Yiming Hei, Xi Zhang, Zhongyuan Wang</p><p><b>Upvotes:</b> 176</p><p><b>Summary:</b> OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell command execution. However, these broad operational privileges introduce critical security vulnerabilities, transforming model errors into tangible system-level threats such as sensitive data leakage, privilege escalation, and malicious third-party skill execution. Existing security measures for the OpenClaw ecosystem remain highly fragmented, addressing only isolated stages of the agent lifecycle rather than providing holistic protection. To bridge this gap, we present ClawKeeper, a real-time security framework that integrates multi-dimensional protection mechanisms across three complementary architectural layers. (1) Skill-based protection operates at the instruction level, injecting structured security policies directly into the agent context to enforce environment-specific constraints and cross-platform boundaries. (2) Plugin-based protection serves as an internal runtime enforcer, providing configuration hardening, proactive threat detection, and continuous behavioral monitoring throughout the execution pipeline. (3) Watcher-based protection introduces a novel, decoupled system-level security middleware that continuously verifies agent state evolution. It enables real-time execution intervention without coupling to the agent's internal logic, supporting operations such as halting high-risk actions or enforcing human confirmation. We argue that this Watcher paradigm holds strong potential to serve as a foundational building block for securing next-generation autonomous agent systems. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and robustness of ClawKeeper across diverse threat scenarios. We release our code.</p> + https://arxiv.org/abs/2603.24414 + Wed, 25 Mar 2026 15:27:54 +0000 - Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models - https://arxiv.org/abs/2603.17051 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17051.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songchun Zhang, Zeyue Xue, Siming Fu, Jie Huang, Xianghao Kong, Y Ma, Haoyang Huang, Nan Duan, Anyi Rao</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures, typically requiring either expensive re-distillation or solver-coupled reverse-process optimization that introduces considerable memory and computational overhead. We present Astrolabe, an efficient online RL framework tailored for distilled AR models. To overcome existing bottlenecks, we introduce a forward-process RL formulation based on negative-aware fine-tuning. By contrasting positive and negative samples directly at inference endpoints, this approach establishes an implicit policy improvement direction without requiring reverse-process unrolling. To scale this alignment to long videos, we propose a streaming training scheme that generates sequences progressively via a rolling KV-cache, applying RL updates exclusively to local clip windows while conditioning on prior context to ensure long-range coherence. Finally, to mitigate reward hacking, we integrate a multi-reward objective stabilized by uncertainty-aware selective regularization and dynamic reference updates. Extensive experiments demonstrate that our method consistently enhances generation quality across multiple distilled AR video models, serving as a robust and scalable alignment solution.</p> - https://arxiv.org/abs/2603.17051 - Tue, 17 Mar 2026 18:32:18 +0000 + Composer 2 Technical Report + https://arxiv.org/abs/2603.24477 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24477.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cursor Research, Aaron Chan, Ahmed Shalaby, Alexander Wettig, Aman Sanger, Andrew Zhai, Anurag Ajay, Ashvin Nair, Charlie Snell, Chen Lu, Chen Shen, Emily Jia, Federico Cassano, Hanpeng Liu, Haoyu Chen, Henry Wildermuth, Jacob Jackson, Janet Li, Jediah Katz, Jiajun Yao, Joey Hejna, Josh Warner, Julius Vering, Kevin Frans, Lee Danilek, Less Wright, Lujing Cen, Luke Melas-Kyriazi, Michael Truell, Michiel de Jong, Naman Jain, Nate Schmidt, Nathan Wang, Niklas Muennighoff, Oleg Rybkin, Paul Loh, Phillip Kravtsov, Rishabh Yadav, Sahil Shah, Sam Kottler, Alexander M Rush, Shengtong Zhang, Shomil Jain, Sriram Sankar, Stefan Heule, Stuart H. Sul, Sualeh Asif, Victor Rong, Wanqi Zhu, William Lin, Yuchen Wu, Yuri Volkov, Yury Zemlyanskiy, Zack Holbrook, Zhiyuan Zhang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems.</p> + https://arxiv.org/abs/2603.24477 + Wed, 25 Mar 2026 16:18:37 +0000 - OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis - https://arxiv.org/abs/2603.20278 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20278.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce. We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis and executes the search-and-browse loop entirely offline using three explicit browser primitives: search, open, and find, over a 15M-document corpus. Using GPT-OSS-120B as the teacher model, we synthesize over 97K trajectories, including a substantial long-horizon tail with 100+ tool calls. Supervised fine-tuning a 30B-A3B backbone on these trajectories achieves 54.8\% accuracy on BrowseComp-Plus, a +34.0 point improvement over the base model, while remaining competitive on BrowseComp, GAIA, and xbench-DeepSearch. Because the environment is offline and fully instrumented, it also enables controlled analysis, where our study reveals practical insights into deep research pipeline design, including data filtering strategies, agent configuration choices, and how retrieval success relates to final answer accuracy. We release the pipeline, synthesized trajectories, model checkpoints, and the offline search environment at https://github.com/TIGER-AI-Lab/OpenResearcher.</p> - https://arxiv.org/abs/2603.20278 - Tue, 17 Mar 2026 20:10:12 +0000 + MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies + https://arxiv.org/abs/2603.24649 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24649.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixiang Shen, Yanzhu Hu, Che Liu, Junde Wu, Jiayuan Zhu, Chengzhi Shen, Min Xu, Yueming Jin, Benedikt Wiestler, Daniel Rueckert, Jiazhen Pan</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Currently, evaluating vision-language models (VLMs) in medical imaging tasks oversimplifies clinical reality by relying on pre-selected 2D images that demand significant manual labor to curate. This setup misses the core challenge of realworld diagnostics: a true clinical agent must actively navigate full 3D volumes across multiple sequences or modalities to gather evidence and ultimately support a final decision. To address this, we propose MEDOPENCLAW, an auditable runtime designed to let VLMs operate dynamically within standard medical tools or viewers (e.g., 3D Slicer). On top of this runtime, we introduce MEDFLOWBENCH, a full-study medical imaging benchmark covering multi-sequence brain MRI and lung CT/PET. It systematically evaluates medical agentic capabilities across viewer-only, tool-use, and open-method tracks. Initial results reveal a critical insight: while state-of-the-art LLMs/VLMs (e.g., Gemini 3.1 Pro and GPT-5.4) can successfully navigate the viewer to solve basic study-level tasks, their performance paradoxically degrades when given access to professional support tools due to a lack of precise spatial grounding. By bridging the gap between static-image perception and interactive clinical workflows, MEDOPENCLAW and MEDFLOWBENCH establish a reproducible foundation for developing auditable, full-study medical imaging agents.</p> + https://arxiv.org/abs/2603.24649 + Wed, 25 Mar 2026 17:33:58 +0000 - Abstraction as a Memory-Efficient Inductive Bias for Continual Learning - https://arxiv.org/abs/2603.17198 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati, Nina Rouhani, Morteza Dehghani</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The real world is non-stationary and infinitely complex, requiring intelligent agents to learn continually without the prohibitive cost of retraining from scratch. While online continual learning offers a framework for this setting, learning new information often interferes with previously acquired knowledge, causes forgetting and degraded generalization. To address this, we propose Abstraction-Augmented Training (AAT), a loss-level modification encouraging models to capture the latent relational structure shared across examples. By jointly optimizing over concrete instances and their abstract representations, AAT introduces a memory-efficient inductive bias that stabilizes learning in strictly online data streams, eliminating the need for a replay buffer. To capture the multi-faceted nature of abstraction, we introduce and evaluate AAT on two benchmarks: a controlled relational dataset where abstraction is realized through entity masking, and a narrative dataset where abstraction is expressed through shared proverbs. Our results show that AAT achieves performance comparable to or exceeding strong experience replay (ER) baselines, despite requiring zero additional memory and only minimal changes to the training objective. This work highlights structural abstraction as a powerful, memory-free alternative to ER.</p> - https://arxiv.org/abs/2603.17198 - Tue, 17 Mar 2026 22:59:13 +0000 + Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills + https://arxiv.org/abs/2603.25158 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingwei Ni, Yihao Liu, Xinpeng Liu, Yutao Sun, Mengyu Zhou, Pengyu Cheng, Dexin Wang, Xiaoxi Jiang, Guanjun Jiang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or fragmented results because it either relies on shallow parametric knowledge or sequentially overfits to non-generalizable trajectory-local lessons. To overcome this, we introduce Trace2Skill, a framework that mirrors how human experts author skills: by holistically analyzing broad execution experience before distilling it into a single, comprehensive guide. Instead of reacting sequentially to individual trajectories, Trace2Skill dispatches a parallel fleet of sub-agents to analyze a diverse pool of executions. It extracts trajectory-specific lessons and hierarchically consolidates them into a unified, conflict-free skill directory via inductive reasoning. Trace2Skill supports both deepening existing human-written skills and creating new ones from scratch. Experiments in challenging domains, such as spreadsheet, VisionQA and math reasoning, show that Trace2Skill significantly improves upon strong baselines, including Anthropic's official xlsx skills. Crucially, this trajectory-grounded evolution does not merely memorize task instances or model-specific quirks: evolved skills transfer across LLM scales and generalize to OOD settings. For example, skills evolved by Qwen3.5-35B on its own trajectories improved a Qwen3.5-122B agent by up to 57.65 absolute percentage points on WikiTableQuestions. Ultimately, our results demonstrate that complex agent experience can be packaged into highly transferable, declarative skills -- requiring no parameter updates, no external retrieval modules, and utilizing open-source models as small as 35B parameters.</p> + https://arxiv.org/abs/2603.25158 + Thu, 26 Mar 2026 08:26:38 +0000 - Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models - https://arxiv.org/abs/2603.18118 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18118.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Dong, Zuyan Liu, Shulin Tian, Yongming Rao, Ziwei Liu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant challenge due to a critical scarcity of high-quality, long-chain reasoning data and optimized training pipelines. To bridge this gap, we present a unified multi-agent visual reasoning framework that systematically evolves from our foundational image-centric model, Insight-V, into a generalized spatial-temporal architecture, Insight-V++. We first propose a scalable data generation pipeline equipped with multi-granularity assessment that autonomously synthesizes structured, complex reasoning trajectories across image and video domains without human intervention. Recognizing that directly supervising MLLMs with such intricate data yields sub-optimal results, we design a dual-agent architecture comprising a reasoning agent to execute extensive analytical chains, and a summary agent to critically evaluate and distill final outcomes. While our initial framework utilized Direct Preference Optimization (DPO), its off-policy nature fundamentally constrained reinforcement learning potential. To overcome these limitations, particularly for long-horizon video understanding, Insight-V++ introduces two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness. Crucially, by leveraging reliable feedback from the summary agent, we guide an iterative reasoning path generation process, retraining the entire multi-agent system in a continuous, self-improving loop. Extensive experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks while preserving strong capabilities on traditional perception-focused tasks.</p> - https://arxiv.org/abs/2603.18118 - Wed, 18 Mar 2026 15:28:07 +0000 + Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells + https://arxiv.org/abs/2603.25240 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Zhang, Guo-Hua Yuan, Chaohao Yuan, Tingyang Xu, Tian Bian, Hong Cheng, Wenbing Huang, Deli Zhao, Yu Rong</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> Modeling cellular states and predicting their responses to perturbations are central challenges in computational biology and the development of virtual cells. Existing foundation models for single-cell transcriptomics provide powerful static representations, but they do not explicitly model the distribution of cellular states for generative simulation. Here, we introduce Lingshu-Cell, a masked discrete diffusion model that learns transcriptomic state distributions and supports conditional simulation under perturbation. By operating directly in a discrete token space that is compatible with the sparse, non-sequential nature of single-cell transcriptomic data, Lingshu-Cell captures complex transcriptome-wide expression dependencies across approximately 18,000 genes without relying on prior gene selection, such as filtering by high variability or ranking by expression level. Across diverse tissues and species, Lingshu-Cell accurately reproduces transcriptomic distributions, marker-gene expression patterns and cell-subtype proportions, demonstrating its ability to capture complex cellular heterogeneity. Moreover, by jointly embedding cell type or donor identity with perturbation, Lingshu-Cell can predict whole-transcriptome expression changes for novel combinations of identity and perturbation. It achieves leading performance on the Virtual Cell Challenge H1 genetic perturbation benchmark and in predicting cytokine-induced responses in human PBMCs. Together, these results establish Lingshu-Cell as a flexible cellular world model for in silico simulation of cell states and perturbation responses, laying the foundation for a new paradigm in biological discovery and perturbation screening.</p> + https://arxiv.org/abs/2603.25240 + Thu, 26 Mar 2026 09:46:27 +0000 - Versatile Editing of Video Content, Actions, and Dynamics without Training - https://arxiv.org/abs/2603.17989 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17989.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vladimir Kulikov, Roni Paiss, Andrey Voynov, Inbar Mosseri, Tali Dekel, Tomer Michaeli</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Controlled video generation has seen drastic improvements in recent years. However, editing actions and dynamic events, or inserting contents that should affect the behaviors of other objects in real-world videos, remains a major challenge. Existing trained models struggle with complex edits, likely due to the difficulty of collecting relevant training data. Similarly, existing training-free methods are inherently restricted to structure- and motion-preserving edits and do not support modification of motion or interactions. Here, we introduce DynaEdit, a training-free editing method that unlocks versatile video editing capabilities with pretrained text-to-video flow models. Our method relies on the recently introduced inversion-free approach, which does not intervene in the model internals, and is thus model-agnostic. We show that naively attempting to adapt this approach to general unconstrained editing results in severe low-frequency misalignment and high-frequency jitter. We explain the sources for these phenomena and introduce novel mechanisms for overcoming them. Through extensive experiments, we show that DynaEdit achieves state-of-the-art results on complex text-based video editing tasks, including modifying actions, inserting objects that interact with the scene, and introducing global effects.</p> - https://arxiv.org/abs/2603.17989 - Wed, 18 Mar 2026 17:50:56 +0000 + Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models + https://arxiv.org/abs/2603.25716 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25716.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaijin Chen, Dingkang Liang, Xin Zhou, Yikang Ding, Xiaoqiang Liu, Pengfei Wan, Xiang Bai</p><p><b>Upvotes:</b> 151</p><p><b>Summary:</b> Video world models have shown immense potential in simulating the physical world, yet existing memory mechanisms primarily treat environments as static canvases. When dynamic subjects hide out of sight and later re-emerge, current methods often struggle, leading to frozen, distorted, or vanishing subjects. To address this, we introduce Hybrid Memory, a novel paradigm requiring models to simultaneously act as precise archivists for static backgrounds and vigilant trackers for dynamic subjects, ensuring motion continuity during out-of-view intervals. To facilitate research in this direction, we construct HM-World, the first large-scale video dataset dedicated to hybrid memory. It features 59K high-fidelity clips with decoupled camera and subject trajectories, encompassing 17 diverse scenes, 49 distinct subjects, and meticulously designed exit-entry events to rigorously evaluate hybrid coherence. Furthermore, we propose HyDRA, a specialized memory architecture that compresses memory into tokens and utilizes a spatiotemporal relevance-driven retrieval mechanism. By selectively attending to relevant motion cues, HyDRA effectively preserves the identity and motion of hidden subjects. Extensive experiments on HM-World demonstrate that our method significantly outperforms state-of-the-art approaches in both dynamic subject consistency and overall generation quality.</p> + https://arxiv.org/abs/2603.25716 + Thu, 26 Mar 2026 17:56:01 +0000 - HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering - https://arxiv.org/abs/2603.18558 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Long-form video question answering requires reasoning over extended temporal contexts, making frame selection critical for large vision-language models (LVLMs) bound by finite context windows. Existing methods face a sharp trade-off: similarity-based selectors are fast but collapse compositional queries into a single dense vector, losing sub-event ordering and cross-modal bindings; agent-based methods recover this structure through iterative LVLM inference, but at prohibitive cost. We introduce HiMu, a training-free framework that bridges this gap. A single text-only LLM call decomposes the query into a hierarchical logic tree whose leaves are atomic predicates, each routed to a lightweight expert spanning vision (CLIP, open-vocabulary detection, OCR) and audio (ASR, CLAP). The resulting signals are normalized, temporally smoothed to align different modalities, and composed bottom-up through fuzzy-logic operators that enforce temporal sequencing and adjacency, producing a continuous satisfaction curve. Evaluations on Video-MME, LongVideoBench and HERBench-Lite show that HiMu advances the efficiency-accuracy Pareto front: at 16 frames with Qwen3-VL 8B it outperforms all competing selectors, and with GPT-4o it surpasses agentic systems operating at 32-512 frames while requiring roughly 10x fewer FLOPs.</p> - https://arxiv.org/abs/2603.18558 - Thu, 19 Mar 2026 07:11:53 +0000 + Natural-Language Agent Harnesses + https://arxiv.org/abs/2603.25723 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25723.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linyue Pan, Lexiao Zou, Shuo Guo, Jingchen Ni, Hai-Tao Zheng</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Agent performance increasingly depends on harness engineering, yet harness design is usually buried in controller code and runtime-specific conventions, making it hard to transfer, compare, and study as a scientific object. We ask whether the high-level control logic of an agent harness can instead be externalized as a portable executable artifact. We introduce Natural-Language Agent Harnesses (NLAHs), which express harness behavior in editable natural language, and Intelligent Harness Runtime (IHR), a shared runtime that executes these harnesses through explicit contracts, durable artifacts, and lightweight adapters. Across coding and computer-use benchmarks, we conduct controlled evaluations of operational viability, module ablation, and code-to-text harness migration.</p> + https://arxiv.org/abs/2603.25723 + Thu, 26 Mar 2026 17:58:15 +0000 - MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution - https://arxiv.org/abs/2603.18718 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18718.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minhua Lin, Zhiwei Zhang, Hanqing Lu, Hui Liu, Xianfeng Tang, Qi He, Xiang Zhang, Suhang Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled challenges: strategic blindness on the forward path of the memory cycle, where construction and retrieval are driven by local heuristics rather than explicit strategic reasoning, and sparse, delayed supervision on the backward path, where downstream failures rarely translate into direct repairs of the memory bank. To address these challenges, we propose MemMA, a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths. On the forward path, a Meta-Thinker produces structured guidance that steers a Memory Manager during construction and directs a Query Reasoner during iterative retrieval. On the backward path, MemMA introduces in-situ self-evolving memory construction, which synthesizes probe QA pairs, verifies the current memory, and converts failures into repair actions before the memory is finalized. Extensive experiments on LoCoMo show that MemMA consistently outperforms existing baselines across multiple LLM backbones and improves three different storage backends in a plug-and-play manner. Our code is publicly available at https://github.com/ventr1c/memma.</p> - https://arxiv.org/abs/2603.18718 - Thu, 19 Mar 2026 10:15:59 +0000 + PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference + https://arxiv.org/abs/2603.25730 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaofeng Mao, Shaohao Rui, Kaining Ying, Bo Zheng, Chuanhao Li, Mingmin Chi, Kaipeng Zhang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-k context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing</p> + https://arxiv.org/abs/2603.25730 + Thu, 26 Mar 2026 17:59:05 +0000 - Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation - https://arxiv.org/abs/2603.18795 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18795.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Li, Amanmeet Garg, Shalini Chaudhuri, Rui Zhao, Garin Kessler</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large Vision Language Models (LVLMs) excel at semantic understanding but struggle with fine grained spatial grounding, as the model must implicitly infer complex geometry without ever producing a spatial interpretation. We present Perceptio, a perception enhanced LVLM with 2D and 3D spatial reasoning abilities, enabled via explicit semantic segmentation tokens and depth tokens generated directly within the autoregressive sequence. Concretely, we (i) distill a VQVAE depth codebook from a strong monocular teacher to tokenize dense depth into compact sequences, and (ii) integrate SAM2 based semantic segmentation tokens and VQ-VAE depth tokens inside the LLM so the model first emits spatial tokens and then answers. To stabilize depth token generation, we introduce novel composite depth-token objectives (marker, token, and count losses) and a soft-merging technique for differentiable reconstruction. We adopt a multi-task co-training strategy across diverse datasets, letting the model learn perception tokens to tackle multiple downstream tasks. Building on InternVL, Perceptio achieves state-of-the-art performance across benchmarks: improving referring expression segmentation by +0.8/+1.4/+1.1 cIoU on RefCOCO/+/g HardBLINK spatial understanding accuracy by 10.3%, and MMBench accuracy by 1.0%, demonstrating that explicit spatial chain-of-thought materially strengthens spatial grounding in LVLMs.</p> - https://arxiv.org/abs/2603.18795 - Thu, 19 Mar 2026 11:46:01 +0000 + BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation + https://arxiv.org/abs/2603.25732 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25732.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Li, Zezi Zeng, Ziwei Zhou, Xin Gao, Muzhao Tian, Yifan Yang, Mingxi Cheng, Qi Dai, Yuqing Yang, Lili Qiu, Zhendong Wang, Zhengyuan Yang, Xue Yang, Lijuan Wang, Ji Li, Chong Luo</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent advances in image generation models have expanded their applications beyond aesthetic imagery toward practical visual content creation. However, existing benchmarks mainly focus on natural image synthesis and fail to systematically evaluate models under the structured and multi-constraint requirements of real-world commercial design tasks. In this work, we introduce BizGenEval, a systematic benchmark for commercial visual content generation. The benchmark spans five representative document types: slides, charts, webpages, posters, and scientific figures, and evaluates four key capability dimensions: text rendering, layout control, attribute binding, and knowledge-based reasoning, forming 20 diverse evaluation tasks. BizGenEval contains 400 carefully curated prompts and 8000 human-verified checklist questions to rigorously assess whether generated images satisfy complex visual and semantic constraints. We conduct large-scale benchmarking on 26 popular image generation systems, including state-of-the-art commercial APIs and leading open-source models. The results reveal substantial capability gaps between current generative models and the requirements of professional visual content creation. We hope BizGenEval serves as a standardized benchmark for real-world commercial visual content generation.</p> + https://arxiv.org/abs/2603.25732 + Thu, 26 Mar 2026 17:59:16 +0000 - AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science - https://arxiv.org/abs/2603.19005 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19005.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, Ashish Kundu, Jayanth Srinivasa, Mingyi Hong, Rui Zhang, Tianxi Li, Galin Jones, Jie Ding</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data science workflow. However, it remains unclear to what extent AI agents can match the performance of human experts on domain-specific data science tasks, and in which aspects human expertise continues to provide advantages. We introduce AgentDS, a benchmark and competition designed to evaluate both AI agents and human-AI collaboration performance in domain-specific data science. AgentDS consists of 17 challenges across six industries: commerce, food production, healthcare, insurance, manufacturing, and retail banking. We conducted an open competition involving 29 teams and 80 participants, enabling systematic comparison between human-AI collaborative approaches and AI-only baselines. Our results show that current AI agents struggle with domain-specific reasoning. AI-only baselines perform near or below the median of competition participants, while the strongest solutions arise from human-AI collaboration. These findings challenge the narrative of complete automation by AI and underscore the enduring importance of human expertise in data science, while illuminating directions for the next generation of AI. Visit the AgentDS website here: https://agentds.org/ and open source datasets here: https://huggingface.co/datasets/lainmn/AgentDS .</p> - https://arxiv.org/abs/2603.19005 - Thu, 19 Mar 2026 15:11:13 +0000 - - - SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models - https://arxiv.org/abs/2603.19028 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19028.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate directly in the dense CLIP embedding space, where bias and task-relevant information are highly entangled. This entanglement limits their ability to remove bias without degrading semantic fidelity. In this work, we propose Sparse Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder (SAE) latent space. By decomposing CLIP text embeddings into disentangled features, SEM identifies and modulates bias-relevant neurons while preserving query-relevant ones. This enables more precise, non-linear interventions. Across four benchmark datasets and two CLIP backbones, SEM achieves substantial fairness gains in retrieval and zero-shot classification. Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of vision-language models.</p> - https://arxiv.org/abs/2603.19028 - Thu, 19 Mar 2026 15:28:08 +0000 - - - TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation - https://arxiv.org/abs/2603.19039 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19039.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations. To address this problem, we introduce TerraScope, a unified VLM that delivers pixel-grounded geospatial reasoning with two key capabilities: (1) modality-flexible reasoning: it handles single-modality inputs (optical or SAR) and adaptively fuses different modalities into the reasoning process when both are available; (2) multi-temporal reasoning: it integrates temporal sequences for change analysis across multiple time points. In addition, we curate Terra-CoT, a large-scale dataset containing 1 million samples with pixel-level masks embedded in reasoning chains across multiple sources. We also propose TerraScope-Bench, the first benchmark for pixel-grounded geospatial reasoning with six sub-tasks that evaluates both answer accuracy and mask quality to ensure authentic pixel-grounded reasoning. Experiments show that TerraScope significantly outperforms existing VLMs on pixel-grounded geospatial reasoning while providing interpretable visual evidence.</p> - https://arxiv.org/abs/2603.19039 - Thu, 19 Mar 2026 15:38:02 +0000 - - - BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs - https://arxiv.org/abs/2603.20309 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duyi Pan, Tianao Lou, Xin Li, Haoze Song, Yiwen Wu, Mengyi Deng, Mingyu Yang, Wei Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Large Language Models (LLMs) exhibit hallucinations in knowledge-intensive tasks. Graph-based retrieval augmented generation (RAG) has emerged as a promising solution, yet existing approaches suffer from fundamental recall and precision limitations when operating over black-box knowledge graphs -- graphs whose schema and structure are unknown in advance. We identify three core challenges that cause recall loss (semantic instantiation uncertainty and structural path uncertainty) and precision loss (evidential comparison uncertainty). To address these challenges, we formalize the retrieval task as the Optimal Informative Subgraph Retrieval (OISR) problem -- a variant of Group Steiner Tree -- and prove it to be NP-hard and APX-hard. We propose BubbleRAG, a training-free pipeline that systematically optimizes for both recall and precision through semantic anchor grouping, heuristic bubble expansion to discover candidate evidence graphs (CEGs), composite ranking, and reasoning-aware expansion. Experiments on multi-hop QA benchmarks demonstrate that BubbleRAG achieves state-of-the-art results, outperforming strong baselines in both F1 and accuracy while remaining plug-and-play.</p> - https://arxiv.org/abs/2603.20309 - Thu, 19 Mar 2026 16:00:36 +0000 - - - Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders - https://arxiv.org/abs/2603.19209 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shang-Jui Ray Kuo, Paola Cascante-Bonilla</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large vision--language models (VLMs) often use a frozen vision backbone, whose image features are mapped into a large language model through a lightweight connector. While transformer-based encoders are the standard visual backbone, we ask whether state space model (SSM) vision backbones can be a strong alternative. We systematically evaluate SSM vision backbones for VLMs in a controlled setting. Under matched ImageNet-1K initialization, the SSM backbone achieves the strongest overall performance across both VQA and grounding/localization. We further adapt both SSM and ViT-family backbones with detection or segmentation training and find that dense-task tuning generally improves performance across families; after this adaptation, the SSM backbone remains competitive while operating at a substantially smaller model scale. We further observe that (i) higher ImageNet accuracy or larger backbones do not reliably translate into better VLM performance, and (ii) some visual backbones are unstable in localization. Based on these findings, we propose stabilization strategies that improve robustness for both backbone families and highlight SSM backbones as a strong alternative to transformer-based vision encoders in VLMs.</p> - https://arxiv.org/abs/2603.19209 - Thu, 19 Mar 2026 17:56:32 +0000 - - - Scalable Prompt Routing via Fine-Grained Latent Task Discovery - https://arxiv.org/abs/2603.19415 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19415.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunyi Zhang, Soji Adeshina, Patrick Guan, Ashwin Ganesh, Zhen Han, Vassilis N. Ioannidis, Huzefa Rangwala, George Karypis</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.</p> - https://arxiv.org/abs/2603.19415 - Thu, 19 Mar 2026 19:15:51 +0000 - - - Hyperagents - https://arxiv.org/abs/2603.19461 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19461.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster, Jeff Clune, Minqi Jiang, Sam Devlin, Tatiana Shavrina</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin Gödel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly generating and evaluating self-modified variants. Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. However, this alignment does not generally hold beyond coding domains. We introduce hyperagents, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program. Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements. We instantiate this framework by extending DGM to create DGM-Hyperagents (DGM-H), eliminating the assumption of domain-specific alignment between task performance and self-modification skill to potentially support self-accelerating progress on any computable task. Across diverse domains, the DGM-H improves performance over time and outperforms baselines without self-improvement or open-ended exploration, as well as prior self-improving systems. Furthermore, the DGM-H improves the process by which it generates new agents (e.g., persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. DGM-Hyperagents offer a glimpse of open-ended AI systems that do not merely search for better solutions, but continually improve their search for how to improve.</p> - https://arxiv.org/abs/2603.19461 - Thu, 19 Mar 2026 20:50:08 +0000 - - - ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models - https://arxiv.org/abs/2603.19466 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thomas De Min, Subhankar Roy, Stéphane Lathuilière, Elisa Ricci, Massimiliano Mancini</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting simple user interventions? To investigate this, we introduce ProactiveBench, a benchmark built from seven repurposed datasets that tests proactiveness across different tasks such as recognizing occluded objects, enhancing image quality, and interpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness; (ii) proactiveness does not correlate with model capacity; (iii) "hinting" at proactiveness yields only marginal gains. Surprisingly, we found that conversation histories and in-context learning introduce negative biases, hindering performance. Finally, we explore a simple fine-tuning strategy based on reinforcement learning: its results suggest that proactiveness can be learned, even generalizing to unseen scenarios. We publicly release ProactiveBench as a first step toward building proactive multimodal models.</p> - https://arxiv.org/abs/2603.19466 - Thu, 19 Mar 2026 20:58:03 +0000 - - - Teaching an Agent to Sketch One Part at a Time - https://arxiv.org/abs/2603.19500 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaodan Du, Ruize Xu, David Yunis, Yael Vinker, Greg Shakhnarovich</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We develop a method for producing vector sketches one part at a time. To do this, we train a multi-modal language model-based agent using a novel multi-turn process-reward reinforcement learning following supervised fine-tuning. Our approach is enabled by a new dataset we call ControlSketch-Part, containing rich part-level annotations for sketches, obtained using a novel, generic automatic annotation pipeline that segments vector sketches into semantic parts and assigns paths to parts with a structured multi-stage labeling process. Our results indicate that incorporating structured part-level data and providing agent with the visual feedback through the process enables interpretable, controllable, and locally editable text-to-vector sketch generation.</p> - https://arxiv.org/abs/2603.19500 - Thu, 19 Mar 2026 22:08:53 +0000 - - - FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow - https://arxiv.org/abs/2603.19598 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19598.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhifei Yang, Guangyao Zhai, Keyang Lu, YuYang Yin, Chao Zhang, Zhen Xiao, Jieyi Long, Nassir Navab, Yikai Wang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook object-level control and often fail to enforce scene-level style coherence. Graph-based formulations offer higher controllability over objects and inform holistic consistency by explicitly modeling relations, yet existing methods struggle to produce high-fidelity textured results, thereby limiting their practical utility. We present FlowScene, a tri-branch scene generative model conditioned on multimodal graphs that collaboratively generates scene layouts, object shapes, and object textures. At its core lies a tight-coupled rectified flow model that exchanges object information during generation, enabling collaborative reasoning across the graph. This enables fine-grained control of objects' shapes, textures, and relations while enforcing scene-level style coherence across structure and appearance. Extensive experiments show that FlowScene outperforms both language-conditioned and graph-conditioned baselines in terms of generation realism, style consistency, and alignment with human preferences.</p> - https://arxiv.org/abs/2603.19598 - Fri, 20 Mar 2026 03:15:42 +0000 - - - BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection - https://arxiv.org/abs/2603.19635 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19635.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengpei Hu, Kai Li, Dapeng Fu, Chang Zeng, Yue Li, Yuanhao Tang, Jianqiang Huang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning. In this paper, we propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection. BEAVER maximizes hardware parallelism by mapping variable-length contexts into dense page-level tensors via dual-path pooling, and preserves discourse integrity through a hybrid planner combining semantic and lexical dual-branch selection with sentence smoothing. Extensive evaluations on four long-context benchmarks demonstrate that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua. Notably, on the RULER benchmark, BEAVER maintains high fidelity in multi-needle retrieval where baselines deteriorate. Regarding efficiency, BEAVER reduces latency by 26.4x on 128k contexts, offering a scalable solution for high-throughput applications. Our code is available at https://cslikai.cn/BEAVER/.</p> - https://arxiv.org/abs/2603.19635 - Fri, 20 Mar 2026 04:35:04 +0000 - - - A Subgoal-driven Framework for Improving Long-Horizon LLM Agents - https://arxiv.org/abs/2603.19685 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19685.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taiyi Wang, Sian Gooding, Florian Hartmann, Oriana Riva, Edward Grefenstette</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic content and long sequences of actions, making it particularly challenging. Existing LLM-based agents struggle with long-horizon planning in two main ways. During online execution, they often lose track as new information arrives, lacking a clear and adaptive path toward the final goal. This issue is further exacerbated during reinforcement learning (RL) fine-tuning, where sparse and delayed rewards make it difficult for agents to identify which actions lead to success, preventing them from maintaining coherent reasoning over extended tasks. To address these challenges, we propose two contributions. First, we introduce an agent framework that leverages proprietary models for online planning through subgoal decomposition. Second, we present MiRA (Milestoning your Reinforcement Learning Enhanced Agent), an RL training framework that uses dense, milestone-based reward signals. The real-time planning mechanism improves proprietary models such as Gemini by approximately a 10% absolute increase in success rate (SR) on the WebArena-Lite benchmark. Meanwhile, applying MiRA to the open Gemma3-12B model increases its success rate from 6.4% to 43.0%. This performance surpasses proprietary systems such as GPT-4-Turbo (17.6%) and GPT-4o (13.9%), as well as the previous open-model state of the art, WebRL (38.4%). Overall, our findings demonstrate that combining explicit inference-time planning with milestone-based rewards significantly improves an agent's long-horizon capabilities, paving the way for more robust and general-purpose autonomous systems.</p> - https://arxiv.org/abs/2603.19685 - Fri, 20 Mar 2026 06:32:16 +0000 - - - WorldAgents: Can Foundation Image Models be Agents for 3D World Models? - https://arxiv.org/abs/2603.19708 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19708.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziya Erkoç, Angela Dai, Matthias Nießner</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Given the remarkable ability of 2D foundation image models to generate high-fidelity outputs, we investigate a fundamental question: do 2D foundation image models inherently possess 3D world model capabilities? To answer this, we systematically evaluate multiple state-of-the-art image generation models and Vision-Language Models (VLMs) on the task of 3D world synthesis. To harness and benchmark their potential implicit 3D capability, we propose an agentic framing to facilitate 3D world generation. Our approach employs a multi-agent architecture: a VLM-based director that formulates prompts to guide image synthesis, a generator that synthesizes new image views, and a VLM-backed two-step verifier that evaluates and selectively curates generated frames from both 2D image and 3D reconstruction space. Crucially, we demonstrate that our agentic approach provides coherent and robust 3D reconstruction, producing output scenes that can be explored by rendering novel views. Through extensive experiments across various foundation models, we demonstrate that 2D models do indeed encapsulate a grasp of 3D worlds. By exploiting this understanding, our method successfully synthesizes expansive, realistic, and 3D-consistent worlds.</p> - https://arxiv.org/abs/2603.19708 - Fri, 20 Mar 2026 07:22:41 +0000 - - - LoopRPT: Reinforcement Pre-Training for Looped Language Models - https://arxiv.org/abs/2603.19714 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guo Tang, Shixin Jiang, Heng Chang, Nuo Chen, Yuhan Li, Huiming Fan, Jia Li, Ming Liu, Bing Qin</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Looped language models (LoopLMs) perform iterative latent computation to refine internal representations, offering a promising alternative to explicit chain-of-thought (CoT) reasoning. However, existing reinforcement learning (RL) paradigms primarily target output tokens, creating a structural mismatch with looped architectures whose reasoning unfolds implicitly. In this work, we propose LoopRPT, a reinforcement pre-training framework tailored for LoopLMs. By reframing next-token prediction as a next-token reasoning task, LoopRPT assigns reinforcement signals directly to latent steps using an EMA teacher reference and noisy latent rollouts. This formulation enables RL to directly shape intermediate representations, compressing effective reasoning into fewer iterations. We instantiate LoopRPT on the Ouro architecture across multiple model scales. Results demonstrate that LoopRPT consistently improves per-step representation quality, achieving Pareto dominance in accuracy-computation trade-offs. Notably, significant gains on hard tokens indicate that LoopRPT enhances early-stage reasoning rather than merely encouraging premature exits. Our findings highlight reinforcement pre-training as a principled paradigm for learning efficient latent reasoning in LoopLMs.</p> - https://arxiv.org/abs/2603.19714 - Fri, 20 Mar 2026 07:35:38 +0000 - - - How Well Does Generative Recommendation Generalize? - https://arxiv.org/abs/2603.19809 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijie Ding, Zitian Guo, Jiacheng Li, Letian Peng, Shuai Shao, Wei Shao, Xiaoqiang Luo, Luke Simon, Jingbo Shang, Julian McAuley, Yupeng Hou</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> A widely held hypothesis for why generative recommendation (GR) models outperform conventional item ID-based models is that they generalize better. However, there is few systematic way to verify this hypothesis beyond a superficial comparison of overall performance. To address this gap, we categorize each data instance based on the specific capability required for a correct prediction: either memorization (reusing item transition patterns observed during training) or generalization (composing known patterns to predict unseen item transitions). Extensive experiments show that GR models perform better on instances that require generalization, whereas item ID-based models perform better when memorization is more important. To explain this divergence, we shift the analysis from the item level to the token level and show that what appears to be item-level generalization often reduces to token-level memorization for GR models. Finally, we show that the two paradigms are complementary. We propose a simple memorization-aware indicator that adaptively combines them on a per-instance basis, leading to improved overall recommendation performance.</p> - https://arxiv.org/abs/2603.19809 - Fri, 20 Mar 2026 09:48:57 +0000 - - - Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States - https://arxiv.org/abs/2603.19987 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19987.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yurun Yuan, Tengyang Xie</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Reinforcement learning (RL) has become a standard paradigm for post-training and aligning Large Language Models (LLMs), yet recent evidence suggests it faces a persistent "capability ceiling": unlike classical RL systems that discover novel strategies, RL for LLMs often acts as a mere refiner of patterns already latent in pre-trained weights. In this work, we identify a fundamental structural bottleneck: while classical RL relies on compact, informative Markov states, current LLM post-training formulations are tethered to an ever-expanding history of actions. We revisit a classical principle long central to RL yet absent from LLM post-training: explicit Markov states. Theoretically, we provide rigorous guarantees demonstrating that leveraging estimated Markov states can significantly reduce sample complexity. Empirically, we show that introducing Markov states consistently breaks the performance boundaries of standard RL post-training across a suite of complex logic puzzles. Our findings suggest that moving beyond "history-as-state" modeling in favor of structured Markovian representations is essential for unlocking open-ended discovery and genuinely new reasoning capabilities in Generative AI.</p> - https://arxiv.org/abs/2603.19987 - Fri, 20 Mar 2026 14:35:49 +0000 - - - The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus - https://arxiv.org/abs/2603.20105 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20105.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amartya Roy, Rasul Tutunov, Xiaotong Ji, Matthieu Zimmer, Haitham Bou-Ammar</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs) address this by externalising the prompt and recursively solving subproblems. Yet existing RLMs depend on an open-ended read-eval-print loop (REPL) in which the model generates arbitrary control code, making execution difficult to verify, predict, and analyse. We introduce λ-RLM, a framework for long-context reasoning that replaces free-form recursive code generation with a typed functional runtime grounded in λ-calculus. It executes a compact library of pre-verified combinators and uses neural inference only on bounded leaf subproblems, turning recursive reasoning into a structured functional program with explicit control flow. We show that λ-RLM admits formal guarantees absent from standard RLMs, including termination, closed-form cost bounds, controlled accuracy scaling with recursion depth, and an optimal partition rule under a simple cost model. Empirically, across four long-context reasoning tasks and nine base models, λ-RLM outperforms standard RLM in 29 of 36 model-task comparisons, improves average accuracy by up to +21.9 points across model tiers, and reduces latency by up to 4.1x. These results show that typed symbolic control yields a more reliable and efficient foundation for long-context reasoning than open-ended recursive code generation. The complete implementation of λ-RLM, is open-sourced for the community at: https://github.com/lambda-calculus-LLM/lambda-RLM.</p> - https://arxiv.org/abs/2603.20105 - Fri, 20 Mar 2026 16:29:51 +0000 - - - AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI - https://arxiv.org/abs/2603.22327 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shreyansh Padarha, Ryan Othniel Kearns, Tristan Naidoo, Lingyi Yang, Łukasz Borchmann, Piotr BŁaszczyk, Christian Morgenstern, Ruth McCabe, Sangeeta Bhatia, Philip H. Torr, Jakob Foerster, Scott A. Hale, Thomas Rawson, Anne Cori, Elizaveta Semenova, Adam Mahdi</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Systematic literature reviews are essential for synthesizing scientific evidence but are costly, difficult to scale and time-intensive, creating bottlenecks for evidence-based policy. We study whether large language models can automate the complete systematic review workflow, from article retrieval, article screening, data extraction to report synthesis. Applied to epidemiological reviews of nine WHO-designated priority pathogens and validated against expert-curated ground truth, our open-source agentic pipeline (AgentSLR) achieves performance comparable to human researchers while reducing review time from approximately 7 weeks to 20 hours (a 58x speed-up). Our comparison of five frontier models reveals that performance on SLR is driven less by model size or inference cost than by each model's distinctive capabilities. Through human-in-the-loop validation, we identify key failure modes. Our results demonstrate that agentic AI can substantially accelerate scientific evidence synthesis in specialised domains.</p> - https://arxiv.org/abs/2603.22327 - Fri, 20 Mar 2026 17:11:58 +0000 - - - Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD - https://arxiv.org/abs/2603.20155 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20155.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Emiel Hoogeboom, David Ruhe, Jonathan Heek, Thomas Mensink, Tim Salimans</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps to a handful. Our method, Discrete Moment Matching Distillation (D-MMD), leverages ideas that have been highly successful in the continuous domain. Whereas previous discrete distillation methods collapse, D-MMD maintains high quality and diversity (given sufficient sampling steps). This is demonstrated on both text and image datasets. Moreover, the newly distilled generators can outperform their teachers.</p> - https://arxiv.org/abs/2603.20155 - Fri, 20 Mar 2026 17:29:12 +0000 - - - EgoForge: Goal-Directed Egocentric World Simulator - https://arxiv.org/abs/2603.20169 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Shen, Jiateng Liu, Xinzhuo Li, Yuanzhe Liu, Bingxuan Li, Houze Yang, Wenqi Jia, Yijiang Li, Tianjiao Yu, James Matthew Rehg, Xu Cao, Ismini Lourentzou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object interactions, and goal-directed procedures whose evolution depends on latent human intent. Existing approaches either focus on hand-centric instructional synthesis with limited scene evolution, perform static view translation without modeling action dynamics, or rely on dense supervision, such as camera trajectories, long video prefixes, synchronized multicamera capture, etc. In this work, we introduce EgoForge, an egocentric goal-directed world simulator that generates coherent, first-person video rollouts from minimal static inputs: a single egocentric image, a high-level instruction, and an optional auxiliary exocentric view. To improve intent alignment and temporal consistency, we propose VideoDiffusionNFT, a trajectory-level reward-guided refinement that optimizes goal completion, temporal causality, scene consistency, and perceptual fidelity during diffusion sampling. Extensive experiments show EgoForge achieves consistent gains in semantic alignment, geometric stability, and motion fidelity over strong baselines, and robust performance in real-world smart-glasses experiments.</p> - https://arxiv.org/abs/2603.20169 - Fri, 20 Mar 2026 17:46:55 +0000 - - - LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis - https://arxiv.org/abs/2603.20176 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20176.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Stanislaw Szymanowicz, Minghao Chen, Jianyuan Wang, Christian Rupprecht, Andrea Vedaldi</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent work has shown that neural networks can perform 3D tasks such as Novel View Synthesis (NVS) without explicit 3D reconstruction. Even so, we argue that strong 3D inductive biases are still helpful in the design of such networks. We show this point by introducing LagerNVS, an encoder-decoder neural network for NVS that builds on `3D-aware' latent features. The encoder is initialized from a 3D reconstruction network pre-trained using explicit 3D supervision. This is paired with a lightweight decoder, and trained end-to-end with photometric losses. LagerNVS achieves state-of-the-art deterministic feed-forward Novel View Synthesis (including 31.4 PSNR on Re10k), with and without known cameras, renders in real time, generalizes to in-the-wild data, and can be paired with a diffusion decoder for generative extrapolation.</p> - https://arxiv.org/abs/2603.20176 - Fri, 20 Mar 2026 17:53:06 +0000 - - - LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation - https://arxiv.org/abs/2603.20192 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiazheng Xing, Fei Du, Hangjie Yuan, Pengwei Liu, Hongbin Xu, Hai Ci, Ruigang Niu, Weihua Chen, Fan Wang, Yong Liu</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and background elements. However, precise face-attribute alignment across subjects remains challenging, as existing methods lack explicit mechanisms to ensure intra-group consistency. Addressing this gap requires both explicit modeling strategies and face-attribute-aware data resources. We therefore propose LumosX, a framework that advances both data and model design. On the data side, a tailored collection pipeline orchestrates captions and visual cues from independent videos, while multimodal large language models (MLLMs) infer and assign subject-specific dependencies. These extracted relational priors impose a finer-grained structure that amplifies the expressive control of personalized video generation and enables the construction of a comprehensive benchmark. On the modeling side, Relational Self-Attention and Relational Cross-Attention intertwine position-aware embeddings with refined attention dynamics to inscribe explicit subject-attribute dependencies, enforcing disciplined intra-group cohesion and amplifying the separation between distinct subject clusters. Comprehensive evaluations on our benchmark demonstrate that LumosX achieves state-of-the-art performance in fine-grained, identity-consistent, and semantically aligned personalized multi-subject video generation. Code and models are available at https://jiazheng-xing.github.io/lumosx-home/.</p> - https://arxiv.org/abs/2603.20192 - Fri, 20 Mar 2026 17:59:46 +0000 - - - PEARL: Personalized Streaming Video Understanding Model - https://arxiv.org/abs/2603.20422 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanhong Zheng, Ruichuan An, Xiaopeng Lin, Yuxing Liu, Sihan Yang, Huanyu Zhang, Haodong Li, Qintong Zhang, Renrui Zhang, Guopeng Li, Yifan Zhang, Yuheng Li, Wentao Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Human cognition of new concepts is inherently a streaming process: we continuously recognize new objects or identities and update our memories over time. However, current multimodal personalization methods are largely limited to static images or offline videos. This disconnects continuous visual input from instant real-world feedback, limiting their ability to provide the real-time, interactive personalized responses essential for future AI assistants. To bridge this gap, we first propose and formally define the novel task of Personalized Streaming Video Understanding (PSVU). To facilitate research in this new direction, we introduce PEARL-Bench, the first comprehensive benchmark designed specifically to evaluate this challenging setting. It evaluates a model's ability to respond to personalized concepts at exact timestamps under two modes: (1) Frame-level, focusing on a specific person or object in discrete frames, and (2) a novel Video-level, focusing on personalized actions unfolding across continuous frames. PEARL-Bench comprises 132 unique videos and 2,173 fine-grained annotations with precise timestamps. Concept diversity and annotation quality are strictly ensured through a combined pipeline of automated generation and human verification. To tackle this challenging new setting, we further propose PEARL, a plug-and-play, training-free strategy that serves as a strong baseline. Extensive evaluations across 8 offline and online models demonstrate that PEARL achieves state-of-the-art performance. Notably, it brings consistent PSVU improvements when applied to 3 distinct architectures, proving to be a highly effective and robust strategy. We hope this work advances vision-language model (VLM) personalization and inspires further research into streaming personalized AI assistants. Code is available at https://github.com/Yuanhong-Zheng/PEARL.</p> - https://arxiv.org/abs/2603.20422 - Fri, 20 Mar 2026 18:47:54 +0000 - - - Agentic AI and the next intelligence explosion - https://arxiv.org/abs/2603.20639 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20639.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> James Evans, Benjamin Bratton, Blaise Agüera y Arcas</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> The "AI singularity" is often miscast as a monolithic, godlike mind. Evolution suggests a different path: intelligence is fundamentally plural, social, and relational. Recent advances in agentic AI reveal that frontier reasoning models, such as DeepSeek-R1, do not improve simply by "thinking longer". Instead, they simulate internal "societies of thought," spontaneous cognitive debates that argue, verify, and reconcile to solve complex tasks. Moreover, we are entering an era of human-AI centaurs: hybrid actors where collective agency transcends individual control. Scaling this intelligence requires shifting from dyadic alignment (RLHF) toward institutional alignment. By designing digital protocols, modeled on organizations and markets, we can build a social infrastructure of checks and balances. The next intelligence explosion will not be a single silicon brain, but a complex, combinatorial society specializing and sprawling like a city. No mind is an island.</p> - https://arxiv.org/abs/2603.20639 - Sat, 21 Mar 2026 04:23:11 +0000 - - - REVERE: Reflective Evolving Research Engineer for Scientific Workflows - https://arxiv.org/abs/2603.20667 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured merges, resulting in knowledge loss. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories, underspecified environments, and weak feedback, where reproducing results from public codebases is an established evaluation regime. We introduce Reflective Evolving Research Engineer (REVERE), a framework that continuously learns from Global Training Context, recognizes recurring failure modes in cross-repository execution trajectories, distills them into reusable heuristics, and performs targeted edits across three configurable fields: the system prompt, a task-prompt template, and a cumulative cheatsheet. REVERE, via this reflective optimization framework, improves performance over prior state-of-the-art expert-crafted instructions on research coding tasks by 4.50% on SUPER, 3.51% on ResearchCodeBench, and 4.89% on ScienceAgentBench across their respective metrics. These results demonstrate that agents equipped with mechanisms for continual learning and global memory consolidation can meaningfully evolve their capabilities over time.</p> - https://arxiv.org/abs/2603.20667 - Sat, 21 Mar 2026 05:58:30 +0000 - - - T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search - https://arxiv.org/abs/2603.22341 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyomin Lee, Sangwoo Park, Yumin Choi, Sohyun An, Seanie Lee, Sung Ju Hwang</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protocol (MCP). To address this gap, we propose a trajectory-aware evolutionary search method, T-MAP, which leverages execution trajectories to guide the discovery of adversarial prompts. Our approach enables the automatic generation of attacks that not only bypass safety guardrails but also reliably realize harmful objectives through actual tool interactions. Empirical evaluations across diverse MCP environments demonstrate that T-MAP substantially outperforms baselines in attack realization rate (ARR) and remains effective against frontier models, including GPT-5.2, Gemini-3-Pro, Qwen3.5, and GLM-5, thereby revealing previously underexplored vulnerabilities in autonomous LLM agents.</p> - https://arxiv.org/abs/2603.22341 - Sat, 21 Mar 2026 12:33:34 +0000 - - - 2Xplat: Two Experts Are Better Than One Generalist - https://arxiv.org/abs/2603.21064 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21064.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hwasik Jeong, Seungryong Lee, Gyeongjin Kang, Seungkwon Yang, Xiangyu Sun, Seungtae Nam, Eunbyung Park</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Pose-free feed-forward 3D Gaussian Splatting (3DGS) has opened a new frontier for rapid 3D modeling, enabling high-quality Gaussian representations to be generated from uncalibrated multi-view images in a single forward pass. The dominant approach in this space adopts unified monolithic architectures, often built on geometry-centric 3D foundation models, to jointly estimate camera poses and synthesize 3DGS representations within a single network. While architecturally streamlined, such "all-in-one" designs may be suboptimal for high-fidelity 3DGS generation, as they entangle geometric reasoning and appearance modeling within a shared representation. In this work, we introduce 2Xplat, a pose-free feed-forward 3DGS framework based on a two-expert design that explicitly separates geometry estimation from Gaussian generation. A dedicated geometry expert first predicts camera poses, which are then explicitly passed to a powerful appearance expert that synthesizes 3D Gaussians. Despite its conceptual simplicity, being largely underexplored in prior works, the proposed approach proves highly effective. In fewer than 5K training iterations, the proposed two-experts pipeline substantially outperforms prior pose-free feed-forward 3DGS approaches and achieves performance on par with state-of-the-art posed methods. These results challenge the prevailing unified paradigm and suggest the potential advantages of modular design principles for complex 3D geometric estimation and appearance synthesis tasks.</p> - https://arxiv.org/abs/2603.21064 - Sun, 22 Mar 2026 05:14:38 +0000 - - - LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning - https://arxiv.org/abs/2603.21065 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21065.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianing Wang, Jianfei Zhang, Qi Guo, Linsen Guo, Rumei Li, Chao Zhang, Chong Peng, Cunguang Wang, Dengchang Zhao, Jiarong Shi, Jingang Wang, Liulin Feng, Mengxia Shen, Qi Li, Shengnan An, Shun Wang, Wei Shi, Xiangyu Xi, Xiaoyu Li, Xuezhi Cao, Yi Lu, Yunke Zhao, Zhengyu Chen, Zhimin Lin, Wei Wang, Peng Pei, Xunliang Cai</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent formal capabilities, i.e., auto-formalization, sketching, and proving. To facilitate these capabilities, we propose a Hybrid-Experts Iteration Framework to expand high-quality task trajectories, including generating a formal statement based on a given informal problem, producing a whole-proof directly from the statement, or a lemma-style sketch. During agentic RL, we present a Hierarchical Importance Sampling Policy Optimization (HisPO) algorithm, which aims to stabilize the MoE model training on such long-horizon tasks. It employs a gradient masking strategy that accounts for the policy staleness and the inherent train-inference engine discrepancies at both sequence and token levels. Additionally, we also incorporate theorem consistency and legality detection mechanisms to eliminate reward hacking issues. Extensive evaluations show that our LongCat-Flash-Prover sets a new state-of-the-art for open-weights models in both auto-formalization and theorem proving. Demonstrating remarkable sample efficiency, it achieves a 97.1% pass rate on MiniF2F-Test using only 72 inference budget per problem. On more challenging benchmarks, it solves 70.8% of ProverBench and 41.5% of PutnamBench with no more than 220 attempts per problem, significantly outperforming existing open-weights baselines.</p> - https://arxiv.org/abs/2603.21065 - Sun, 22 Mar 2026 05:16:09 +0000 - - - When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning - https://arxiv.org/abs/2603.21289 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21289.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxian Wu, Kai Shi, Chuanrui Zhang, Zirui Liao, Jun Yang, Ni Yang, Qiuying Peng, Luyuan Zhang, Hangrui Xu, Tianhuang Su, Zhenyu Yang, Haonan Lu, Haoqian Wang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge.</p> - https://arxiv.org/abs/2603.21289 - Sun, 22 Mar 2026 15:22:19 +0000 - - - F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting - https://arxiv.org/abs/2603.21304 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians.</p> - https://arxiv.org/abs/2603.21304 - Sun, 22 Mar 2026 16:03:56 +0000 - - - RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models - https://arxiv.org/abs/2603.21341 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21341.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jinwoo Shin, Jaehyung Kim, Younggyo Seo</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1\% of the data, RoboAlign achieves performance improvements of 17.5\%, 18.9\%, and 106.6\% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.</p> - https://arxiv.org/abs/2603.21341 - Sun, 22 Mar 2026 17:57:55 +0000 - - - Generalized Discrete Diffusion from Snapshots - https://arxiv.org/abs/2603.21342 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Oussama Zekri, Théo Uscidda, Nicolas Boullé, Anna Korba</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on uniformization and enables fast arbitrary corruption. For the reverse process, we derive a simple evidence lower bound (ELBO) based on snapshot latents, instead of the entire noising path, that allows efficient training of standard generative modeling architectures with clear probabilistic interpretation. Our experiments on large-vocabulary discrete generation tasks suggest that the proposed framework outperforms existing discrete diffusion methods in terms of training efficiency and generation quality, and beats autoregressive models for the first time at this scale. We provide the code along with a blog post on the project page : https://oussamazekri.fr/gdds{https://oussamazekri.fr/gdds}.</p> - https://arxiv.org/abs/2603.21342 - Sun, 22 Mar 2026 17:58:01 +0000 - - - PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost - https://arxiv.org/abs/2603.21383 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21383.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkeun Yi, Damon Mosk-Aoyama, Baihe Huang, Ritu Gala, Charles Wang, Sugam Dipak Devare, Khushi Bhardwaj, Abhibha Gupta, Oleksii Kuchaiev, Jiantao Jiao, Jian Zhang, Venkat Srinivasan</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities, but incurs high compute costs due to many turns of on-policy rollout. We introduce PivotRL, a novel framework that operates on existing SFT trajectories to combine the compute efficiency of SFT with the OOD accuracy of E2E RL. PivotRL relies on two key mechanisms: first, it executes local, on-policy rollouts and filters for pivots: informative intermediate turns where sampled actions exhibit high variance in outcomes; second, it utilizes rewards for functional-equivalent actions rather than demanding strict string matching with the SFT data demonstration. We theoretically show that these mechanisms incentivize strong learning signals with high natural gradient norm, while maximally preserving policy probability ordering on actions unrelated to training tasks. In comparison to standard SFT on identical data, we demonstrate that PivotRL achieves +4.17% higher in-domain accuracy on average across four agentic domains, and +10.04% higher OOD accuracy in non-agentic tasks. Notably, on agentic coding tasks, PivotRL achieves competitive accuracy with E2E RL with 4x fewer rollout turns. PivotRL is adopted by NVIDIA's Nemotron-3-Super-120B-A12B, acting as the workhorse in production-scale agentic post-training.</p> - https://arxiv.org/abs/2603.21383 - Sun, 22 Mar 2026 19:59:48 +0000 - - - Effective Strategies for Asynchronous Software Engineering Agents - https://arxiv.org/abs/2603.21489 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21489.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayi Geng, Graham Neubig</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to timely completion. A natural approach to solving these long-horizon tasks in a timely manner is asynchronous multi-agent collaboration, where multiple agents work on different parts of the task at the same time. But effective application of multi-agent systems has proven surprisingly difficult: concurrent edits by multiple agents interfere with each other, dependencies are difficult to synchronize, and combining partial progress into a coherent whole is challenging. On the other hand, human developers have long relied on mature collaboration infrastructure to manage these challenges in large software projects. Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous execution, and isolated workspaces. CAID constructs dependency-aware task plans through a central manager, executes subtasks concurrently in isolated workspaces, and consolidates progress via structured integration with executable test-based verification. In empirical evaluation, we find that CAID improves accuracy over single-agent baselines by 26.7% absolute on paper reproduction tasks (PaperBench) and 14.3% on Python library development tasks (Commit0). Through systematic analysis, we find that branch-and-merge is a central coordination mechanism for multi-agent collaboration, and that SWE primitives such as git worktree, git commit, and git merge enable it to be realized in a reliable and executable manner.</p> - https://arxiv.org/abs/2603.21489 - Mon, 23 Mar 2026 02:26:35 +0000 - - - mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT - https://arxiv.org/abs/2603.21606 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21606.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Woosung Koh, Jeyoung Jeon, Youngjin Song, Yujin Cheon, Soowon Oh, Jaehyeong Choi, Se-Young Yun</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally sub-optimal: heterogeneous learning dynamics cause faster-learning tasks to overfit early while slower ones remain under-fitted. To address this, we introduce mSFT, an iterative, overfitting-aware search algorithm for multi-task data mixtures. mSFT trains the model on an active mixture, identifies and excludes the earliest overfitting sub-dataset, and reverts to that specific optimal checkpoint before continuing. Extensive evaluations demonstrate that mSFT consistently outperforms 4 baselines across 10 benchmarks and 6 base models. Further analysis confirms mSFT maintains robust gains across diverse dataset sizes, task granularities, and is insensitive to its single new hyperparameter (compute budget). Notably, at low compute budget, mSFT can improve performance while lowering training FLOPs. Ultimately, mSFT establishes a practical overfitting-aware algorithm for multi-task SFT that maximizes the potential of models across diverse data mixtures.</p> - https://arxiv.org/abs/2603.21606 - Mon, 23 Mar 2026 06:01:51 +0000 - - - 4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video - https://arxiv.org/abs/2603.21618 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jae Won Jang, Yeonjin Chang, Wonsik Shin, Juhwan Cho, Nojun Kwak</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We introduce 4DGS360, a diffusion-free framework for 360^{circ} dynamic object reconstruction from casual monocular video. Existing methods often fail to reconstruct consistent 360^{circ} geometry, as their heavy reliance on 2D-native priors causes initial points to overfit to visible surface in each training view. 4DGS360 addresses this challenge through a advanced 3D-native initialization that mitigates the geometric ambiguity of occluded regions. Our proposed 3D tracker, AnchorTAP3D, produces reinforced 3D point trajectories by leveraging confident 2D track points as anchors, suppressing drift and providing reliable initialization that preserves geometry in occluded regions. This initialization, combined with optimization, yields coherent 360^{circ} 4D reconstructions. We further present iPhone360, a new benchmark where test cameras are placed up to 135^{circ} apart from training views, enabling 360^{circ} evaluation that existing datasets cannot provide. Experiments show that 4DGS360 achieves state-of-the-art performance on the iPhone360, iPhone, and DAVIS datasets, both qualitatively and quantitatively.</p> - https://arxiv.org/abs/2603.21618 - Mon, 23 Mar 2026 06:30:46 +0000 - - - The Universal Normal Embedding - https://arxiv.org/abs/2603.21786 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chen Tasker, Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Generative models and vision encoders have largely advanced on separate tracks, optimized for different goals and grounded in different mathematical principles. Yet, they share a fundamental property: latent space Gaussianity. Generative models map Gaussian noise to images, while encoders map images to semantic embeddings whose coordinates empirically behave as Gaussian. We hypothesize that both are views of a shared latent source, the Universal Normal Embedding (UNE): an approximately Gaussian latent space from which encoder embeddings and DDIM-inverted noise arise as noisy linear projections. To test our hypothesis, we introduce NoiseZoo, a dataset of per-image latents comprising DDIM-inverted diffusion noise and matching encoder representations (CLIP, DINO). On CelebA, linear probes in both spaces yield strong, aligned attribute predictions, indicating that generative noise encodes meaningful semantics along linear directions. These directions further enable faithful, controllable edits (e.g., smile, gender, age) without architectural changes, where simple orthogonalization mitigates spurious entanglements. Taken together, our results provide empirical support for the UNE hypothesis and reveal a shared Gaussian-like latent geometry that concretely links encoding and generation. Code and data are available https://rbetser.github.io/UNE/</p> - https://arxiv.org/abs/2603.21786 - Mon, 23 Mar 2026 10:28:14 +0000 - - - Manifold-Aware Exploration for Reinforcement Learning in Video Generation - https://arxiv.org/abs/2603.21872 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingzhe Zheng, Weijie Kong, Yue Wu, Dengyang Jiang, Yue Ma, Xuanhua He, Bin Lin, Kaixiong Gong, Zhao Zhong, Liefeng Bo, Qifeng Chen, Harry Yang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and the ODE-to-SDE conversion used for exploration can inject excess noise, lowering rollout quality and making reward estimates less reliable, which destabilizes post-training alignment. To address this problem, we view the pre-trained model as defining a valid video data manifold and formulate the core problem as constraining exploration within the vicinity of this manifold, ensuring that rollout quality is preserved and reward estimates remain reliable. We propose SAGE-GRPO (Stable Alignment via Exploration), which applies constraints at both micro and macro levels. At the micro level, we derive a precise manifold-aware SDE with a logarithmic curvature correction and introduce a gradient norm equalizer to stabilize sampling and updates across timesteps. At the macro level, we use a dual trust region with a periodic moving anchor and stepwise constraints so that the trust region tracks checkpoints that are closer to the manifold and limits long-horizon drift. We evaluate SAGE-GRPO on HunyuanVideo1.5 using the original VideoAlign as the reward model and observe consistent gains over previous methods in VQ, MQ, TA, and visual metrics (CLIPScore, PickScore), demonstrating superior performance in both reward maximization and overall video quality. The code and visual gallery are available at https://dungeonmassster.github.io/SAGE-GRPO-Page/.</p> - https://arxiv.org/abs/2603.21872 - Mon, 23 Mar 2026 12:04:38 +0000 - - - Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation - https://arxiv.org/abs/2603.21884 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21884.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Donald Shenaj, Federico Errica, Antonio Carta</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since it trades off performance and memory consumption, but today the decision is often left to the community's consensus, regardless of the personalized subject's complexity. The reason is evident: the cost of selecting a good rank for each LoRA component is combinatorial, so we opt for practical shortcuts such as fixing the same rank for all components. In this paper, we take a first step to overcome this challenge. Inspired by variational methods that learn an adaptive width of neural networks, we let the ranks of each layer freely adapt during fine-tuning on a subject. We achieve it by imposing an ordering of importance on the rank's positions, effectively encouraging the creation of higher ranks when strictly needed. Qualitatively and quantitatively, our approach, LoRA^2, achieves a competitive trade-off between DINO, CLIP-I, and CLIP-T across 29 subjects while requiring much less memory and lower rank than high rank LoRA versions. Code: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.</p> - https://arxiv.org/abs/2603.21884 - Mon, 23 Mar 2026 12:13:47 +0000 - - - MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation - https://arxiv.org/abs/2603.21937 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21937.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqing Tian, Hanyi Mao, Zhaocheng Liu, Lihua Zhang, Qiang Liu, Jian Wu, Liang Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Subject-driven image generation is increasingly expected to support fine-grained control over multiple entities within a single image. In multi-reference workflows, users may provide several subject images, a background reference, and long, entity-indexed prompts to control multiple people within one scene. In this setting, a key failure mode is cross-subject attribute misbinding: attributes are preserved, edited, or transferred to the wrong subject. Existing benchmarks and metrics largely emphasize holistic fidelity or per-subject self-similarity, making such failures hard to diagnose. We introduce MultiBind, a benchmark built from real multi-person photographs. Each instance provides slot-ordered subject crops with masks and bounding boxes, canonicalized subject references, an inpainted background reference, and a dense entity-indexed prompt derived from structured annotations. We also propose a dimension-wise confusion evaluation protocol that matches generated subjects to ground-truth slots and measures slot-to-slot similarity using specialists for face identity, appearance, pose, and expression. By subtracting the corresponding ground-truth similarity matrices, our method separates self-degradation from true cross-subject interference and exposes interpretable failure patterns such as drift, swap, dominance, and blending. Experiments on modern multi-reference generators show that MultiBind reveals binding failures that conventional reconstruction metrics miss.</p> - https://arxiv.org/abs/2603.21937 - Mon, 23 Mar 2026 12:54:36 +0000 - - - Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection - https://arxiv.org/abs/2603.21944 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21944.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youbin Kim, Jinho Park, Hogun Park, Eunbyung Park</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Open-vocabulary 3D object detection aims to localize and recognize objects beyond a fixed training taxonomy. In multi-view RGB settings, recent approaches often decouple geometry-based instance construction from semantic labeling, generating class-agnostic fragments and assigning open-vocabulary categories post hoc. While flexible, such decoupling leaves instance construction governed primarily by geometric consistency, without semantic constraints during merging. When geometric evidence is view-dependent and incomplete, this geometry-only merging can lead to irreversible association errors, including over-merging of distinct objects or fragmentation of a single instance. We propose Group3D, a multi-view open-vocabulary 3D detection framework that integrates semantic constraints directly into the instance construction process. Group3D maintains a scene-adaptive vocabulary derived from a multimodal large language model (MLLM) and organizes it into semantic compatibility groups that encode plausible cross-view category equivalence. These groups act as merge-time constraints: 3D fragments are associated only when they satisfy both semantic compatibility and geometric consistency. This semantically gated merging mitigates geometry-driven over-merging while absorbing multi-view category variability. Group3D supports both pose-known and pose-free settings, relying only on RGB observations. Experiments on ScanNet and ARKitScenes demonstrate that Group3D achieves state-of-the-art performance in multi-view open-vocabulary 3D detection, while exhibiting strong generalization in zero-shot scenarios. The project page is available at https://ubin108.github.io/Group3D/.</p> - https://arxiv.org/abs/2603.21944 - Mon, 23 Mar 2026 13:01:14 +0000 - - - Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model - https://arxiv.org/abs/2603.21986 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> SII-GAIR, Sand. ai, Ethan Chern, Hansi Teng, Hanwen Sun, Hao Wang, Hong Pan, Hongyu Jia, Jiadi Su, Jin Li, Junjie Yu, Lijie Liu, Lingzhi Li, Lyumanshan Ye, Min Hu, Qiangang Wang, Quanwei Qi, Steffi Chern, Tao Bu, Taoran Wang, Teren Xu, Tianning Zhang, Tiantian Mi, Weixian Xu, Wenqiang Zhang, Wentai Zhang, Xianping Yi, Xiaojie Cai, Xiaoyang Kang, Yan Ma, Yixiu Liu, Yunbo Zhang, Yunpeng Huang, Yutong Lin, Zewei Tao, Zhaoliang Liu, Zheng Zhang, Zhiyao Cen, Zhixuan Yu, Zhongshu Wang, Zhulin Hu, Zijin Zhou, Zinan Guo, Yue Cao, Pengfei Liu</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio using a single-stream Transformer that processes text, video, and audio within a unified token sequence via self-attention only. This single-stream design avoids the complexity of multi-stream or cross-attention architectures while remaining easy to optimize with standard training and inference infrastructure. The model is particularly strong in human-centric scenarios, producing expressive facial performance, natural speech-expression coordination, realistic body motion, and precise audio-video synchronization. It supports multilingual spoken generation across Chinese (Mandarin and Cantonese), English, Japanese, Korean, German, and French. For efficient inference, we combine the single-stream backbone with model distillation, latent-space super-resolution, and a Turbo VAE decoder, enabling generation of a 5-second 256p video in 2 seconds on a single H100 GPU. In automatic evaluation, daVinci-MagiHuman achieves the highest visual quality and text alignment among leading open models, along with the lowest word error rate (14.60%) for speech intelligibility. In pairwise human evaluation, it achieves win rates of 80.0% against Ovi 1.1 and 60.9% against LTX 2.3 over 2000 comparisons. We open-source the complete model stack, including the base model, the distilled model, the super-resolution model, and the inference codebase.</p> - https://arxiv.org/abs/2603.21986 - Mon, 23 Mar 2026 13:49:06 +0000 - - - VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models - https://arxiv.org/abs/2603.22003 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22003.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixuan Wang, Yuxin Chen, Yuqi Liu, Jinhui Ye, Pengguang Chen, Changsheng Lu, Shu Liu, Jiaya Jia</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to robotic control signals. This "black-box" mapping forces a single forward pass to simultaneously handle instruction interpretation, spatial grounding, and low-level control, often leading to poor spatial precision and limited robustness in out-of-distribution scenarios. To address these limitations, we propose VP-VLA, a dual-system framework that decouples high-level reasoning and low-level execution via a structured visual prompting interface. Specifically, a "System 2 Planner" decomposes complex instructions into sub-tasks and identifies relevant target objects and goal locations. These spatial anchors are then overlaid directly onto visual observations as structured visual prompts, such as crosshairs and bounding boxes. Guided by these prompts and enhanced by a novel auxiliary visual grounding objective during training, a "System 1 Controller" reliably generates precise low-level execution motions. Experiments on the Robocasa-GR1-Tabletop benchmark and SimplerEnv simulation demonstrate that VP-VLA improves success rates by 5% and 8.3%, surpassing competitive baselines including QwenOFT and GR00T-N1.6.</p> - https://arxiv.org/abs/2603.22003 - Mon, 23 Mar 2026 14:08:58 +0000 - - - SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning - https://arxiv.org/abs/2603.22057 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22057.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Byungwoo Jeon, Dongyoung Kim, Huiwon Jang, Insoo Kim, Jinwoo Shin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Despite the remarkable success of large-scale pre-trained image representation models (i.e., vision encoders) across various vision tasks, they are predominantly trained on 2D image data and therefore often fail to capture 3D spatial relationships between objects and backgrounds in the real world, constraining their effectiveness in many downstream applications. To address this, we propose SpatialBoost, a scalable framework that enhances the spatial awareness of existing pre-trained vision encoders by injecting 3D spatial knowledge expressed in linguistic descriptions. The core idea involves converting dense 3D spatial information from 2D images into linguistic expressions, which is then used to inject such spatial knowledge into vision encoders through a Large Language Model (LLM). To this end, we adopt a multi-turn Chain-of-Thought (CoT) reasoning process that progressively incorporates dense spatial knowledge and builds hierarchical spatial understanding. To validate effectiveness, we adapt SpatialBoost to state-of-the-art vision encoders such as DINOv3, and evaluate its performance gains on a wide range of benchmarks requiring both 3D perception and general vision abilities. For instance, SpatialBoost improves DINOv3 performance from 55.9 to 59.7 mIoU on ADE20K, achieving state-of-the-art performance with 3.8% gain over the pre-trained DINOv3.</p> - https://arxiv.org/abs/2603.22057 - Mon, 23 Mar 2026 14:54:34 +0000 - - - On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation - https://arxiv.org/abs/2603.22117 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the magnitude of these updates, largely overlooking their direction. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference Δlog p between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that Δlog p more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (\eg divergence or entropy). Building on this insight, we propose two practical applications: (1) a test-time extrapolation method that amplifies the policy along the learned Δlog p direction to improve reasoning accuracy without further training; (2) a training-time reweighting method that focuses learning on low-probability (corresponding to higher Δlog p) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.</p> - https://arxiv.org/abs/2603.22117 - Mon, 23 Mar 2026 15:42:24 +0000 - - - StreamingClaw Technical Report - https://arxiv.org/abs/2603.22120 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22120.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Chen, Zhe Chen, Chaoqun Du, Maokui He, Wei He, Hengtao Li, Qizhen Li, Zide Liu, Hao Ma, Xuhao Pan, Chang Ren, Xudong Rao, Xintian Shen, Chenfeng Wang, Tao Wei, Chengjun Yu, Pengfei Yu, Shengyu Yao, Chunpeng Zhou, Kun Zhan, Lihao Zheng, Pan Zhou, Xuhan Zhu, Yufei Zheng</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Applications such as embodied intelligence rely on a real-time perception-decision-action closed loop, posing stringent challenges for streaming video understanding. However, current agents suffer from fragmented capabilities, such as supporting only offline video understanding, lacking long-term multimodal memory mechanisms, or struggling to achieve real-time reasoning and proactive interaction under streaming inputs. These shortcomings have become a key bottleneck for preventing them from sustaining perception, making real-time decisions, and executing actions in real-world environments. To alleviate these issues, we propose StreamingClaw, a unified agent framework for streaming video understanding and embodied intelligence. It is also an OpenClaw-compatible framework that supports real-time, multimodal streaming interaction. StreamingClaw integrates five core capabilities: (1) It supports real-time streaming reasoning. (2) It supports reasoning about future events and proactive interaction under the online evolution of interaction objectives. (3) It supports multimodal long-term storage, hierarchical evolution, and efficient retrieval of shared memory across multiple agents. (4) It supports a closed-loop of perception-decision-action. In addition to conventional tools and skills, it also provides streaming tools and action-centric skills tailored for real-world physical environments. (5) It is compatible with the OpenClaw framework, allowing it to fully leverage the resources and support of the open-source community. With these designs, StreamingClaw integrates online real-time reasoning, multimodal long-term memory, and proactive interaction within a unified framework. Moreover, by translating decisions into executable actions, it enables direct control of the physical world, supporting practical deployment of embodied interaction.</p> - https://arxiv.org/abs/2603.22120 - Mon, 23 Mar 2026 15:43:52 +0000 - - - Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models - https://arxiv.org/abs/2603.22212 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meiqi Wu, Zhixin Cai, Fufangchen Zhao, Xiaokun Feng, Rujing Dang, Bingze Song, Ruitian Tian, Jiashu Zhu, Jiachen Lei, Hao Dou, Jing Tang, Lei Sun, Jiahong Wu, Xiangxiang Chu, Zeming Liu, Kaiqi Huang</p><p><b>Upvotes:</b> 122</p><p><b>Summary:</b> Video--based world models have emerged along two dominant paradigms: video generation and 3D reconstruction. However, existing evaluation benchmarks either focus narrowly on visual fidelity and text--video alignment for generative models, or rely on static 3D reconstruction metrics that fundamentally neglect temporal dynamics. We argue that the future of world modeling lies in 4D generation, which jointly models spatial structure and temporal evolution. In this paradigm, the core capability is interactive response: the ability to faithfully reflect how interaction actions drive state transitions across space and time. Yet no existing benchmark systematically evaluates this critical dimension. To address this gap, we propose Omni--WorldBench, a comprehensive benchmark specifically designed to evaluate the interactive response capabilities of world models in 4D settings. Omni--WorldBench comprises two key components: Omni--WorldSuite, a systematic prompt suite spanning diverse interaction levels and scene types; and Omni--Metrics, an agent-based evaluation framework that quantifies world modeling capabilities by measuring the causal impact of interaction actions on both final outcomes and intermediate state evolution trajectories. We conduct extensive evaluations of 18 representative world models across multiple paradigms. Our analysis reveals critical limitations of current world models in interactive response, providing actionable insights for future research. Omni-WorldBench will be publicly released to foster progress in interactive 4D world modeling.</p> - https://arxiv.org/abs/2603.22212 - Mon, 23 Mar 2026 17:10:29 +0000 - - - From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents - https://arxiv.org/abs/2603.22386 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22386.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko, Dhaval Patel, Shuxin Lin, Nianjun Zhou, Jianxi Gao, Pin-Yu Chen, Shaowu Pan</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification. This survey reviews recent methods for designing and optimizing such workflows, which we treat as agentic computation graphs (ACGs). We organize the literature based on when workflow structure is determined, where structure refers to which components or agents are present, how they depend on each other, and how information flows between them. This lens distinguishes static methods, which fix a reusable workflow scaffold before deployment, from dynamic methods, which select, generate, or revise the workflow for a particular run before or during execution. We further organize prior work along three dimensions: when structure is determined, what part of the workflow is optimized, and which evaluation signals guide optimization (e.g., task metrics, verifier signals, preferences, or trace-derived feedback). We also distinguish reusable workflow templates, run-specific realized graphs, and execution traces, separating reusable design choices from the structures actually deployed in a given run and from realized runtime behavior. Finally, we outline a structure-aware evaluation perspective that complements downstream task metrics with graph-level properties, execution cost, robustness, and structural variation across inputs. Our goal is to provide a clear vocabulary, a unified framework for positioning new methods, a more comparable view of existing body of literature, and a more reproducible evaluation standard for future work in workflow optimizations for LLM agents.</p> - https://arxiv.org/abs/2603.22386 - Mon, 23 Mar 2026 17:42:59 +0000 - - - Repurposing Geometric Foundation Models for Multi-view Diffusion - https://arxiv.org/abs/2603.22275 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22275.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wooseok Jang, Seonghu Jeon, Jisang Han, Jinhyeok Choi, Minkyung Kwon, Seungryong Kim, Saining Xie, Sainan Liu</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> While recent advances in generative latent spaces have driven substantial progress in single-image generation, the optimal latent space for novel view synthesis (NVS) remains largely unexplored. In particular, NVS requires geometrically consistent generation across viewpoints, but existing approaches typically operate in a view-independent VAE latent space. In this paper, we propose Geometric Latent Diffusion (GLD), a framework that repurposes the geometrically consistent feature space of geometric foundation models as the latent space for multi-view diffusion. We show that these features not only support high-fidelity RGB reconstruction but also encode strong cross-view geometric correspondences, providing a well-suited latent space for NVS. Our experiments demonstrate that GLD outperforms both VAE and RAE on 2D image quality and 3D consistency metrics, while accelerating training by more than 4.4x compared to the VAE latent space. Notably, GLD remains competitive with state-of-the-art methods that leverage large-scale text-to-image pretraining, despite training its diffusion model from scratch without such generative pretraining.</p> - https://arxiv.org/abs/2603.22275 - Mon, 23 Mar 2026 17:57:05 +0000 - - - Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels - https://arxiv.org/abs/2603.22276 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexandra Zelenin, Alexandra Zhuravlyova</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Weight-Decomposed Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction, but its forward pass requires the row-wise norm of W + sBA, a computation that every major framework we surveyed implements by materializing the dense [d_out, d_in] product BA. At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16, making high-rank DoRA costly and often infeasible on common single-GPU setups once hundreds of adapted modules and checkpointing are involved. We present two systems contributions. A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r^2) intermediates, eliminating the dense product. Fused Triton kernels collapse the four-kernel DoRA composition into a single pass, reducing memory traffic by about 4x and using a numerically stable form that avoids catastrophic cancellation in the near-unity rescaling regime where magnitude scales concentrate in practice. Across six 8-32B vision-language models (VLMs) on three NVIDIA GPUs (RTX 6000 PRO, H200, B200) at r = 384 in bf16, the fused implementation is 1.5-2.0x faster than Hugging Face PEFT's DoRA implementation for inference and 1.5-1.9x faster for gradient computation (optimizer step excluded), with up to 7 GB lower peak VRAM. Microbenchmarks on six GPUs spanning four architecture generations (L40S, A100, RTX 6000 PRO, H200, B200, B300) confirm 1.5-2.7x compose-kernel speedup. Final-logit cosine similarity exceeds 0.9999 across all model/GPU pairs, and multi-seed training curves match within 7.1 x 10^-4 mean per-step loss delta over 2000 steps.</p> - https://arxiv.org/abs/2603.22276 - Mon, 23 Mar 2026 17:57:24 +0000 - - - ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model - https://arxiv.org/abs/2603.22281 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. Vision--language models (VLMs), in contrast, provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames, but they are not ideal as standalone dense predictors due to compute-driven sparse sampling, a language-output bottleneck that compresses fine-grained interaction states into text-oriented representations, and a data-regime mismatch when adapting to small action-conditioned datasets. We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance via a dual-temporal pathway: a dense JEPA branch for fine-grained motion and interaction cues, and a uniformly sampled VLM thinker branch with a larger temporal stride for knowledge-rich guidance. To transfer the VLM's progressive reasoning signals effectively, we introduce a hierarchical pyramid representation extraction module that aggregates multi-layer VLM representations into guidance features compatible with latent prediction. Experiments on hand-manipulation trajectory prediction show that our method outperforms both a strong VLM-only baseline and a JEPA-predictor baseline, and yields more robust long-horizon rollout behavior.</p> - https://arxiv.org/abs/2603.22281 - Mon, 23 Mar 2026 17:59:42 +0000 - - - VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding - https://arxiv.org/abs/2603.22285 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22285.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoliu Yang, Chu Wu, Caifeng Shan, Ran He, Chaoyou Fu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identifying sparse query-relevant video segments. However, existing methods predominantly localize clues based solely on the query, overlooking the video's intrinsic structure and varying relevance across segments. To address this, we propose VideoDetective, a framework that integrates query-to-segment relevance and inter-segment affinity for effective clue hunting in long-video question answering. Specifically, we divide a video into various segments and represent them as a visual-temporal affinity graph built from visual similarity and temporal proximity. We then perform a Hypothesis-Verification-Refinement loop to estimate relevance scores of observed segments to the query and propagate them to unseen segments, yielding a global relevance distribution that guides the localization of the most critical segments for final answering with sparse observation. Experiments show our method consistently achieves substantial gains across a wide range of mainstream MLLMs on representative benchmarks, with accuracy improvements of up to 7.5% on VideoMME-long. Our code is available at https://videodetective.github.io/</p> - https://arxiv.org/abs/2603.22285 - Mon, 23 Mar 2026 17:59:51 +0000 - - - Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs - https://arxiv.org/abs/2603.22446 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22446.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoming Meng, Kexin Huang, Shaohang Wei, Chiyu Ma, Shuo Yang, Xue Wang, Guoyin Wang, Bolin Ding, Jingren Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study of RLVR's distributional effects organized around three main analyses: (1) token-level characterization of distributional shifts between base and RL models, (2) the impact of token-level distributional shifts on sequence-level reasoning performance through cross-sampling interventions, and (3) fine-grained mechanics of these shifts at the token level. We find that RL fine-tuning induces highly sparse and targeted changes, with only a small fraction of token distributions exhibiting meaningful divergence between the base and RL policies. We further characterize the structure and evolution of these shifts through analyses of token entropy, positional concentration, and reallocation of probability mass. To assess the functional importance of these sparse changes, we conduct cross-sampling experiments that selectively swap token choices between the base and RL models with varying intervention budgets. We show that inserting only a small fraction of RL-sampled tokens into base generations progressively recovers RL performance gains, while injecting a similarly small number of base token choices into otherwise RL-generated sequences collapses performance to base levels, isolating a small set of token-level decisions directly responsible for RLVR's performance gains. Finally, we explore divergence-weighted variants of the advantage signal as a diagnostic intervention, finding that they can yield improvements over baselines. Together, our results shed light on the distributional changes induced by RLVR and provide a fine-grained, token-level lens for understanding RLVR fine-tuning as a targeted refinement process.</p> - https://arxiv.org/abs/2603.22446 - Mon, 23 Mar 2026 18:17:15 +0000 - - - MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding - https://arxiv.org/abs/2603.22458 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22458.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hejun Dong, Junbo Niu, Bin Wang, Weijun Zeng, Wentao Zhang, Conghui He</p><p><b>Upvotes:</b> 130</p><p><b>Summary:</b> Optical character recognition (OCR) has evolved from line-level transcription to structured document parsing, requiring models to recover long-form sequences containing layout, tables, and formulas. Despite recent advances in vision-language models, most existing systems rely on autoregressive decoding, which introduces sequential latency and amplifies error propagation in long documents. In this work, we revisit document OCR from an inverse rendering perspective, arguing that left-to-right causal generation is an artifact of serialization rather than an intrinsic property of the task. Motivated by this insight, we propose MinerU-Diffusion, a unified diffusion-based framework that replaces autoregressive sequential decoding with parallel diffusion denoising under visual conditioning. MinerU-Diffusion employs a block-wise diffusion decoder and an uncertainty-driven curriculum learning strategy to enable stable training and efficient long-sequence inference. Extensive experiments demonstrate that MinerU-Diffusion consistently improves robustness while achieving up to 3.2x faster decoding compared to autoregressive baselines. Evaluations on the proposed Semantic Shuffle benchmark further confirm its reduced dependence on linguistic priors and stronger visual OCR capability.</p> - https://arxiv.org/abs/2603.22458 - Mon, 23 Mar 2026 18:25:17 +0000 - - - Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos - https://arxiv.org/abs/2603.22529 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shoubin Yu, Lei Shu, Antoine Yang, Yao Fu, Srinivas Sunkara, Maria Wang, Jindong Chen, Mohit Bansal, Boqing Gong</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Multimodal AI agents are increasingly automating complex real-world workflows that involve online web execution. However, current web-agent benchmarks suffer from a critical limitation: they focus entirely on web-based interaction and perception, lacking grounding in the user's real-world physical surroundings. This limitation prevents evaluation in crucial scenarios, such as when an agent must use egocentric visual perception (e.g., via AR glasses) to recognize an object in the user's surroundings and then complete a related task online. To address this gap, we introduce Ego2Web, the first benchmark designed to bridge egocentric video perception and web agent execution. Ego2Web pairs real-world first-person video recordings with web tasks that require visual understanding, web task planning, and interaction in an online environment for successful completion. We utilize an automatic data-generation pipeline combined with human verification and refinement to curate well-constructed, high-quality video-task pairs across diverse web task types, including e-commerce, media retrieval, knowledge lookup, etc. To facilitate accurate and scalable evaluation for our benchmark, we also develop a novel LLM-as-a-Judge automatic evaluation method, Ego2WebJudge, which achieves approximately 84% agreement with human judgment, substantially higher than existing evaluation methods. Experiments with diverse SoTA agents on our Ego2Web show that their performance is weak, with substantial headroom across all task categories. We also conduct a comprehensive ablation study on task design, highlighting the necessity of accurate video understanding in the proposed task and the limitations of current agents. We hope Ego2Web can be a critical new resource for developing truly capable AI assistants that can seamlessly see, understand, and act across the physical and digital worlds.</p> - https://arxiv.org/abs/2603.22529 - Mon, 23 Mar 2026 19:47:58 +0000 - - - CanViT: Toward Active-Vision Foundation Models - https://arxiv.org/abs/2603.22570 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22570.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yohaï-Eliel Berreby, Sabrina Du, Audrey Durand, B. Suresh Krishna</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Active computer vision promises efficient, biologically plausible perception through sequential, localized glimpses, but lacks scalable general-purpose architectures and pretraining pipelines. As a result, Active-Vision Foundation Models (AVFMs) have remained unexplored. We introduce CanViT, the first task- and policy-agnostic AVFM. CanViT uses scene-relative RoPE to bind a retinotopic Vision Transformer backbone and a spatiotopic scene-wide latent workspace, the canvas. Efficient interaction with this high-capacity working memory is supported by Canvas Attention, a novel asymmetric cross-attention mechanism. We decouple thinking (backbone-level) and memory (canvas-level), eliminating canvas-side self-attention and fully-connected layers to achieve low-latency sequential inference and scalability to large scenes. We propose a label-free active vision pretraining scheme, policy-agnostic passive-to-active dense latent distillation: reconstructing scene-wide DINOv3 embeddings from sequences of low-resolution glimpses with randomized locations, zoom levels, and lengths. We pretrain CanViT-B from a random initialization on 13.2 million ImageNet-21k scenes -- an order of magnitude more than previous active models -- and 1 billion random glimpses, in 166 hours on a single H100. On ADE20K segmentation, a frozen CanViT-B achieves 38.5% mIoU in a single low-resolution glimpse, outperforming the best active model's 27.6% with 19.5x fewer inference FLOPs and no fine-tuning, as well as its FLOP- or input-matched DINOv3 teacher. Given additional glimpses, CanViT-B reaches 45.9% ADE20K mIoU. On ImageNet-1k classification, CanViT-B reaches 81.2% top-1 accuracy with frozen teacher probes. CanViT generalizes to longer rollouts, larger scenes, and new policies. Our work closes the wide gap between passive and active vision on semantic segmentation and demonstrates the potential of AVFMs as a new research axis.</p> - https://arxiv.org/abs/2603.22570 - Mon, 23 Mar 2026 21:05:21 +0000 - - - TrajLoom: Dense Future Trajectory Generation from Video - https://arxiv.org/abs/2603.22606 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22606.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zewei Zhang, Jia Jun Cheng Xian, Kaiwen Liu, Ming Liang, Hang Chu, Jun Chen, Renjie Liao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Predicting future motion is crucial in video understanding and controllable video generation. Dense point trajectories are a compact, expressive motion representation, but modeling their future evolution from observed video remains challenging. We propose a framework that predicts future trajectories and visibility from past trajectories and video context. Our method has three components: (1) Grid-Anchor Offset Encoding, which reduces location-dependent bias by representing each point as an offset from its pixel-center anchor; (2) TrajLoom-VAE, which learns a compact spatiotemporal latent space for dense trajectories with masked reconstruction and a spatiotemporal consistency regularizer; and (3) TrajLoom-Flow, which generates future trajectories in latent space via flow matching, with boundary cues and on-policy K-step fine-tuning for stable sampling. We also introduce TrajLoomBench, a unified benchmark spanning real and synthetic videos with a standardized setup aligned with video-generation benchmarks. Compared with state-of-the-art methods, our approach extends the prediction horizon from 24 to 81 frames while improving motion realism and stability across datasets. The predicted trajectories directly support downstream video generation and editing. Code, model checkpoints, and datasets are available at https://trajloom.github.io/.</p> - https://arxiv.org/abs/2603.22606 - Mon, 23 Mar 2026 22:10:58 +0000 - - - Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought - https://arxiv.org/abs/2603.22847 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22847.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunheng Li, Hangyi Kuang, Hengrui Zhang, Jiangxia Cao, Zhaojie Liu, Qibin Hou, Ming-Ming Cheng</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable Rewards (RLVR) methods typically optimize reasoning at a coarse granularity, treating CoT uniformly without distinguishing their varying degrees of visual grounding. In this work, we conduct a token-level analysis of multimodal reasoning trajectories and show that successful reasoning is characterized by structured token dynamics reflecting both perceptual grounding and exploratory inference. Building upon this analysis, we propose Perception-Exploration Policy Optimization (PEPO), which derives a perception prior from hidden state similarity and integrates it with token entropy through a smooth gating mechanism to produce token-level advantages. PEPO integrates seamlessly with existing RLVR frameworks such as GRPO and DAPO, requiring neither additional supervision nor auxiliary branches. Extensive experiments across diverse multimodal benchmarks demonstrate consistent and robust improvements over strong RL baselines, spanning geometry reasoning, visual grounding, visual puzzle solving, and few-shot classification, while maintaining stable training dynamics. Code: https://github.com/xzxxntxdy/PEPO</p> - https://arxiv.org/abs/2603.22847 - Tue, 24 Mar 2026 06:38:00 +0000 - - - EVA: Efficient Reinforcement Learning for End-to-End Video Agent - https://arxiv.org/abs/2603.22918 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22918.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaolun Zhang, Ruohui Wang, Jiahao Wang, Yepeng Tang, Xuanyu Zheng, Haonan Duan, Hao Lu, Hanming Deng, Lewei Lu</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames. Existing approaches typically treat MLLMs as passive recognizers, processing entire videos or uniformly sampled frames without adaptive reasoning. Recent agent-based methods introduce external tools, yet still depend on manually designed workflows and perception-first strategies, resulting in inefficiency on long videos. We present EVA, an Efficient Reinforcement Learning framework for End-to-End Video Agent, which enables planning-before-perception through iterative summary-plan-action-reflection reasoning. EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding. To train such agents, we design a simple yet effective three-stage learning pipeline - comprising supervised fine-tuning (SFT), Kahneman-Tversky Optimization (KTO), and Generalized Reward Policy Optimization (GRPO) - that bridges supervised imitation and reinforcement learning. We further construct high-quality datasets for each stage, supporting stable and reproducible training. We evaluate EVA on six video understanding benchmarks, demonstrating its comprehensive capabilities. Compared with existing baselines, EVA achieves a substantial improvement of 6-12% over general MLLM baselines and a further 1-3% gain over prior adaptive agent methods. Our code and model are available at https://github.com/wangruohui/EfficientVideoAgent.</p> - https://arxiv.org/abs/2603.22918 - Tue, 24 Mar 2026 08:06:29 +0000 - - - SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM - https://arxiv.org/abs/2603.23386 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23386.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuanrui Zhang, Minghan Qin, Yuang Wang, Baifeng Xie, Hang Li, Ziwei Wang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> High-quality articulated 3D assets are indispensable for embodied AI and physical simulation, yet 3D generation still focuses on static meshes, leaving a gap in "sim-ready" interactive objects. Most recent articulated object creation methods rely on multi-stage pipelines that accumulate errors across decoupled modules. Alternatively, unified MLLMs offer a single-stage path to joint static asset understanding and sim-ready asset generation. However dense voxel-based 3D tokenization yields long 3D token sequences and high memory overhead, limiting scalability to complex articulated objects. To address this, we propose SIMART, a unified MLLM framework that jointly performs part-level decomposition and kinematic prediction. By introducing a Sparse 3D VQ-VAE, SIMART reduces token counts by 70% vs. dense voxel tokens, enabling high-fidelity multi-part assemblies. SIMART achieves state-of-the-art performance on PartNet-Mobility and in-the-wild AIGC datasets, and enables physics-based robotic simulation.</p> - https://arxiv.org/abs/2603.23386 - Tue, 24 Mar 2026 16:16:52 +0000 - - - RealMaster: Lifting Rendered Scenes into Photorealistic Video - https://arxiv.org/abs/2603.23462 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23462.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dana Cohen-Bar, Ido Sobol, Raphael Bensadoun, Shelly Sheynin, Oran Gafni, Or Patashnik, Daniel Cohen-Or, Amit Zohar</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Furthermore, without an underlying explicit geometry, these models cannot guarantee 3D consistency. Conversely, 3D engines offer granular control over every scene element and provide native 3D consistency by design, yet their output often remains trapped in the "uncanny valley". Bridging this sim-to-real gap requires both structural precision, where the output must exactly preserve the geometry and dynamics of the input, and global semantic transformation, where materials, lighting, and textures must be holistically transformed to achieve photorealism. We present RealMaster, a method that leverages video diffusion models to lift rendered video into photorealistic video while maintaining full alignment with the output of the 3D engine. To train this model, we generate a paired dataset via an anchor-based propagation strategy, where the first and last frames are enhanced for realism and propagated across the intermediate frames using geometric conditioning cues. We then train an IC-LoRA on these paired videos to distill the high-quality outputs of the pipeline into a model that generalizes beyond the pipeline's constraints, handling objects and characters that appear mid-sequence and enabling inference without requiring anchor frames. Evaluated on complex GTA-V sequences, RealMaster significantly outperforms existing video editing baselines, improving photorealism while preserving the geometry, dynamics, and identity specified by the original 3D control.</p> - https://arxiv.org/abs/2603.23462 - Tue, 24 Mar 2026 17:32:42 +0000 - - - VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs - https://arxiv.org/abs/2603.23481 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23481.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Yuan, Weigang Yi, Zhenyu Zhang, Wendi Chen, Yuchen Mo, Jiashi Yin, Xinzhuo Li, Xiangyu Zeng, Chuan Wen, Cewu Lu, Katherine Driggs-Campbell, Ismini Lourentzou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Video-Action Models (VAMs) have emerged as a promising framework for embodied intelligence, learning implicit world dynamics from raw video streams to produce temporally consistent action predictions. Although such models demonstrate strong performance on long-horizon tasks through visual reasoning, they remain limited in contact-rich scenarios where critical interaction states are only partially observable from vision alone. In particular, fine-grained force modulation and contact transitions are not reliably encoded in visual tokens, leading to unstable or imprecise behaviors. To bridge this gap, we introduce the Video-Tactile Action Model (VTAM), a multimodal world modeling framework that incorporates tactile perception as a complementary grounding signal. VTAM augments a pretrained video transformer with tactile streams via a lightweight modality transfer finetuning, enabling efficient cross-modal representation learning without tactile-language paired data or independent tactile pretraining. To stabilize multimodal fusion, we introduce a tactile regularization loss that enforces balanced cross-modal attention, preventing visual latent dominance in the action model. VTAM demonstrates superior performance in contact-rich manipulation, maintaining a robust success rate of 90 percent on average. In challenging scenarios such as potato chip pick-and-place requiring high-fidelity force awareness, VTAM outperforms the pi 0.5 baseline by 80 percent. Our findings demonstrate that integrating tactile feedback is essential for correcting visual estimation errors in world action models, providing a scalable approach to physically grounded embodied foundation models.</p> - https://arxiv.org/abs/2603.23481 - Tue, 24 Mar 2026 17:45:06 +0000 - - - SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning - https://arxiv.org/abs/2603.23483 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23483.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Huang, Jinfa Huang, Zhongwei Wan, Xiawu Zheng, Rongrong Ji, Jiebo Luo</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling loops introduce significant sequential overhead. This overhead, termed agentic depth, incurs prohibitive latency and seriously limits system-level concurrency. To this end, we propose SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck. Our key insight is that a lightweight, tool-free MLLM can serve as a speculative planner to predict the execution trajectory, enabling early termination of expensive tool chains without sacrificing accuracy. To regulate this speculative planning, we introduce a cognitive gating mechanism based on answer separability, which quantifies the model's confidence for self-verification without requiring oracle labels. Furthermore, we design a heterogeneous parallel funnel that exploits the stateless concurrency of the small model to mask the stateful serial execution of the large model, maximizing system throughput. Extensive experiments on V* Bench, HR-Bench, and POPE demonstrate that SpecEyes achieves 1.1-3.35x speedup over the agentic baseline while preserving or even improving accuracy (up to +6.7%), thereby boosting serving throughput under concurrent workloads.</p> - https://arxiv.org/abs/2603.23483 - Tue, 24 Mar 2026 17:45:47 +0000 - - - WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG - https://arxiv.org/abs/2603.23497 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23497.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Li, Zian Meng, Shuwei Shi, Wenshuo Peng, Yuwei Wu, Bo Zheng, Chuanhao Li, Kaipeng Zhang</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> Dynamical systems theory and reinforcement learning view world evolution as latent-state dynamics driven by actions, with visual observations providing partial information about the state. Recent video world models attempt to learn this action-conditioned dynamics from data. However, existing datasets rarely match the requirement: they typically lack diverse and semantically meaningful action spaces, and actions are directly tied to visual observations rather than mediated by underlying states. As a result, actions are often entangled with pixel-level changes, making it difficult for models to learn structured world dynamics and maintain consistent evolution over long horizons. In this paper, we propose WildWorld, a large-scale action-conditioned world modeling dataset with explicit state annotations, automatically collected from a photorealistic AAA action role-playing game (Monster Hunter: Wilds). WildWorld contains over 108 million frames and features more than 450 actions, including movement, attacks, and skill casting, together with synchronized per-frame annotations of character skeletons, world states, camera poses, and depth maps. We further derive WildBench to evaluate models through Action Following and State Alignment. Extensive experiments reveal persistent challenges in modeling semantically rich actions and maintaining long-horizon state consistency, highlighting the need for state-aware video generation. The project page is https://shandaai.github.io/wildworld-project/.</p> - https://arxiv.org/abs/2603.23497 - Tue, 24 Mar 2026 17:58:25 +0000 - - - DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models - https://arxiv.org/abs/2603.23499 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaewon Min, Jaeeun Lee, Yeji Choi, Paul Hyunbin Cho, Jin Hyeon Kim, Tae-Young Lee, Jongsik Ahn, Hwayeong Lee, Seonghyun Park, Seungryong Kim</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this limitation, we formulate Degradation-Aware Optical Flow, a new task targeting accurate dense correspondence estimation from real-world corrupted videos. Our key insight is that the intermediate representations of image restoration diffusion models are inherently corruption-aware but lack temporal awareness. To address this limitation, we lift the model to attend across adjacent frames via full spatio-temporal attention, and empirically demonstrate that the resulting features exhibit zero-shot correspondence capabilities. Based on this finding, we present DA-Flow, a hybrid architecture that fuses these diffusion features with convolutional features within an iterative refinement framework. DA-Flow substantially outperforms existing optical flow methods under severe degradation across multiple benchmarks.</p> - https://arxiv.org/abs/2603.23499 - Tue, 24 Mar 2026 17:59:13 +0000 - - - UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation - https://arxiv.org/abs/2603.23500 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Liu, Zilyu Ye, Linxiao Yuan, Shenhan Zhu, Yu Gao, Jie Wu, Kunchang Li, Xionghui Wang, Xiaonan Nie, Weilin Huang, Wanli Ouyang</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image generation. To advance this direction, we propose a unified reinforcement learning framework tailored for interleaved generation. We validate our approach on its fundamental unit: a single round of reasoning-driven image generation, where the model first expands the user prompt through reasoning, followed by image synthesis. Formulating this multimodal generation process as a Markov Decision Process with sparse terminal rewards, we introduce UniGRPO to jointly optimize text and image generation policies using GRPO. Adopting a minimalist methodology to avoid over-design, we leverage established training recipes for both modalities by seamlessly integrating standard GRPO for reasoning and FlowGRPO for visual synthesis. To ensure scalability to multi-round interleaved generation, we introduce two critical modifications to the original FlowGRPO: (1) eliminating classifier-free guidance to maintain linear, unbranched rollouts, which is essential for scaling to complex scenarios involving multi-turn interactions and multi-condition generation (e.g., editing); and (2) replacing the standard latent KL penalty with an MSE penalty directly on the velocity fields, providing a more robust and direct regularization signal to mitigate reward hacking effectively. Our experiments demonstrate that this unified training recipe significantly enhances image generation quality through reasoning, providing a robust and scalable baseline for the future post-training of fully interleaved models.</p> - https://arxiv.org/abs/2603.23500 - Tue, 24 Mar 2026 17:59:17 +0000 - - - Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments - https://arxiv.org/abs/2603.23638 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Han, Lingfei Qian, Yan Wang, Yueru He, Xueqing Peng, Dongji Feng, Yankai Chen, Haohang Li, Yupeng Cao, Jimin Huang, Xue Liu, Jian-Yun Nie, Sophia Ananiadou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large language models (LLMs) have enabled agentic systems that can reason, plan, and act across complex tasks, but it remains unclear whether they can allocate resources effectively under uncertainty. Unlike short-horizon reactive decisions, allocation requires committing scarce resources over time while balancing competing objectives and preserving flexibility for future needs. We introduce EnterpriseArena, the first benchmark for evaluating agents on long-horizon enterprise resource allocation. It instantiates CFO-style decision-making in a 132-month enterprise simulator combining firm-level financial data, anonymized business documents, macroeconomic and industry signals, and expert-validated operating rules. The environment is partially observable and reveals the state only through budgeted organizational tools, forcing agents to trade off information acquisition against conserving scarce resources. Experiments on eleven advanced LLMs show that this setting remains highly challenging: only 16% of runs survive the full horizon, and larger models do not reliably outperform smaller ones. These results identify long-horizon resource allocation under uncertainty as a distinct capability gap for current LLM agents.</p> - https://arxiv.org/abs/2603.23638 - Tue, 24 Mar 2026 18:25:00 +0000 - - - Understanding the Challenges in Iterative Generative Optimization with LLMs - https://arxiv.org/abs/2603.23994 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23994.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Allen Nie, Xavier Daull, Zhiyi Kuang, Abhinav Akkiraju, Anish Chaudhuri, Max Piasevoli, Ryan Rong, YuCheng Yuan, Prerit Choudhary, Shannon Xiao, Rasool Fakoor, Adith Swaminathan, Ching-An Cheng</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach to building self-improving agents, yet in practice remains brittle: despite active research, only 9% of surveyed agents used any automated optimization. We argue that this brittleness arises because, to set up a learning loop, an engineer must make ``hidden'' design choices: What can the optimizer edit and what is the "right" learning evidence to provide at each update? We investigate three factors that affect most applications: the starting artifact, the credit horizon for execution traces, and batching trials and errors into learning evidence. Through case studies in MLAgentBench, Atari, and BigBench Extra Hard, we find that these design decisions can determine whether generative optimization succeeds, yet they are rarely made explicit in prior work. Different starting artifacts determine which solutions are reachable in MLAgentBench, truncated traces can still improve Atari agents, and larger minibatches do not monotonically improve generalization on BBEH. We conclude that the lack of a simple, universal way to set up learning loops across domains is a major hurdle for productionization and adoption. We provide practical guidance for making these choices.</p> - https://arxiv.org/abs/2603.23994 - Wed, 25 Mar 2026 06:49:24 +0000 - - - CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare - https://arxiv.org/abs/2603.24157 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24157.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Akash Ghosh, Tajamul Ashraf, Rishu Kumar Singh, Numan Saeed, Sriparna Saha, Xiuying Chen, Salman Khan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have focused on short-horizon or general-purpose applications (e.g., mobile or desktop interfaces), leaving long-horizon automation for domain-specific systems, particularly in healthcare, largely unexplored. To address this, we introduce CareFlow, a high-quality human-annotated benchmark comprising complex, long-horizon software workflows across medical annotation tools, DICOM viewers, EHR systems, and laboratory information systems. On this benchmark, existing vision-language models (VLMs) perform poorly, struggling with long-horizon reasoning and multi-step interactions in medical contexts. To overcome this, we propose CarePilot, a multi-agent framework based on the actor-critic paradigm. The Actor integrates tool grounding with dual-memory mechanisms (long-term and short-term experience) to predict the next semantic action from the visual interface and system state. The Critic evaluates each action, updates memory based on observed effects, and either executes or provides corrective feedback to refine the workflow. Through iterative agentic simulation, the Actor learns to perform more robust and reasoning-aware predictions during inference. Our experiments show that CarePilot achieves state-of-the-art performance, outperforming strong closed-source and open-source multimodal baselines by approximately 15.26% and 3.38%, respectively, on our benchmark and out-of-distribution dataset.</p> - https://arxiv.org/abs/2603.24157 - Wed, 25 Mar 2026 10:25:48 +0000 - - - GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents - https://arxiv.org/abs/2603.24329 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24329.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans, Volkan Ustun</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to perceive rapid state changes, attribute actions to the correct entities, and reason about concurrent multi-agent behaviors from a first-person perspective, capabilities that existing benchmarks do not adequately evaluate. We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding. Specifically, we densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World, a natural decomposition for multi-agent environments. From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy that enables fine-grained analysis of where models hallucinate. Evaluation of frontier MLLMs reveals a substantial gap from human performance, with common failures in temporal and cross-video grounding, agent-role attribution, and handling the decision density of the game. We hope GameplayQA stimulates future research at the intersection of embodied AI, agentic perception, and world modeling.</p> - https://arxiv.org/abs/2603.24329 - Wed, 25 Mar 2026 14:10:45 +0000 - - - CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents - https://arxiv.org/abs/2603.24440 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24440.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin, Aarash Feizi, Kaixin Li, Patrice Bechard, Spandana Gella, Sai Rajeswar</p><p><b>Upvotes:</b> 87</p><p><b>Summary:</b> Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarcity of continuous, high-quality human demonstration videos. Recent work emphasizes that continuous video, not sparse screenshots, is the critical missing ingredient for scaling these agents. However, the largest existing open dataset, ScaleCUA, contains only 2 million screenshots, equating to less than 20 hours of video. To address this bottleneck, we introduce CUA-Suite, a large-scale ecosystem of expert video demonstrations and dense annotations for professional desktop computer-use agents. At its core is VideoCUA, which provides approximately 10,000 human-demonstrated tasks across 87 diverse applications with continuous 30 fps screen recordings, kinematic cursor traces, and multi-layerfed reasoning annotations, totaling approximately 55 hours and 6 million frames of expert video. Unlike sparse datasets that capture only final click coordinates, these continuous video streams preserve the full temporal dynamics of human interaction, forming a superset of information that can be losslessly transformed into the formats required by existing agent frameworks. CUA-Suite further provides two complementary resources: UI-Vision, a rigorous benchmark for evaluating grounding and planning capabilities in CUAs, and GroundCUA, a large-scale grounding dataset with 56K annotated screenshots and over 3.6 million UI element annotations. Preliminary evaluation reveals that current foundation action models struggle substantially with professional desktop applications (~60% task failure rate). Beyond evaluation, CUA-Suite's rich multimodal corpus supports emerging research directions including generalist screen parsing, continuous spatial control, video-based reward modeling, and visual world models. All data and models are publicly released.</p> - https://arxiv.org/abs/2603.24440 - Wed, 25 Mar 2026 15:52:56 +0000 - - - Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? - https://arxiv.org/abs/2603.24472 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dohyung Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading performance. We trace this degradation to the suppression of epistemic verbalization - the model's expression of uncertainty during reasoning. Through controlled experiments varying conditioning context richness and task coverage, we show that conditioning the teacher on rich information suppresses uncertainty expression, enabling rapid in-domain optimization with limited task coverage but harming OOD performance, where unseen problems benefit from expressing uncertainty and adjusting accordingly. Across Qwen3-8B, DeepSeek-Distill-Qwen-7B, and Olmo3-7B-Instruct, we observe performance drops of up to 40%. Our findings highlight that exposing appropriate levels of uncertainty is crucial for robust reasoning and underscore the importance of optimizing reasoning behavior beyond merely reinforcing correct answer traces.</p> - https://arxiv.org/abs/2603.24472 - Wed, 25 Mar 2026 16:14:52 +0000 - - - AVO: Agentic Variation Operators for Autonomous Evolutionary Search - https://arxiv.org/abs/2603.24517 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Terry Chen, Zhifan Ye, Bing Xu, Zihao Ye, Timmy Liu, Ali Hassani, Tianqi Chen, Andrew Kerr, Haicheng Wu, Yang Xu, Yu-Jung Chen, Hanfeng Chen, Aditya Kane, Ronny Krashinsky, Ming-Yu Liu, Vinod Grover, Luis Ceze, Roger Bringmann, John Tran, Wei Liu, Fung Xie, Michael Lightstone, Humphrey Shi</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than confining a language model to candidate generation within a prescribed pipeline, AVO instantiates variation as a self-directed agent loop that can consult the current lineage, a domain-specific knowledge base, and execution feedback to propose, repair, critique, and verify implementation edits. We evaluate AVO on attention, among the most aggressively optimized kernel targets in AI, on NVIDIA Blackwell (B200) GPUs. Over 7 days of continuous autonomous evolution on multi-head attention, AVO discovers kernels that outperform cuDNN by up to 3.5% and FlashAttention-4 by up to 10.5% across the evaluated configurations. The discovered optimizations transfer readily to grouped-query attention, requiring only 30 minutes of additional autonomous adaptation and yielding gains of up to 7.0% over cuDNN and 9.3% over FlashAttention-4. Together, these results show that agentic variation operators move beyond prior LLM-in-the-loop evolutionary pipelines by elevating the agent from candidate generator to variation operator, and can discover performance-critical micro-architectural optimizations that produce kernels surpassing state-of-the-art expert-engineered attention implementations on today's most advanced GPU hardware.</p> - https://arxiv.org/abs/2603.24517 - Wed, 25 Mar 2026 16:55:04 +0000 - - - UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience - https://arxiv.org/abs/2603.24533 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24533.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichuan Lin, Feiyu Liu, Yijun Yang, Jiafei Lyu, Yiming Gao, Yicheng Liu, Zhicong Lu, Yangbin Yu, Mingyu Yang, Junyou Li, Deheng Ye, Jie Jiang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones. Extensive experiments on AndroidWorld show that our 4B model achieves an 81.0% Pass@1 success rate, outperforming numerous recent baselines and exceeding human-level performance. Ablation and case studies further verify the effectiveness of GRSD. Our method represents a significant leap toward efficient, self-evolving, and high-performance mobile GUI automation without expensive manual data annotation.</p> - https://arxiv.org/abs/2603.24533 - Wed, 25 Mar 2026 17:10:29 +0000 - - - VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models - https://arxiv.org/abs/2603.24575 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Jason Ren, Daniel S Weld, Ranjay Krishna</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Scalable Vector Graphics (SVG) are an essential format for technical illustration and digital design, offering precise resolution independence and flexible semantic editability. In practice, however, original vector source files are frequently lost or inaccessible, leaving only "flat" rasterized versions (e.g., PNG or JPEG) that are difficult to modify or scale. Manually reconstructing these figures is a prohibitively labor-intensive process, requiring specialized expertise to recover the original geometric intent. To bridge this gap, we propose VFIG, a family of Vision-Language Models trained for complex and high-fidelity figure-to-SVG conversion. While this task is inherently data-driven, existing datasets are typically small-scale and lack the complexity of professional diagrams. We address this by introducing VFIG-DATA, a large-scale dataset of 66K high-quality figure-SVG pairs, curated from a diverse mix of real-world paper figures and procedurally generated diagrams. Recognizing that SVGs are composed of recurring primitives and hierarchical local structures, we introduce a coarse-to-fine training curriculum that begins with supervised fine-tuning (SFT) to learn atomic primitives and transitions to reinforcement learning (RL) refinement to optimize global diagram fidelity, layout consistency, and topological edge cases. Finally, we introduce VFIG-BENCH, a comprehensive evaluation suite with novel metrics designed to measure the structural integrity of complex figures. VFIG achieves state-of-the-art performance among open-source models and performs on par with GPT-5.2, achieving a VLM-Judge score of 0.829 on VFIG-BENCH.</p> - https://arxiv.org/abs/2603.24575 - Wed, 25 Mar 2026 17:52:23 +0000 - - - SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks - https://arxiv.org/abs/2603.24755 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24755.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabriel Orlanski, Devjeet Roy, Alexander Yun, Changho Shin, Alex Gu, Albert Ge, Dyah Adila, Frederic Sala, Aws Albarghouthi</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Software development is iterative, yet agentic coding benchmarks overwhelmingly evaluate single-shot solutions against complete specifications. Code can pass the test suite but become progressively harder to extend. Recent iterative benchmarks attempt to close this gap, but constrain the agent's design decisions too tightly to faithfully measure how code quality shapes future extensions. We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints, in which agents repeatedly extend their own prior solutions under evolving specifications that force architectural decisions without prescribing internal structure. We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion, the share of complexity mass concentrated in high-complexity functions. No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%. Quality degrades steadily: erosion rises in 80% of trajectories and verbosity in 89.8%. Against 48 open-source Python repositories, agent code is 2.2x more verbose and markedly more eroded. Tracking 20 of those repositories over time shows that human code stays flat, while agent code deteriorates with each iteration. A prompt-intervention study shows that initial quality can be improved, but it does not halt degradation. These results demonstrate that pass-rate benchmarks systematically undermeasure extension robustness, and that current agents lack the design discipline iterative software development demands.</p> - https://arxiv.org/abs/2603.24755 - Wed, 25 Mar 2026 19:26:44 +0000 - - - AVControl: Efficient Framework for Training Audio-Visual Controls - https://arxiv.org/abs/2603.24793 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Matan Ben-Yosef, Tavi Halperin, Naomi Ken Korem, Mohammad Salama, Harel Cain, Asaf Joseph, Anthony Chen, Urska Jelercic, Ofir Bibi</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Controlling video and audio generation requires diverse modalities, from depth and pose to camera trajectories and audio transformations, yet existing approaches either train a single monolithic model for a fixed set of controls or introduce costly architectural changes for each new modality. We introduce AVControl, a lightweight, extendable framework built on LTX-2, a joint audio-visual foundation model, where each control modality is trained as a separate LoRA on a parallel canvas that provides the reference signal as additional tokens in the attention layers, requiring no architectural changes beyond the LoRA adapters themselves. We show that simply extending image-based in-context methods to video fails for structural control, and that our parallel canvas approach resolves this. On the VACE Benchmark, we outperform all evaluated baselines on depth- and pose-guided generation, inpainting, and outpainting, and show competitive results on camera control and audio-visual benchmarks. Our framework supports a diverse set of independently trained modalities: spatially-aligned controls such as depth, pose, and edges, camera trajectory with intrinsics, sparse motion control, video editing, and, to our knowledge, the first modular audio-visual controls for a joint generation model. Our method is both compute- and data-efficient: each modality requires only a small dataset and converges within a few hundred to a few thousand training steps, a fraction of the budget of monolithic alternatives. We publicly release our code and trained LoRA checkpoints.</p> - https://arxiv.org/abs/2603.24793 - Wed, 25 Mar 2026 20:06:43 +0000 - - - Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration - https://arxiv.org/abs/2603.24800 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov, Konstantin Sobolev</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analysis of the denoising process, we demonstrate that introducing a single learned scaling parameter can significantly improve the performance of DiT blocks. Building on this insight, we propose Calibri, a parameter-efficient approach that optimally calibrates DiT components to elevate generative quality. Calibri frames DiT calibration as a black-box reward optimization problem, which is efficiently solved using an evolutionary algorithm and modifies just ~100 parameters. Experimental results reveal that despite its lightweight design, Calibri consistently improves performance across various text-to-image models. Notably, Calibri also reduces the inference steps required for image generation, all while maintaining high-quality outputs.</p> - https://arxiv.org/abs/2603.24800 - Wed, 25 Mar 2026 20:19:50 +0000 - - - FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol - https://arxiv.org/abs/2603.24943 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Zhu, Yimin Tian, Boyang Li, Kehao Wu, Zhongzhi Liang, Junhui Li, Xianyin Zhang, Lifan Guo, Feng Chen, Yong Liu, Chi Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> This paper introduces FinMCP-Bench, a novel benchmark for evaluating large language models (LLMs) in solving real-world financial problems through tool invocation of financial model context protocols. FinMCP-Bench contains 613 samples spanning 10 main scenarios and 33 sub-scenarios, featuring both real and synthetic user queries to ensure diversity and authenticity. It incorporates 65 real financial MCPs and three types of samples, single tool, multi-tool, and multi-turn, allowing evaluation of models across different levels of task complexity. Using this benchmark, we systematically assess a range of mainstream LLMs and propose metrics that explicitly measure tool invocation accuracy and reasoning capabilities. FinMCP-Bench provides a standardized, practical, and challenging testbed for advancing research on financial LLM agents.</p> - https://arxiv.org/abs/2603.24943 - Thu, 26 Mar 2026 02:20:04 +0000 - - - Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale - https://arxiv.org/abs/2603.25040 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yicheng Zou, Dongsheng Zhu, Lin Zhu, Tong Zhu, Yunhua Zhou, Peiheng Zhou, Xinyu Zhou, Dongzhan Zhou, Zhiwang Zhou, Yuhao Zhou, Bowen Zhou, Zhanping Zhong, Zhijie Zhong, Haiteng Zhao, Penghao Zhao, Xiaomeng Zhao, Zhiyuan Zhao, Yechen Zhang, Jin Zhang, Wenwei Zhang, Hongjie Zhang, Zhuo Zhang, Wenlong Zhang, Bo Zhang, Chao Zhang, Chen Zhang, Yuhang Zang, Fei Yuan, Jiakang Yuan, Jiashuo Yu, Jinhui Yin, Haochen Ye, Qian Yao, Bowen Yang, Danni Yang, Kaichen Yang, Ziang Yan, Jun Xu, Yicheng Xu, Wanghan Xu, Xuenan Xu, Chao Xu, Ruiliang Xu, Shuhao Xing, Long Xing, Xinchen Xie, Ling-I Wu, Zijian Wu, Zhenyu Wu, Lijun Wu, Yue Wu, Jianyu Wu, Wen Wu, Fan Wu, Xilin Wei, Qi Wei, Bingli Wang, Rui Wang, Ziyi Wang, Zun Wang, Yi Wang, Haomin Wang, Yizhou Wang, Lintao Wang, Yiheng Wang, Longjiang Wang, Bin Wang, Jian Tong, Zhongbo Tian, Huanze Tang, Chen Tang, Shixiang Tang, Yu Sun, Qiushi Sun, Xuerui Su, Qisheng Su, Chenlin Su, Demin Song, Jin Shi, Fukai Shang, Yuchen Ren, Pengli Ren, Xiaoye Qu, Yuan Qu, Jiantao Qiu, Yu Qiao, Runyu Peng, Tianshuo Peng, Jiahui Peng, Qizhi Pei, Zhuoshi Pan, Linke Ouyang, Wenchang Ning, Yichuan Ma, Zerun Ma, Ningsheng Ma, Runyuan Ma, Chengqi Lyu, Haijun Lv, Han Lv, Lindong Lu, Kuikun Liu, Jiangning Liu, Yuhong Liu, Kai Liu, Hongwei Liu, Zhoumianze Liu, Mengjie Liu, Ziyu Liu, Wenran Liu, Yang Liu, Liwei Liu, Kaiwen Liu, Junyao Lin, Junming Lin, Tianyang Lin, Dahua Lin, Jianze Liang, Linyang Li, Peiji Li, Zonglin Li, Zehao Li, Pengze Li, Guoyan Li, Lingkai Kong, Linglin Jing, Zhenjiang Jin, Feifei Jiang, Qian Jiang, Junhao Huang, Zixian Huang, Haian Huang, Zhouqi Hua, Han Hu, Linfeng Hou, Yinan He, Conghui He, Tianyao He, Xu Guo, Qipeng Guo, Aijia Guo, Yuzhe Gu, Lixin Gu, Jingyang Gong, Qiming Ge, Jiaye Ge, Songyang Gao, Jianfei Gao, Xinyu Fang, Caihua fan, Yue Fan, Yanhui Duan, Zichen Ding, Shengyuan Ding, Xuanlang Dai, Erfei Cui, Ganqu Cui, Pei Chu, Tao Chu, Guangran Cheng, Yu Cheng, Kai Chen, Yongkang Chen, Chiyu Chen, Guanzhou Chen, Qiaosheng Chen, Sitao Chen, Xin Chen, Haojiong Chen, Yicheng Chen, Weihan Cao, Yuhang Cao, Qinglong Cao, Lei Bai</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.</p> - https://arxiv.org/abs/2603.25040 - Thu, 26 Mar 2026 05:21:45 +0000 - - - MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data - https://arxiv.org/abs/2603.25319 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25319.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhekai Chen, Yuqing Wang, Manyuan Zhang, Xihui Liu</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance degradation as the number of input references grows. We identify the root cause as a fundamental data bottleneck: existing datasets are dominated by single- or few-reference pairs and lack the structured, long-context supervision needed to learn dense inter-reference dependencies. To address this, we introduce MacroData, a large-scale dataset of 400K samples, each containing up to 10 reference images, systematically organized across four complementary dimensions -- Customization, Illustration, Spatial reasoning, and Temporal dynamics -- to provide comprehensive coverage of the multi-reference generation space. Recognizing the concurrent absence of standardized evaluation protocols, we further propose MacroBench, a benchmark of 4,000 samples that assesses generative coherence across graded task dimensions and input scales. Extensive experiments show that fine-tuning on MacroData yields substantial improvements in multi-reference generation, and ablation studies further reveal synergistic benefits of cross-task co-training and effective strategies for handling long-context complexity. The dataset and benchmark will be publicly released.</p> - https://arxiv.org/abs/2603.25319 - Thu, 26 Mar 2026 11:09:14 +0000 - - - RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models - https://arxiv.org/abs/2603.25502 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25502.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufeng Yang, Xianfang Zeng, Zhangqi Jiang, Fukun Yin, Jianzhuang Liu, Wei Cheng, jinghong lan, Shiyu Liu, Yuqi Peng, Gang YU, Shifeng Chen</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often limited by the scale and distribution of their training data, resulting in poor generalization to real-world scenarios. Recently, large-scale image editing models have shown strong generalization ability in restoration tasks, especially for closed-source models like Nano Banana Pro, which can restore images while preserving consistency. Nevertheless, achieving such performance with those large universal models requires substantial data and computational costs. To address this issue, we construct a large-scale dataset covering nine common real-world degradation types and train a state-of-the-art open-source model to narrow the gap with closed-source alternatives. Furthermore, we introduce RealIR-Bench, which contains 464 real-world degraded images and tailored evaluation metrics focusing on degradation removal and consistency preservation. Extensive experiments demonstrate our model ranks first among open-source methods, achieving state-of-the-art performance.</p> - https://arxiv.org/abs/2603.25502 - Thu, 26 Mar 2026 14:39:39 +0000 - - - Voxtral TTS - https://arxiv.org/abs/2603.25551 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25551.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Henry Lagarde, Jean-Malo Delignon, Jaeyoung Kim, John Harvill, Khyathi Raghavi Chandu, Lorenzo Signoretti, Margaret Jennings, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora, Sanchit Gandhi, Samuel Humeau, Soham Ghosh, Srijan Mishra, Van Phung, Abdelaziz Bounhar, Abhinav Rastogi, Adrien Sadé, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Amélie Héliou, Amos You, Andrew Bai, Andrew Zhao, Angele Lenglemetz, Anmol Agarwal, Anton Eliseev, Antonia Calvi, Arjun Majumdar, Arthur Fournier, Artjom Joosen, Avi Sooriyarachchi, Aysenur Karaduman Utkur, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Benjamin Tibi, Bowen Yang, Charlotte Cronjäger, Clémence Lanfranchi, Connor Chen, Corentin Barreau, Corentin Sautier, Cyprien Courtot, Darius Dabert, Diego de las Casas, Elizaveta Demyanenko, Elliot Chane-Sane, Emmanuel Gottlob, Enguerrand Paquin, Etienne Goffinet, Fabien Niel, Faruk Ahmed, Federico Baldassarre, Gabrielle Berrada, Gaëtan Ecrepont, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Guillaume Kunsch, Guillaume Martin, Guillaume Raille, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Harshil Shah, Hope McGovern, Hugo Thimonier, Indraneel Mukherjee, Irene Zhang, Jacques Sun, Jan Ludziejewski, Jason Rute, Jérémie Dentan, Joachim Studnia, Jonas Amar, Joséphine Delas, Josselin Somerville Roberts, Julien Tauran, Karmesh Yadav, Kartik Khandelwal, Kilian Tep, Kush Jain, Laurence Aitchison, Laurent Fainsin, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Manan Sharma, Marie Pellat, Mark Prins, Martin Alexandre, Mathieu Poirée, Mathieu Schmitt, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mert Unsal, Mia Chiquier, Mikhail Biriuchinskii, Minh-Quang Pham, Mircea Lica, Morgane Rivière, Nathan Grinsztajn, Neha Gupta, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philippe Pinel, Philomène Chagniot, Pierre Stock, Piotr Miłoś, Prateek Gupta, Pravesh Agrawal, Quentin Torroba, Ram Ramrakhya, Randall Isenhour, Rishi Shah, Romain Sauvestre, Roman Soletskyi, Rosalie Millner, Rupert Menneer, Sagar Vaze, Samuel Barry, Samuel Belkadi, Sandeep Subramanian, Sean Cha, Shashwat Verma, Siddhant Waghjale, Siddharth Gandhi, Simon Lepage, Sumukh Aithal, Szymon Antoniak, Tarun Kumar Vangani, Teven Le Scao, Théo Cachet, Theo Simon Sorg, Thibaut Lavril, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Edwards, Tyler Wang, Umar Jamil, Umberto Tomasini, Valeriia Nemychnikova, Vedant Nanda, Victor Jouault, Vincent Maladière, Vincent Pfister, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen-Ding Li, William Havard, William Marshall, Xinghui Li, Xingran Guo, Xinyu Yang, Yannic Neuhaus, Yassine El Ouahidi, Yassir Bendou, Yihan Wang, Yimu Pan, Zaccharie Ramzi, Zhenlin Xu</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid architecture that combines auto-regressive generation of semantic speech tokens with flow-matching for acoustic tokens. These tokens are encoded and decoded with Voxtral Codec, a speech tokenizer trained from scratch with a hybrid VQ-FSQ quantization scheme. In human evaluations conducted by native speakers, Voxtral TTS is preferred for multilingual voice cloning due to its naturalness and expressivity, achieving a 68.4\% win rate over ElevenLabs Flash v2.5. We release the model weights under a CC BY-NC license.</p> - https://arxiv.org/abs/2603.25551 - Thu, 26 Mar 2026 15:23:34 +0000 - - - Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes - https://arxiv.org/abs/2603.25562 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25562.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqian Fu, Haohuan Huang, Kaiwen Jiang, Yuanheng Zhu, Dongbin Zhao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> On-policy distillation (OPD) is appealing for large language model (LLM) post-training because it evaluates teacher feedback on student-generated rollouts rather than fixed teacher traces. In long-horizon settings, however, the common sampled-token variant is fragile: it reduces distribution matching to a one-token signal and becomes increasingly unreliable as rollouts drift away from prefixes the teacher commonly visits. We revisit OPD from the estimator and implementation sides. Theoretically, token-level OPD is biased relative to sequence-level reverse-KL, but it has a much tighter worst-case variance bound; our toy study shows the same tradeoff empirically, with stronger future-reward coupling producing higher gradient variance and less stable learning. Empirically, we identify three failure modes of sampled-token OPD: an imbalanced one-token signal, unreliable teacher guidance on student-generated prefixes, and distortions caused by tokenizer or special-token mismatch. We address these issues with teacher top-K local support matching, implemented as truncated reverse-KL with top-p rollout sampling and special-token masking. Across single-task math reasoning and multi-task agentic-plus-math training, this objective yields more stable optimization and better downstream performance than sampled-token OPD.</p> - https://arxiv.org/abs/2603.25562 - Thu, 26 Mar 2026 15:35:59 +0000 - - - PixelSmile: Toward Fine-Grained Facial Expression Editing - https://arxiv.org/abs/2603.25728 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25728.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiabin Hua, Hengyuan Xu, Aojie Li, Wei Cheng, Gang Yu, Xingjun Ma, Yu-Gang Jiang</p><p><b>Upvotes:</b> 111</p><p><b>Summary:</b> Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, we construct the Flex Facial Expression (FFE) dataset with continuous affective annotations and establish FFE-Bench to evaluate structural confusion, editing accuracy, linear controllability, and the trade-off between expression editing and identity preservation. We propose PixelSmile, a diffusion framework that disentangles expression semantics via fully symmetric joint training. PixelSmile combines intensity supervision with contrastive learning to produce stronger and more distinguishable expressions, achieving precise and stable linear expression control through textual latent interpolation. Extensive experiments demonstrate that PixelSmile achieves superior disentanglement and robust identity preservation, confirming its effectiveness for continuous, controllable, and fine-grained expression editing, while naturally supporting smooth expression blending.</p> - https://arxiv.org/abs/2603.25728 - Thu, 26 Mar 2026 17:59:04 +0000 - - - MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models - https://arxiv.org/abs/2603.25744 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25744.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bocheng Zou, Mu Cai, Mark Stanley, Dingfu Lu, Yong Jae Lee</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training, inference typically remains restricted to a single, fixed scale. This prevalent single-scale paradigm overlooks a fundamental property of visual perception: varying resolutions offer complementary inductive biases, where low-resolution views excel at global semantic recognition and high-resolution views are essential for fine-grained refinement. In this work, we propose Multi-Resolution Fusion (MuRF), a simple yet universally effective strategy to harness this synergy at inference time. Instead of relying on a single view, MuRF constructs a unified representation by processing an image at multiple resolutions through a frozen VFM and fusing the resulting features. The universality of MuRF is its most compelling attribute. It is not tied to a specific architecture, serving instead as a fundamental, training-free enhancement to visual representation. We empirically validate this by applying MuRF to a broad spectrum of critical computer vision tasks across multiple distinct VFM families - primarily DINOv2, but also demonstrating successful generalization to contrastive models like SigLIP2.</p> - https://arxiv.org/abs/2603.25744 - Thu, 26 Mar 2026 17:59:58 +0000 - - - Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting - https://arxiv.org/abs/2603.25745 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixing Lao, Xuyang Bai, Xiaoyang Wu, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without per-scene optimization, a capability previously out of reach for feed-forward methods, all while using significantly fewer Gaussian primitives. Project page: https://yxlao.github.io/lgtm/</p> - https://arxiv.org/abs/2603.25745 + ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling + https://arxiv.org/abs/2603.25746 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25746.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yawen Luo, Xiaoyu Shi, Junhao Zhuang, Yutian Chen, Quande Liu, Xintao Wang, Pengfei Wan, Tianfan Xue</p><p><b>Upvotes:</b> 153</p><p><b>Summary:</b> Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame generation. By reformulating the task as next-shot generation conditioned on historical context, ShotStream allows users to dynamically instruct ongoing narratives via streaming prompts. We achieve this by first fine-tuning a text-to-video model into a bidirectional next-shot generator, which is then distilled into a causal student via Distribution Matching Distillation. To overcome the challenges of inter-shot consistency and error accumulation inherent in autoregressive generation, we introduce two key innovations. First, a dual-cache memory mechanism preserves visual coherence: a global context cache retains conditional frames for inter-shot consistency, while a local context cache holds generated frames within the current shot for intra-shot consistency. And a RoPE discontinuity indicator is employed to explicitly distinguish the two caches to eliminate ambiguity. Second, to mitigate error accumulation, we propose a two-stage distillation strategy. This begins with intra-shot self-forcing conditioned on ground-truth historical shots and progressively extends to inter-shot self-forcing using self-generated histories, effectively bridging the train-test gap. Extensive experiments demonstrate that ShotStream generates coherent multi-shot videos with sub-second latency, achieving 16 FPS on a single GPU. It matches or exceeds the quality of slower bidirectional models, paving the way for real-time interactive storytelling. Training and inference code, as well as the models, are available on our</p> + https://arxiv.org/abs/2603.25746 Thu, 26 Mar 2026 17:59:59 +0000 + + RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation + https://arxiv.org/abs/2603.25804 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25804.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Zhetong Li, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To address this gap, we introduce \texttt{RealChart2Code}, a new large-scale benchmark with over 2,800 instances grounded in authentic datasets and featuring tasks with clear analytical intent. Crucially, it is the first benchmark to systematically evaluate chart generation from large-scale raw data and assess iterative code refinement in a multi-turn conversational setting. Our comprehensive evaluation of 14 leading VLMs on RealChart2Code reveals significant performance degradation compared to simpler benchmarks, highlighting their struggles with complex plot structures and authentic data. Our analysis uncovers a substantial performance gap between proprietary and open-weight models and confirms that even state-of-the-art VLMs often fail to accurately replicate intricate, multi-panel charts. These findings provide valuable insights into the current limitations of VLMs and guide future research directions. We release the benchmark and code at https://github.com/Speakn0w/RealChart2Code.</p> + https://arxiv.org/abs/2603.25804 + Thu, 26 Mar 2026 18:11:46 +0000 + + + ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? + https://arxiv.org/abs/2603.25823 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25823.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haonan Han, Jiancheng Huang, Xiaopeng Sun, Junyan He, Rui Yang, Jie Hu, Xiaojiang Peng, Lin Ma, Xiaoming Wei, Xiu Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Beneath the stunning visual fidelity of modern AIGC models lies a "logical desert", where systems fail tasks that require physical, causal, or complex spatial reasoning. Current evaluations largely rely on superficial metrics or fragmented benchmarks, creating a ``performance mirage'' that overlooks the generative process. To address this, we introduce ViGoR Vision-G}nerative Reasoning-centric Benchmark), a unified framework designed to dismantle this mirage. ViGoR distinguishes itself through four key innovations: 1) holistic cross-modal coverage bridging Image-to-Image and Video tasks; 2) a dual-track mechanism evaluating both intermediate processes and final results; 3) an evidence-grounded automated judge ensuring high human alignment; and 4) granular diagnostic analysis that decomposes performance into fine-grained cognitive dimensions. Experiments on over 20 leading models reveal that even state-of-the-art systems harbor significant reasoning deficits, establishing ViGoR as a critical ``stress test'' for the next generation of intelligent vision models. The demo have been available at https://vincenthancoder.github.io/ViGoR-Bench/</p> + https://arxiv.org/abs/2603.25823 + Thu, 26 Mar 2026 18:40:09 +0000 + + + Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio + https://arxiv.org/abs/2603.25926 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25926.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijiong Yu, Shuai Yuan, Jie Zheng, Huazheng Wang, Ji Pei</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to account for the extreme variance in natural language information density. While adopting a density-aware dynamic compression ratio seems intuitive, empirical investigations reveal that models struggle intrinsically with operations parameterized by input dependent, continuous structural hyperparameters. To resolve this pitfall, we introduce Semi-Dynamic Context Compression framework. Our approach features a Discrete Ratio Selector, which predicts a compression target based on intrinsic information density and quantizes it to a predefined set of discrete compression ratios. It is efficiently jointly trained with the compressor on synthetic data, with the summary lengths as a proxy to create labels for compression ratio prediction. Extensive evaluations confirm that our density-aware framework, utilizing mean pooling as the backbone, consistently outperforms static baselines, establishing a robust Pareto frontier for context compression techniques. Our code, data and model weights are available at https://github.com/yuyijiong/semi-dynamic-context-compress</p> + https://arxiv.org/abs/2603.25926 + Thu, 26 Mar 2026 21:36:55 +0000 + + + QuitoBench: A High-Quality Open Time Series Forecasting Benchmark + https://arxiv.org/abs/2603.26017 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26017.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqiao Xue, Zhaoyang Zhu, Wei Zhang, Rongyao Cai, Rui Wang, Yixiang Mu, Fan Zhou, Jianguo Li, Peng Di, Hang Yu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Time series forecasting is critical across finance, healthcare, and cloud computing, yet progress is constrained by a fundamental bottleneck: the scarcity of large-scale, high-quality benchmarks. To address this gap, we introduce QuitoBench, a regime-balanced benchmark for time series forecasting with coverage across eight trendtimesseasonalitytimesforecastability (TSF) regimes, designed to capture forecasting-relevant properties rather than application-defined domain labels. The benchmark is built upon Quito, a billion-scale time series corpus of application traffic from Alipay spanning nine business domains. Benchmarking 10 models from deep learning, foundation models, and statistical baselines across 232,200 evaluation instances, we report four key findings: (i) a context-length crossover where deep learning models lead at short context (L=96) but foundation models dominate at long context (L ge 576); (ii) forecastability is the dominant difficulty driver, producing a 3.64 times MAE gap across regimes; (iii) deep learning models match or surpass foundation models at 59 times fewer parameters; and (iv) scaling the amount of training data provides substantially greater benefit than scaling model size for both model families. These findings are validated by strong cross-benchmark and cross-metric consistency. Our open-source release enables reproducible, regime-aware evaluation for time series forecasting research.</p> + https://arxiv.org/abs/2603.26017 + Fri, 27 Mar 2026 02:24:34 +0000 + + + DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models + https://arxiv.org/abs/2603.26164 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26164.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Liang, Zhengyang Zhao, Meiyi Qiang, Mingrui Chen, Lu Ma, Rongyi Yu, Hengyi Feng, Shixuan Sun, Zimo Meng, Xiaochen Ma, Xuanlin Yang, Qifeng Cai, Ruichuan An, Bohan Zeng, Zhen Hao Wong, Chengyu Shen, Runming He, Zhaoyang Han, Yaowei Zheng, Fangcheng Fu, Conghui He, Bin Cui, Zhiyu Li, Weinan E, Wentao Zhang</p><p><b>Upvotes:</b> 172</p><p><b>Summary:</b> Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters but also the selection, composition, and weighting of training data during optimization. However, existing approaches to data selection, data mixture optimization, and data reweighting are often developed in isolated codebases with inconsistent interfaces, hindering reproducibility, fair comparison, and practical integration. In this paper, we present DataFlex, a unified data-centric dynamic training framework built upon LLaMA-Factory. DataFlex supports three major paradigms of dynamic data optimization: sample selection, domain mixture adjustment, and sample reweighting, while remaining fully compatible with the original training workflow. It provides extensible trainer abstractions and modular components, enabling a drop-in replacement for standard LLM training, and unifies key model-dependent operations such as embedding extraction, inference, and gradient computation, with support for large-scale settings including DeepSpeed ZeRO-3. We conduct comprehensive experiments across multiple data-centric methods. Dynamic data selection consistently outperforms static full-data training on MMLU across both Mistral-7B and Llama-3.2-3B. For data mixture, DoReMi and ODM improve both MMLU accuracy and corpus-level perplexity over default proportions when pretraining Qwen2.5-1.5B on SlimPajama at 6B and 30B token scales. DataFlex also achieves consistent runtime improvements over original implementations. These results demonstrate that DataFlex provides an effective, efficient, and reproducible infrastructure for data-centric dynamic training of LLMs.</p> + https://arxiv.org/abs/2603.26164 + Fri, 27 Mar 2026 08:28:02 +0000 + + + AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing + https://arxiv.org/abs/2603.26546 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Liu, Weitao Xiong, Kunming Luo, Manyuan Zhang, Peng Liu, Yuan Liu, Ping Tan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Generative video models have significantly advanced the photorealistic synthesis of adverse weather for autonomous driving; however, they consistently demand massive datasets to learn rare weather scenarios. While 3D-aware editing methods alleviate these data constraints by augmenting existing video footage, they are fundamentally bottlenecked by costly per-scene optimization and suffer from inherent geometric and illumination entanglement. In this work, we introduce AutoWeather4D, a feed-forward 3D-aware weather editing framework designed to explicitly decouple geometry and illumination. At the core of our approach is a G-buffer Dual-pass Editing mechanism. The Geometry Pass leverages explicit structural foundations to enable surface-anchored physical interactions, while the Light Pass analytically resolves light transport, accumulating the contributions of local illuminants into the global illumination to enable dynamic 3D local relighting. Extensive experiments demonstrate that AutoWeather4D achieves comparable photorealism and structural consistency to generative baselines while enabling fine-grained parametric physical control, serving as a practical data engine for autonomous driving.</p> + https://arxiv.org/abs/2603.26546 + Fri, 27 Mar 2026 15:56:47 +0000 + + + VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward + https://arxiv.org/abs/2603.26599 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26599.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaochong An, Orest Kupyn, Théo Uscidda, Andrea Colaco, Karan Ahuja, Serge Belongie, Mar Gonzalez-Franco, Marta Tintore Gazulla</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying geometry-aware alignment. However, architectural modifications can compromise the generalization of internet-scale pretrained models, while existing alignment methods are limited to static scenes and rely on RGB-space rewards that require repeated VAE decoding, incurring substantial compute overhead and failing to generalize to highly dynamic real-world scenes. To preserve the pretrained capacity while improving geometric consistency, we propose VGGRPO (Visual Geometry GRPO), a latent geometry-guided framework for geometry-aware video post-training. VGGRPO introduces a Latent Geometry Model (LGM) that stitches video diffusion latents to geometry foundation models, enabling direct decoding of scene geometry from the latent space. By constructing LGM from a geometry model with 4D reconstruction capability, VGGRPO naturally extends to dynamic scenes, overcoming the static-scene limitations of prior methods. Building on this, we perform latent-space Group Relative Policy Optimization with two complementary rewards: a camera motion smoothness reward that penalizes jittery trajectories, and a geometry reprojection consistency reward that enforces cross-view geometric coherence. Experiments on both static and dynamic benchmarks show that VGGRPO improves camera stability, geometry consistency, and overall quality while eliminating costly VAE decoding, making latent-space geometry-guided reinforcement an efficient and flexible approach to world-consistent video generation.</p> + https://arxiv.org/abs/2603.26599 + Fri, 27 Mar 2026 16:57:51 +0000 + + + Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling + https://arxiv.org/abs/2603.26610 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruixing Zhang, Hanzhang Jiang, Leilei Sun, Liangzhe Han, Jibin Wang, Weifeng Lv</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Mobile devices continuously interact with cellular base stations, generating massive volumes of signaling records that provide broad coverage for understanding human mobility. However, such records offer only coarse location cues (e.g., serving-cell identifiers) and therefore limit their direct use in applications that require high-precision GPS trajectories. This paper studies the Sig2GPS problem: reconstructing GPS trajectories from cellular signaling. Inspired by domain experts often lay the signaling trace on the map and sketch the corresponding GPS route, unlike conventional solutions that rely on complex multi-stage engineering pipelines or regress coordinates, Sig2GPS is reframed as an image-to-video generation task that directly operates in the map-visual domain: signaling traces are rendered on a map, and a video generation model is trained to draw a continuous GPS path. To support this paradigm, a paired signaling-to-trajectory video dataset is constructed to fine-tune an open-source video model, and a trajectory-aware reinforcement learning-based optimization method is introduced to improve generation fidelity via rewards. Experiments on large-scale real-world datasets show substantial improvements over strong engineered and learning-based baselines, while additional results on next GPS prediction indicate scalability and cross-city transferability. Overall, these results suggest that map-visual video generation provides a practical interface for trajectory data mining by enabling direct generation and refinement of continuous paths under map constraints.</p> + https://arxiv.org/abs/2603.26610 + Fri, 27 Mar 2026 17:07:13 +0000 + + + Make Geometry Matter for Spatial Reasoning + https://arxiv.org/abs/2603.26639 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26639.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihua Zhang, Qiuhong Shen, Shizun Wang, Tianbo Pan, Xinchao Wang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited. Recent advances try to handle this limitation by injecting geometry tokens from pretrained 3D foundation models into VLMs. Nevertheless, we observe that naive token fusion followed by standard fine-tuning in this line of work often leaves such geometric cues underutilized for spatial reasoning, as VLMs tend to rely heavily on 2D visual cues. In this paper, we propose GeoSR, a framework designed to make geometry matter by encouraging VLMs to actively reason with geometry tokens. GeoSR introduces two key components: (1) Geometry-Unleashing Masking, which strategically masks portions of 2D vision tokens during training to weaken non-geometric shortcuts and force the model to consult geometry tokens for spatial reasoning; and (2) Geometry-Guided Fusion, a gated routing mechanism that adaptively amplifies geometry token contributions in regions where geometric evidence is critical. Together, these designs unleash the potential of geometry tokens for spatial reasoning tasks. Extensive experiments on both static and dynamic spatial reasoning benchmarks demonstrate that GeoSR consistently outperforms prior methods and establishes new state-of-the-art performance by effectively leveraging geometric information. The project page is available at https://suhzhang.github.io/GeoSR/.</p> + https://arxiv.org/abs/2603.26639 + Fri, 27 Mar 2026 17:45:12 +0000 + + + Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification + https://arxiv.org/abs/2603.26648 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan, Mingdao Liu, Xiaotao Gu, Jie Tang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, thorough and reliable evaluation, we propose workflow-based agent verification paradigm based on two complementary components: a GUI agent verifier and a VLM-based judge. We evaluate multiple visual language models instantiated under different coding-agent frameworks, revealing substantial performance gaps at all task levels, with state-of-the-art models still struggling on full-stack development.</p> + https://arxiv.org/abs/2603.26648 + Fri, 27 Mar 2026 17:50:45 +0000 + + + PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning + https://arxiv.org/abs/2603.26653 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaoxuan Li, Zhixuan Zhao, Hanze Deng, Zirun Ma, Shulin Tian, Zuyan Liu, Yushi Hu, Haoning Wu, Yuhao Dong, Benlin Liu, Ziwei Liu, Ranjay Krishna</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence and compositional constraints under conjunctive and sequential logic, spanning perceptual subtasks such as objects, attributes, relations, locations, actions, and events, and requiring skills including semantic recognition, visual correspondence, temporal reasoning, and spatial reasoning. The benchmark contains 1,114 highly complex questions on 279 videos from diverse domains including city walk tours, indoor villa tours, video games, and extreme outdoor sports, with 100% manual annotation. Human studies show that PerceptionComp requires substantial test-time thinking and repeated perception steps: participants take much longer than on prior benchmarks, and accuracy drops to near chance (18.97%) when rewatching is disallowed. State-of-the-art MLLMs also perform substantially worse on PerceptionComp than on existing benchmarks: the best model in our evaluation, Gemini-3-Flash, reaches only 45.96% accuracy in the five-choice setting, while open-source models remain below 40%. These results suggest that perception-centric long-horizon video reasoning remains a major bottleneck, and we hope PerceptionComp will help drive progress in perceptual reasoning.</p> + https://arxiv.org/abs/2603.26653 + Fri, 27 Mar 2026 17:54:36 +0000 + + + GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation + https://arxiv.org/abs/2603.26661 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26661.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicolas von Lützow, Barbara Rössle, Katharina Schmid, Matthias Nießner</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians via next-token prediction, thus facilitating full 3D scene generation. We first compress Gaussian primitives into a discrete latent grid using a sparse 3D convolutional autoencoder with vector quantization. The resulting tokens are serialized and modeled using a causal transformer with 3D rotary positional embedding, enabling sequential generation of spatial structure and appearance. Unlike diffusion-based methods that refine scenes holistically, our formulation constructs scenes step-by-step, naturally supporting completion, outpainting, controllable sampling via temperature, and flexible generation horizons. This formulation leverages the compositional inductive biases and scalability of autoregressive modeling while operating on explicit representations compatible with modern neural rendering pipelines, positioning autoregressive transformers as a complementary paradigm for controllable and context-aware 3D generation.</p> + https://arxiv.org/abs/2603.26661 + Fri, 27 Mar 2026 17:58:05 +0000 + + + TAPS: Task Aware Proposal Distributions for Speculative Sampling + https://arxiv.org/abs/2603.27027 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27027.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna, Hasan Abed Al Kader Hammoud, Bernard Ghanem</p><p><b>Upvotes:</b> 140</p><p><b>Summary:</b> Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad generic corpora, which leaves it unclear how much speculative decoding quality depends on the draft training distribution. We study this question with lightweight HASS and EAGLE-2 drafters trained on MathInstruct, ShareGPT, and mixed-data variants, evaluated on MT-Bench, GSM8K, MATH-500, and SVAMP. Measured by acceptance length, task-specific training yields clear specialization: MathInstruct-trained drafts are strongest on reasoning benchmarks, while ShareGPT-trained drafts are strongest on MT-Bench. Mixed-data training improves robustness, but larger mixtures do not dominate across decoding temperatures. We also study how to combine specialized drafters at inference time. Naive checkpoint averaging performs poorly, whereas confidence-based routing improves over single-domain drafts and merged-tree verification yields the highest acceptance length overall for both backbones. Finally, confidence is a more useful routing signal than entropy: rejected tokens tend to have higher entropy, but confidence produces much clearer benchmark-level routing decisions. These results show that speculative decoding quality depends not only on draft architecture, but also on the match between draft training data and downstream workload, and that specialized drafters are better combined at inference time than in weight space.</p> + https://arxiv.org/abs/2603.27027 + Fri, 27 Mar 2026 22:34:20 +0000 + + + Text Data Integration + https://arxiv.org/abs/2603.27055 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Ataur Rahman, Dimitris Sacharidis, Oscar Romero, Sergi Nadal</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Data comes in many forms. From a shallow perspective, they can be viewed as being either in structured (e.g., as a relation, as key-value pairs) or unstructured (e.g., text, image) formats. So far, machines have been fairly good at processing and reasoning over structured data that follows a precise schema. However, the heterogeneity of data poses a significant challenge on how well diverse categories of data can be meaningfully stored and processed. Data Integration, a crucial part of the data engineering pipeline, addresses this by combining disparate data sources and providing unified data access to end-users. Until now, most data integration systems have leaned on only combining structured data sources. Nevertheless, unstructured data (a.k.a. free text) also contains a plethora of knowledge waiting to be utilized. Thus, in this chapter, we firstly make the case for the integration of textual data, to later present its challenges, state of the art and open problems.</p> + https://arxiv.org/abs/2603.27055 + Sat, 28 Mar 2026 00:03:41 +0000 + + + ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding + https://arxiv.org/abs/2603.27064 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27064.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jovana Kondic, Pengyuan Li, Dhiraj Joshi, Isaac Sanchez, Ben Wiesel, Shafiq Abedin, Amit Alfassy, Eli Schwartz, Daniel Caraballo, Yagmur Gizem Cinar, Florian Scheidegger, Steven I. Ross, Daniel Karl I. Weidele, Hang Hua, Ekaterina Arutyunova, Roei Herzig, Zexue He, Zihan Wang, Xinyue Yu, Yunfei Zhao, Sicong Jiang, Minghao Liu, Qunshu Lin, Peter Staar, Luis Lastras, Aude Oliva, Rogerio Feris</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a capability where current vision-language models (VLMs) remain limited. We introduce ChartNet, a high-quality, million-scale multimodal dataset designed to advance chart interpretation and reasoning. ChartNet leverages a novel code-guided synthesis pipeline to generate 1.5 million diverse chart samples spanning 24 chart types and 6 plotting libraries. Each sample consists of five aligned components: plotting code, rendered chart image, data table, natural language summary, and question-answering with reasoning, providing fine-grained cross-modal alignment. To capture the full spectrum of chart comprehension, ChartNet additionally includes specialized subsets encompassing human annotated data, real-world data, safety, and grounding. Moreover, a rigorous quality-filtering pipeline ensures visual fidelity, semantic accuracy, and diversity across chart representations. Fine-tuning on ChartNet consistently improves results across benchmarks, demonstrating its utility as large-scale supervision for multimodal models. As the largest open-source dataset of its kind, ChartNet aims to support the development of foundation models with robust and generalizable capabilities for data visualization understanding. The dataset is publicly available at https://huggingface.co/datasets/ibm-granite/ChartNet</p> + https://arxiv.org/abs/2603.27064 + Sat, 28 Mar 2026 00:45:05 +0000 + + + Story2Proposal: A Scaffold for Structured Scientific Paper Writing + https://arxiv.org/abs/2603.27065 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27065.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoyang Qian, Wei Shi, Xu Lin, Li Ling, Meng Luo, Ziming Wang, Zhiwei Zhang, Tengyue Xu, Gaoge Liu, Zhentao Zhang, Shuo Zhang, Ziqi Wang, Zheng Feng, Yan Luo, Shu Xu, Yongjin Chen, Zhibo Feng, Zhuo Chen, Bruce Yuan, Biao Wu, Harry Wang, Kris Chen</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment.</p> + https://arxiv.org/abs/2603.27065 + Sat, 28 Mar 2026 00:46:14 +0000 + + + daVinci-LLM:Towards the Science of Pretraining + https://arxiv.org/abs/2603.27164 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27164.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiwei Qin, Yixiu Liu, Tiantian Mi, Muhang Xie, Zhen Huang, Weiye Si, Pengrui Lu, Siyuan Feng, Xia Wu, Liming Liu, Ye Luo, Jinlong Hou, Qipeng Guo, Yu Qiao, Pengfei Liu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> The foundational pretraining phase determines a model's capability ceiling, as post-training struggles to overcome capability foundations established during pretraining, yet it remains critically under-explored. This stems from a structural paradox: organizations with computational resources operate under commercial pressures that inhibit transparent disclosure, while academic institutions possess research freedom but lack pretraining-scale computational resources. daVinci-LLM occupies this unexplored intersection, combining industrial-scale resources with full research freedom to advance the science of pretraining. We adopt a fully-open paradigm that treats openness as scientific methodology, releasing complete data processing pipelines, full training processes, and systematic exploration results. Recognizing that the field lacks systematic methodology for data processing, we employ the Data Darwinism framework, a principled L0-L9 taxonomy from filtering to synthesis. We train a 3B-parameter model from random initialization across 8T tokens using a two-stage adaptive curriculum that progressively shifts from foundational capabilities to reasoning-intensive enhancement. Through 200+ controlled ablations, we establish that: processing depth systematically enhances capabilities, establishing it as a critical dimension alongside volume scaling; different domains exhibit distinct saturation dynamics, necessitating adaptive strategies from proportion adjustments to format shifts; compositional balance enables targeted intensification while preventing performance collapse; how evaluation protocol choices shape our understanding of pretraining progress. By releasing the complete exploration process, we enable the community to build upon our findings and systematic methodologies to form accumulative scientific knowledge in pretraining.</p> + https://arxiv.org/abs/2603.27164 + Sat, 28 Mar 2026 07:00:49 +0000 + + + EpochX: Building the Infrastructure for an Emergent Agent Civilization + https://arxiv.org/abs/2603.27304 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huacan Wang, Chaofa Yuan, Xialie Zhuang, Tu Hu, Shuo Zhang, Jun Han, Shi Wei, Daiqiang Li, Jingping Liu, Kunyi Wang, Zihan Yin, Zhenheng Tang, Andy Wang, Henry Peng Zou, Philip S. Yu, Sen Hu, Qizhen Lan, Ronghao Chen</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approaching a similar inflection point: as foundation models make broad task execution and tool use increasingly accessible, the binding constraint shifts from raw capability to how work is delegated, verified, and rewarded at scale. We introduce EpochX, a credits-native marketplace infrastructure for human-agent production networks. EpochX treats humans and agents as peer participants who can post tasks or claim them. Claimed tasks can be decomposed into subtasks and executed through an explicit delivery workflow with verification and acceptance. Crucially, EpochX is designed so that each completed transaction can produce reusable ecosystem assets, including skills, workflows, execution traces, and distilled experience. These assets are stored with explicit dependency structure, enabling retrieval, composition, and cumulative improvement over time. EpochX also introduces a native credit mechanism to make participation economically viable under real compute costs. Credits lock task bounties, budget delegation, settle rewards upon acceptance, and compensate creators when verified assets are reused. By formalizing the end-to-end transaction model together with its asset and incentive layers, EpochX reframes agentic AI as an organizational design problem: building infrastructures where verifiable work leaves persistent, reusable artifacts, and where value flows support durable human-agent collaboration.</p> + https://arxiv.org/abs/2603.27304 + Sat, 28 Mar 2026 15:20:48 +0000 + + + Falcon Perception + https://arxiv.org/abs/2603.27365 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27365.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aviraj Bevli, Sofian Chaybouti, Yasser Dahou, Hakim Hacid, Ngoc Dung Huynh, Phuc H. Le Khac, Sanath Narayan, Wamiq Reyaz Para, Ankit Singh</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Perception-centric systems are typically implemented with a modular encoder-decoder pipeline: a vision backbone for feature extraction and a separate decoder (or late-fusion module) for task prediction. This raises a central question: is this architectural separation essential or can a single early-fusion stack do both perception and task modeling at scale? We introduce Falcon Perception, a unified dense Transformer that processes image patches and text tokens in a shared parameter space from the first layer, using a hybrid attention pattern (bidirectional among image tokens, causal for prediction tokens) to combine global visual context with autoregressive, variable-length instance generation. To keep dense outputs practical, Falcon Perception retains a lightweight token interface and decodes continuous spatial outputs with specialized heads, enabling parallel high-resolution mask prediction. Our design promotes simplicity: we keep a single scalable backbone and shift complexity toward data and training signals, adding only small heads where outputs are continuous and dense. On SA-Co, Falcon Perception improves mask quality to 68.0 Macro-F_1 compared to 62.3 of SAM3. We also introduce PBench, a benchmark targeting compositional prompts (OCR, spatial constraints, relations) and dense long-context regimes, where the model shows better gains. Finally, we extend the same early-fusion recipe to Falcon OCR: a compact 300M-parameter model which attains 80.3% on olmOCR and 88.64 on OmniDocBench.</p> + https://arxiv.org/abs/2603.27365 + Sat, 28 Mar 2026 18:23:20 +0000 + + + Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers + https://arxiv.org/abs/2603.27666 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27666.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhe Liu, Zhenxiong Tan, Yujia Hu, Songhua Liu, Xinchao Wang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Recent advances in diffusion-based controllable visual generation have led to remarkable improvements in image quality. However, these powerful models are typically deployed on cloud servers due to their large computational demands, raising serious concerns about user data privacy. To enable secure and efficient on-device generation, we explore in this paper controllable diffusion models built upon linear attention architectures, which offer superior scalability and efficiency, even on edge devices. Yet, our experiments reveal that existing controllable generation frameworks, such as ControlNet and OminiControl, either lack the flexibility to support multiple heterogeneous condition types or suffer from slow convergence on such linear-attention models. To address these limitations, we propose a novel controllable diffusion framework tailored for linear attention backbones like SANA. The core of our method lies in a unified gated conditioning module working in a dual-path pipeline, which effectively integrates multi-type conditional inputs, such as spatially aligned and non-aligned cues. Extensive experiments on multiple tasks and benchmarks demonstrate that our approach achieves state-of-the-art controllable generation performance based on linear-attention models, surpassing existing methods in terms of fidelity and controllability.</p> + https://arxiv.org/abs/2603.27666 + Sun, 29 Mar 2026 00:00:00 +0000 + + + Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development + https://arxiv.org/abs/2603.27460 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27460.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongying Deng, Cheng Tang, Ziyan Huang, Jiashi Lin, Ying Chen, Junzhi Ning, Chenglong Ma, Jiyao Liu, Wei Li, Yinghao Zhu, Shujian Gao, Yanyan Huang, Sibo Ju, Yanzhou Su, Pengcheng Chen, Wenhao Tang, Tianbin Li, Haoyu Wang, Yuanfeng Ji, Hui Sun, Shaobo Min, Liang Peng, Feilong Tang, Haochen Xue, Rulin Zhou, Chaoyang Zhang, Wenjie Li, Shaohao Rui, Weijie Ma, Xingyue Zhao, Yibin Wang, Kun Yuan, Zhaohui Lu, Shujun Wang, Jinjie Wei, Lihao Liu, Dingkang Yang, Lin Wang, Yulong Li, Haolin Yang, Yiqing Shen, Lequan Yu, Xiaowei Hu, Yun Gu, Yicheng Wu, Benyou Wang, Minghui Zhang, Angelica I. Aviles-Rivero, Qi Gao, Hongming Shan, Xiaoyu Ren, Fang Yan, Hongyu Zhou, Haodong Duan, Maosong Cao, Shanshan Wang, Bin Fu, Xiaomeng Li, Zhi Hou, Chunfeng Song, Lei Bai, Yuan Cheng, Yuandong Pu, Xiang Li, Wenhai Wang, Hao Chen, Jiaxin Zhuang, Songyang Zhang, Huiguang He, Mengzhang Li, Bohan Zhuang, Zhian Bai, Rongshan Yu, Liansheng Wang, Yukun Zhou, Xiaosong Wang, Xin Guo, Guanbin Li, Xiangru Lin, Dakai Jin, Mianxin Liu, Wenlong Zhang, Qi Qin, Conghui He, Yuqiang Li, Ye Luo, Nanqing Dong, Jie Xu, Wenqi Shao, Bo Zhang, Qiujuan Yan, Yihao Liu, Jun Ma, Zhi Lu, Yuewen Cao, Zongwei Zhou, Jianming Liang, Shixiang Tang, Qi Duan, Dongzhan Zhou, Chen Jiang, Yuyin Zhou, Yanwu Xu, Jiancheng Yang, Shaoting Zhang, Xiaohong Liu, Siqi Luo, Yi Xin, Chaoyu Liu, Haochen Wen, Xin Chen, Alejandro Lozano, Min Woo Sun, Yuhui Zhang, Yue Yao, Xiaoxiao Sun, Serena Yeung-Levy, Xia Li, Jing Ke, Chunhui Zhang, Zongyuan Ge, Ming Hu, Jin Ye, Zhifeng Li, Yirong Chen, Yu Qiao, Junjun He</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.</p> + https://arxiv.org/abs/2603.27460 + Sun, 29 Mar 2026 00:46:53 +0000 + + + On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models + https://arxiv.org/abs/2603.27481 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27481.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chongyang Zhao, Mingsong Li, Haodong Lu, Dong Gong</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge. Mixture of Experts (MoE) architectures naturally facilitate this by incrementally adding new experts and expanding routers while keeping the existing ones frozen. However, despite expert isolation, MoE-based continual learners still suffer from forgetting due to routing-drift: old-task tokens become mistakenly attracted to newly added experts, degrading performance on prior tasks. We analyze the failure mode at the token level and reveal the token's dilemma: ambiguous and old tokens in new-task data offer minimal learning benefit yet induce forgetting when routed to new experts, due to their ambiguous routing assignment during training. Motivated by this, we propose LLaVA-DyMoE, a dynamic MoE framework that incrementally expands the MoE with drift-aware token assignment. We characterize token types via their routing score distributions and apply targeted regularization. Specifically, a token-level assignment guidance steers ambiguous and old tokens away from new experts to preserve established routing patterns and alleviate routing-drift, while complementary routing score regularizations enforce expert-group separation and promote new-expert specialization. Extensive experiments demonstrate that our LLaVA-DyMoE effectively mitigates routing-drift-induced forgetting, achieving over a 7% gain in mean final accuracy and a 12% reduction in forgetting compared to baselines. The project page is https://zhaoc5.github.io/DyMoE.</p> + https://arxiv.org/abs/2603.27481 + Sun, 29 Mar 2026 02:30:55 +0000 + + + LongCat-Next: Lexicalizing Modalities as Discrete Tokens + https://arxiv.org/abs/2603.27538 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27538.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meituan LongCat Team, Bin Xiao, Chao Wang, Chengjiang Li, Chi Zhang, Chong Peng, Hang Yu, Hao Yang, Haonan Yan, Haoze Sun, Haozhe Zhao, Hong Liu, Hui Su, Jiaqi Zhang, Jiawei Wang, Jing Li, Kefeng Zhang, Manyuan Zhang, Minhao Jing, Peng Pei, Quan Chen, Taofeng Xue, Tongxin Pan, Xiaotong Li, Xiaoyang Li, Xiaoyu Zhao, Xing Hu, Xinyang Lin, Xunliang Cai, Yan Bai, Yan Feng, Yanjie Li, Yao Qiu, Yerui Sun, Yifan Lu, Ying Luo, Yipeng Mei, Yitian Chen, Yuchen Xie, Yufang Liu, Yufei Chen, Yulei Qian, Yuqi Peng, Zhihang Yu, Zhixiong Han, Changran Wang, Chen Chen, Dian Zheng, Fengjiao Chen, Ge Yang, Haowei Guo, Haozhe Wang, Hongyu Li, Huicheng Jiang, Jiale Hong, Jialv Zou, Jiamu Li, Jianping Lin, Jiaxing Liu, Jie Yang, Jing Jin, Jun Kuang, Juncheng She, Kunming Luo, Kuofeng Gao, Lin Qiu, Linsen Guo, Mianqiu Huang, Qi Li, Qian Wang, Rumei Li, Siyu Ren, Wei Wang, Wenlong He, Xi Chen, Xiao Liu, Xiaoyu Li, Xu Huang, Xuanyu Zhu, Xuezhi Cao, Yaoming Zhu, Yifei Cao, Yimeng Jia, Yizhen Jiang, Yufei Gao, Zeyang Hu, Zhenlong Yuan, Zijian Zhang, Ziwen Wang</p><p><b>Upvotes:</b> 133</p><p><b>Summary:</b> The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next</p> + https://arxiv.org/abs/2603.27538 + Sun, 29 Mar 2026 06:35:03 +0000 + + + STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding + https://arxiv.org/abs/2603.27593 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27593.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junho Kim, Hosu Lee, James M. Rehg, Minsu Kim, Yong Man Ro</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent progress in video large language models (Video-LLMs) has enabled strong offline reasoning over long and complex videos. However, real-world deployments increasingly require streaming perception and proactive interaction, where video frames arrive online and the system must decide not only what to respond, but also when to respond. In this work, we revisit proactive activation in streaming video as a structured sequence modeling problem, motivated by the observation that temporal transitions in streaming video naturally form span-structured activation patterns. To capture this span-level structure, we model activation signals jointly over a sliding temporal window and update them iteratively as new frames arrive. We propose STRIDE (Structured Temporal Refinement with Iterative DEnoising), which employs a lightweight masked diffusion module at the activation interface to jointly predict and progressively refine activation signals across the window. Extensive experiments on diverse streaming benchmarks and downstream models demonstrate that STRIDE shows more reliable and temporally coherent proactive responses, significantly improving when-to-speak decision quality in online streaming scenarios.</p> + https://arxiv.org/abs/2603.27593 + Sun, 29 Mar 2026 09:23:45 +0000 + + + PRBench: End-to-end Paper Reproduction in Physics Research + https://arxiv.org/abs/2603.27646 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27646.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shi Qiu, Junyi Deng, Yiwei Deng, Haoran Dong, Jieyu Fu, Mao Li, Zeyu Li, Zhaolong Zhang, Huiwen Zheng, Leidong Bao, Anqi Lv, Zihan Mo, Yadi Niu, Yiyang Peng, Yu Tian, Yili Wang, Ziyu Wang, Zi-Yu Wang, Jiashen Wei, Liuheng Wu, Aoran Xue, Leyi Yang, Guanglu Yuan, Xiarui Zhan, Jingjun Zhang, Zifan Zheng, Pengfei Liu, Linrui Zhen, Kaiyang Li, Qichang Li, Ziheng Zhou, Guo-En Nian, Yunwei Xiao, Qing-Hong Cao, Linjie Dai, Xu Feng, Peng Gao, Ying Gu, Chang Liu, Jia Liu, Ming-xing Luo, Yan-Qing Ma, Liang-You Peng, Huichao Song, Shufeng Wang, Chenxu Wang, Tao Wang, Yi-Nan Wang, Chengyin Wu, Pengwei Zhao, Hua Xing Zhu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> AI agents powered by large language models exhibit strong reasoning and problem-solving capabilities, enabling them to assist scientific research tasks such as formula derivation and code generation. However, whether these agents can reliably perform end-to-end reproduction from real scientific papers remains an open question. We introduce PRBench, a benchmark of 30 expert-curated tasks spanning 11 subfields of physics. Each task requires an agent to comprehend the methodology of a published paper, implement the corresponding algorithms from scratch, and produce quantitative results matching the original publication. Agents are provided only with the task instruction and paper content, and operate in a sandboxed execution environment. All tasks are contributed by domain experts from over 20 research groups at the School of Physics, Peking University, each grounded in a real published paper and validated through end-to-end reproduction with verified ground-truth results and detailed scoring rubrics. Using an agentified assessment pipeline, we evaluate a set of coding agents on PRBench and analyze their capabilities across key dimensions of scientific reasoning and execution. The best-performing agent, OpenAI Codex powered by GPT-5.3-Codex, achieves a mean overall score of 34%. All agents exhibit a zero end-to-end callback success rate, with particularly poor performance in data accuracy and code correctness. We further identify systematic failure modes, including errors in formula implementation, inability to debug numerical simulations, and fabrication of output data. Overall, PRBench provides a rigorous benchmark for evaluating progress toward autonomous scientific research.</p> + https://arxiv.org/abs/2603.27646 + Sun, 29 Mar 2026 11:44:57 +0000 + + + KAT-Coder-V2 Technical Report + https://arxiv.org/abs/2603.27703 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fengxiang Li, Han Zhang, Haoyang Huang, Jinghui Wang, Jinhua Hao, Kun Yuan, Mengtong Li, Minglei Zhang, Pengcheng Xu, Wenhao Zhuang, Yizhen Shao, Zongxian Feng, Can Tang, Chao Wang, Chengxiao Tong, Fan Yang, Gang Xiong, Haixuan Gao, Han Gao, Hao Wang, Haochen Liu, Hongliang Sun, Jiabao Li, Jingwen Chang, Jun Du, Junyi Peng, Leizhen Cui, Meimei Jing, Mingqi Wu, Shangpeng Yan, Shaotong Qi, Suzhe Xu, Wenxuan Zhao, Xianda Sun, Xuan Xie, Yanbo Wang, Yao Xia, Yinghan Cui, Yingpeng Chen, Yong Wang, Yuze Shi, Zhiwei Shen, Ziyu Wang, Ming Sun, Lin Ye, Bin Chen</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.</p> + https://arxiv.org/abs/2603.27703 + Sun, 29 Mar 2026 14:01:35 +0000 + + + Emergent Social Intelligence Risks in Generative Multi-Agent Systems + https://arxiv.org/abs/2603.27771 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27771.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies.</p> + https://arxiv.org/abs/2603.27771 + Sun, 29 Mar 2026 17:10:28 +0000 + + + MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences + https://arxiv.org/abs/2603.27813 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27813.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijian Wang, Jiarui Jin, Runhao Fu, Zexuan Yan, Xingjian Wang, Mengkang Hu, Eric Wang, Xiaoxi Li, Kangning Zhang, Li Yao, Wenxiang Jiao, Xuelian Cheng, Yuan Lu, Zongyuan Ge</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Research agents have recently achieved significant progress in information seeking and synthesis across heterogeneous textual and visual sources. In this paper, we introduce MuSEAgent, a multimodal reasoning agent that enhances decision-making by extending the capabilities of research agents to discover and leverage stateful experiences. Rather than relying on trajectory-level retrieval, we propose a stateful experience learning paradigm that abstracts interaction data into atomic decision experiences through hindsight reasoning. These experiences are organized into a quality-filtered experience bank that supports policy-driven experience retrieval at inference time. Specifically, MuSEAgent enables adaptive experience exploitation through complementary wide- and deep-search strategies, allowing the agent to dynamically retrieve multimodal guidance across diverse compositional semantic viewpoints. Extensive experiments demonstrate that MuSEAgent consistently outperforms strong trajectory-level experience retrieval baselines on both fine-grained visual perception and complex multimodal reasoning tasks. These results validate the effectiveness of stateful experience modeling in improving multimodal agent reasoning.</p> + https://arxiv.org/abs/2603.27813 + Sun, 29 Mar 2026 18:54:31 +0000 + + + ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks + https://arxiv.org/abs/2603.27862 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27862.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Samin Mahdizadeh Sani, Max Ku, Nima Jamali, Matina Mahdizadeh Sani, Paria Khoshtab, Wei-Chieh Sun, Parnian Fazel, Zhi Rui Tam, Thomas Chong, Edisy Kin Wai Chan, Donald Wai Tong Tsang, Chiao-Wei Hsu, Ting Wai Lam, Ho Yin Sam Ng, Chiafeng Chu, Chak-Wing Mak, Keming Wu, Hiu Tung Wong, Yik Chun Ho, Chi Ruan, Zhuofeng Li, I-Sheng Fang, Shih-Ying Yeh, Ho Kei Cheng, Ping Nie, Wenhu Chen</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Advances in diffusion, autoregressive, and hybrid models have enabled high-quality image synthesis for tasks such as text-to-image, editing, and reference-guided composition. Yet, existing benchmarks remain limited, either focus on isolated tasks, cover only narrow domains, or provide opaque scores without explaining failure modes. We introduce ImagenWorld, a benchmark of 3.6K condition sets spanning six core tasks (generation and editing, with single or multiple references) and six topical domains (artworks, photorealistic images, information graphics, textual graphics, computer graphics, and screenshots). The benchmark is supported by 20K fine-grained human annotations and an explainable evaluation schema that tags localized object-level and segment-level errors, complementing automated VLM-based metrics. Our large-scale evaluation of 14 models yields several insights: (1) models typically struggle more in editing tasks than in generation tasks, especially in local edits. (2) models excel in artistic and photorealistic settings but struggle with symbolic and text-heavy domains such as screenshots and information graphics. (3) closed-source systems lead overall, while targeted data curation (e.g., Qwen-Image) narrows the gap in text-heavy cases. (4) modern VLM-based metrics achieve Kendall accuracies up to 0.79, approximating human ranking, but fall short of fine-grained, explainable error attribution. ImagenWorld provides both a rigorous benchmark and a diagnostic tool to advance robust image generation.</p> + https://arxiv.org/abs/2603.27862 + Sun, 29 Mar 2026 20:42:05 +0000 + + + CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence + https://arxiv.org/abs/2603.28032 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28032.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Zeng, Hanxuan Chen, Yanci Wen, Hong Zhang</p><p><b>Upvotes:</b> 332</p><p><b>Summary:</b> The convergence of low-altitude economies, embodied intelligence, and air-ground cooperative systems creates growing demand for simulation infrastructure capable of jointly modeling aerial and ground agents within a single physically coherent environment. Existing open-source platforms remain domain-segregated: driving simulators lack aerial dynamics, while multirotor simulators lack realistic ground scenes. Bridge-based co-simulation introduces synchronization overhead and cannot guarantee strict spatial-temporal consistency. We present CARLA-Air, an open-source infrastructure that unifies high-fidelity urban driving and physics-accurate multirotor flight within a single Unreal Engine process. The platform preserves both CARLA and AirSim native Python APIs and ROS 2 interfaces, enabling zero-modification code reuse. Within a shared physics tick and rendering pipeline, CARLA-Air delivers photorealistic environments with rule-compliant traffic, socially-aware pedestrians, and aerodynamically consistent UAV dynamics, synchronously capturing up to 18 sensor modalities across all platforms at each tick. The platform supports representative air-ground embodied intelligence workloads spanning cooperation, embodied navigation and vision-language action, multi-modal perception and dataset construction, and reinforcement-learning-based policy training. An extensible asset pipeline allows integration of custom robot platforms into the shared world. By inheriting AirSim's aerial capabilities -- whose upstream development has been archived -- CARLA-Air ensures this widely adopted flight stack continues to evolve within a modern infrastructure. Released with prebuilt binaries and full source: https://github.com/louiszengCN/CarlaAir</p> + https://arxiv.org/abs/2603.28032 + Mon, 30 Mar 2026 04:49:29 +0000 + + + Meta-Harness: End-to-End Optimization of Model Harnesses + https://arxiv.org/abs/2603.28052 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28052.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoonho Lee, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, Chelsea Finn</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering.</p> + https://arxiv.org/abs/2603.28052 + Mon, 30 Mar 2026 05:33:50 +0000 + + + GEMS: Agent-Native Multimodal Generation with Memory and Skills + https://arxiv.org/abs/2603.28088 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28088.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zefeng He, Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Yu Cheng, Yang Yang</p><p><b>Upvotes:</b> 82</p><p><b>Summary:</b> Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose GEMS (Agent-Native Multimodal GEneration with Memory and Skills), a framework that pushes beyond the inherent limitations of foundational models on both general and downstream tasks. GEMS is built upon three core components. Agent Loop introduces a structured multi-agent framework that iteratively improves generation quality through closed-loop optimization. Agent Memory provides a persistent, trajectory-level memory that hierarchically stores both factual states and compressed experiential summaries, enabling a global view of the optimization process while reducing redundancy. Agent Skill offers an extensible collection of domain-specific expertise with on-demand loading, allowing the system to effectively handle diverse downstream applications. Across five mainstream tasks and four downstream tasks, evaluated on multiple generative backends, GEMS consistently achieves significant performance gains. Most notably, it enables the lightweight 6B model Z-Image-Turbo to surpass the state-of-the-art Nano Banana 2 on GenEval2, demonstrating the effectiveness of agent harness in extending model capabilities beyond their original limits.</p> + https://arxiv.org/abs/2603.28088 + Mon, 30 Mar 2026 06:42:55 +0000 + + + Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization + https://arxiv.org/abs/2603.28342 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> He Du, Qiming Ge, Jiakai Hu, Aijun Yang, Zheng Cai, Zixian Huang, Sheng Yuan, Qinxiu Cheng, Xinchen Xie, Yicheng Chen, Yining Li, Jiaxing Xie, Huanan Dong, Yaguang Wu, Xiangjun Huang, Jian Yang, Hui Wang, Bowen Zhou, Bowen Li, Qipeng Guo, Kai Chen</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented post-training recipe. On the agent side, Kernel-Smith maintains a population of executable candidates and iteratively improves them using an archive of top-performing and diverse programs together with structured execution feedback on compilation, correctness, and speedup. To make this search reliable, we build backend-specific evaluation services for Triton on NVIDIA GPUs and Maca on MetaX GPUs. On the training side, we convert long-horizon evolution trajectories into step-centric supervision and reinforcement learning signals by retaining correctness-preserving, high-gain revisions, so that the model is optimized as a strong local improver inside the evolutionary loop rather than as a one-shot generator. Under a unified evolutionary protocol, Kernel-Smith-235B-RL achieves state-of-the-art overall performance on KernelBench with Nvidia Triton backend, attaining the best average speedup ratio and outperforming frontier proprietary models including Gemini-3.0-pro and Claude-4.6-opus. We further validate the framework on the MetaX MACA backend, where our Kernel-Smith-MACA-30B surpasses large-scale counterparts such as DeepSeek-V3.2-think and Qwen3-235B-2507-think, highlighting potential for seamless adaptation across heterogeneous platforms. Beyond benchmark results, the same workflow produces upstream contributions to production systems including SGLang and LMDeploy, demonstrating that LLM-driven kernel optimization can transfer from controlled evaluation to practical deployment.</p> + https://arxiv.org/abs/2603.28342 + Mon, 30 Mar 2026 12:12:49 +0000 + + + Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design + https://arxiv.org/abs/2603.28376 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Zhu, Qianghuai Jia, Tian Lan, Junyang Ren, Feng Gu, Feihu Jiang, Longyue Wang, Zhao Xu, Weihua Luo</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on long-horizon tasks, reliable verification is critical during both training and inference. A major bottleneck in existing paradigms stems from the lack of explicit verification mechanisms in QA data synthesis, trajectory construction, and test-time scaling. Errors introduced at each stage propagate downstream and degrade the overall agent performance. To address this, we present Marco DeepResearch, a deep research agent optimized with a verification-centric framework design at three levels: (1)~QA Data Synthesis: We introduce verification mechanisms to graph-based and agent-based QA synthesis to control question difficulty while ensuring answers are unique and correct; (2)~Trajectory Construction: We design a verification-driven trajectory synthesis method that injects explicit verification patterns into training trajectories; and (3)~Test-time scaling: We use Marco DeepResearch itself as a verifier at inference time and effectively improve performance on challenging questions. Extensive experimental results demonstrate that our proposed Marco DeepResearch agent significantly outperforms 8B-scale deep research agents on most challenging benchmarks, such as BrowseComp and BrowseComp-ZH. Crucially, under a maximum budget of 600 tool calls, Marco DeepResearch even surpasses or approaches several 30B-scale agents, like Tongyi DeepResearch-30B.</p> + https://arxiv.org/abs/2603.28376 + Mon, 30 Mar 2026 12:42:02 +0000 + + + MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome + https://arxiv.org/abs/2603.28407 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28407.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangda Ye, Yuxin Hu, Pengxiang Zhu, Yibo Li, Ziqi Jin, Yao Xiao, Yibo Wang, Lei Wang, Zhen Zhang, Lu Wang, Yue Deng, Bin Wang, Yifan Zhang, Liangcai Su, Xinyu Wang, He Zhao, Chen Wei, Qiang Ren, Bryan Hooi, An Bo, Shuicheng Yan, Lidong Bing</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Recent progress in deep research systems has been impressive, but evaluation still lags behind real user needs. Existing benchmarks predominantly assess final reports using fixed rubrics, failing to evaluate the underlying research process. Most also offer limited multimodal coverage, rely on synthetic tasks that do not reflect real-world query complexity, and cannot be refreshed as knowledge evolves. To address these gaps, we introduce MiroEval, a benchmark and evaluation framework for deep research systems. The benchmark comprises 100 tasks (70 text-only, 30 multimodal), all grounded in real user needs and constructed via a dual-path pipeline that supports periodic updates, enabling a live and evolving setting. The proposed evaluation suite assesses deep research systems along three complementary dimensions: adaptive synthesis quality evaluation with task-specific rubrics, agentic factuality verification via active retrieval and reasoning over both web sources and multimodal attachments, and process-centric evaluation audits how the system searches, reasons, and refines throughout its investigation. Evaluation across 13 systems yields three principal findings: the three evaluation dimensions capture complementary aspects of system capability, with each revealing distinct strengths and weaknesses across systems; process quality serves as a reliable predictor of overall outcome while revealing weaknesses invisible to output-level metrics; and multimodal tasks pose substantially greater challenges, with most systems declining by 3 to 10 points. The MiroThinker series achieves the most balanced performance, with MiroThinker-H1 ranking the highest overall in both settings. Human verification and robustness results confirm the reliability of the benchmark and evaluation framework. MiroEval provides a holistic diagnostic tool for the next generation of deep research agents.</p> + https://arxiv.org/abs/2603.28407 + Mon, 30 Mar 2026 13:16:03 +0000 + + + HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention + https://arxiv.org/abs/2603.28458 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28458.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufei Xu, Fanxu Meng, Fan Jiang, Yuxuan Wang, Ruijie Zhou, Jiexi Wu, Zhixin Pan, Zhaohui Wang, Xiaojuan Tang, Wenjie Pei, Tongxuan Liu, Di yin, Xing Sun, Muhan Zhang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical token for each query using a lightweight indexer, and then computing attention only over the selected subset. While the downstream sparse attention scales efficiently, the indexer still scans the entire prefix for every query, introducing an O(L^2) per-layer bottleneck that becomes prohibitive as context length grows. We propose HISA (Hierarchical Indexed Sparse Attention), a drop-in replacement for the indexer that transforms the search process from a flat token scan into a two-stage hierarchical procedure. First, a block-level coarse filter scores pooled block representatives to prune irrelevant regions. Then, a token-level refinement applies the original indexer only within the remaining candidate blocks. HISA preserves the exact token-level top-k sparsity pattern required by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves a 2times speedup at 32K context length and 4times at 128K. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 with HISA, without any fine-tuning. HISA closely matches the original DSA in quality while significantly outperforming block-sparse baselines. Moreover, the token selection sets produced by HISA and the original DSA exhibit a mean IoU greater than 99%, indicating that the efficiency gains come with virtually no impact on selection fidelity.</p> + https://arxiv.org/abs/2603.28458 + Mon, 30 Mar 2026 13:59:51 +0000 + + + Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms + https://arxiv.org/abs/2603.28489 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28489.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muyang He, Hanzhong Guo, Junxiong Lin, Yizhou Yu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as potential world simulators. However, a critical gap still remains between the theoretical capacity for world simulation and the heavy computational costs of spatiotemporal modeling. To address this, we comprehensively and systematically review video generation frameworks and techniques that consider efficiency as a crucial requirement for practical world modeling. We introduce a novel taxonomy in three dimensions: efficient modeling paradigms, efficient network architectures, and efficient inference algorithms. We further show that bridging this efficiency gap directly empowers interactive applications such as autonomous driving, embodied AI, and game simulation. Finally, we identify emerging research frontiers in efficient video-based world modeling, arguing that efficiency is a fundamental prerequisite for evolving video generators into general-purpose, real-time, and robust world simulators.</p> + https://arxiv.org/abs/2603.28489 + Mon, 30 Mar 2026 14:23:45 +0000 + + + GEditBench v2: A Human-Aligned Benchmark for General Image Editing + https://arxiv.org/abs/2603.28547 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangqi Jiang, Zheng Sun, Xianfang Zeng, Yufeng Yang, Xuanyang Zhang, Yongliang Wu, Wei Cheng, Gang Yu, Xu Yang, Bihan Wen</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks suffer from narrow task coverage, while standard metrics fail to adequately capture visual consistency, i.e., the preservation of identity, structure and semantic coherence between edited and original images. To address these limitations, we introduce GEditBench v2, a comprehensive benchmark with 1,200 real-world user queries spanning 23 tasks, including a dedicated open-set category for unconstrained, out-of-distribution editing instructions beyond predefined tasks. Furthermore, we propose PVC-Judge, an open-source pairwise assessment model for visual consistency, trained via two novel region-decoupled preference data synthesis pipelines. Besides, we construct VCReward-Bench using expert-annotated preference pairs to assess the alignment of PVC-Judge with human judgments on visual consistency evaluation. Experiments show that our PVC-Judge achieves state-of-the-art evaluation performance among open-source models and even surpasses GPT-5.1 on average. Finally, by benchmarking 16 frontier editing models, we show that GEditBench v2 enables more human-aligned evaluation, revealing critical limitations of current models, and providing a reliable foundation for advancing precise image editing.</p> + https://arxiv.org/abs/2603.28547 + Mon, 30 Mar 2026 15:08:32 +0000 + + + Towards a Medical AI Scientist + https://arxiv.org/abs/2603.28589 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28589.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongtao Wu, Boyun Zheng, Dingjie Song, Yu Jiang, Jianfeng Gao, Lei Xing, Lichao Sun, Yixuan Yuan</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> Autonomous systems that generate scientific hypotheses, conduct experiments, and draft manuscripts have recently emerged as a promising paradigm for accelerating discovery. However, existing AI Scientists remain largely domain-agnostic, limiting their applicability to clinical medicine, where research is required to be grounded in medical evidence with specialized data modalities. In this work, we introduce Medical AI Scientist, the first autonomous research framework tailored to clinical autonomous research. It enables clinically grounded ideation by transforming extensively surveyed literature into actionable evidence through clinician-engineer co-reasoning mechanism, which improves the traceability of generated research ideas. It further facilitates evidence-grounded manuscript drafting guided by structured medical compositional conventions and ethical policies. The framework operates under 3 research modes, namely paper-based reproduction, literature-inspired innovation, and task-driven exploration, each corresponding to a distinct level of automated scientific inquiry with progressively increasing autonomy. Comprehensive evaluations by both large language models and human experts demonstrate that the ideas generated by the Medical AI Scientist are of substantially higher quality than those produced by commercial LLMs across 171 cases, 19 clinical tasks, and 6 data modalities. Meanwhile, our system achieves strong alignment between the proposed method and its implementation, while also demonstrating significantly higher success rates in executable experiments. Double-blind evaluations by human experts and the Stanford Agentic Reviewer suggest that the generated manuscripts approach MICCAI-level quality, while consistently surpassing those from ISBI and BIBM. The proposed Medical AI Scientist highlights the potential of leveraging AI for autonomous scientific discovery in healthcare.</p> + https://arxiv.org/abs/2603.28589 + Mon, 30 Mar 2026 15:37:25 +0000 + + + MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models + https://arxiv.org/abs/2603.28590 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Wang, Yifan Sun, Brian Ko, Mann Talati, Jiawen Gong, Zimeng Li, Naicheng Yu, Xucheng Yu, Wei Shen, Vedant Jolly, Huan Zhang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the decision-critical factors driving the model's behavior, leading to the reduced CoT monitorability problem. However, a comprehensive and fully open-source benchmark for studying CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize when CoTs can be used to monitor the factors driving LLM behavior; and (2) two stress-test settings to quantify the extent to which CoT monitorability can be degraded. Extensive experiments across multiple popular LLMs with varying capabilities show that CoT monitorability is higher when producing the final target response requires structural reasoning through the decision-critical factor. Closed-source LLMs generally show lower monitorability, and there exists a negative relationship between monitorability and model capability. Moreover, both open- and closed-source LLMs can intentionally reduce monitorability under stress-tests, with monitorability dropping by up to 30% in some tasks that do not require structural reasoning over the decision-critical factors. Beyond these empirical insights, MonitorBench provides a basis for further research on evaluating future LLMs, studying advanced stress-test monitorability techniques, and developing new monitoring approaches.</p> + https://arxiv.org/abs/2603.28590 + Mon, 30 Mar 2026 15:37:42 +0000 + + + ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning + https://arxiv.org/abs/2603.28610 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huanxuan Liao, Zhongtao Jiang, Yupu Hao, Yuqiao Tan, Shizhu He, Jun Zhao, Kun Xu, Kang Liu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue that the bottleneck lies not in how post-encoding representations are compressed but in the volume of pixels the encoder receives, and address it with ResAdapt, an Input-side adaptation framework that learns how much visual budget each frame should receive before encoding. ResAdapt couples a lightweight Allocator with an unchanged MLLM backbone, so the backbone retains its native visual-token interface while receiving an operator-transformed input. We formulate allocation as a contextual bandit and train the Allocator with Cost-Aware Policy Optimization (CAPO), which converts sparse rollout feedback into a stable accuracy-cost learning signal. Across budget-controlled video QA, temporal grounding, and image reasoning tasks, ResAdapt improves low-budget operating points and often lies on or near the efficiency-accuracy frontier, with the clearest gains on reasoning-intensive benchmarks under aggressive compression. Notably, ResAdapt supports up to 16x more frames at the same visual budget while delivering over 15% performance gain. Code is available at https://github.com/Xnhyacinth/ResAdapt.</p> + https://arxiv.org/abs/2603.28610 + Mon, 30 Mar 2026 15:57:32 +0000 + + + DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing + https://arxiv.org/abs/2603.28713 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28713.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kailai Feng, Yuxiang Wei, Bo Chen, Yang Pan, Hu Ye, Songwei Liu, Chenqian Yan, Yuan Gao</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of parameters, leading to high latency and increased deployment challenges. While on-device diffusion models improve efficiency, they largely focus on T2I generation and lack support for image editing. In this paper, we propose DreamLite, a compact unified on-device diffusion model (0.39B) that supports both T2I generation and text-guided image editing within a single network. DreamLite is built on a pruned mobile U-Net backbone and unifies conditioning through in-context spatial concatenation in the latent space. It concatenates images horizontally as input, using a (target | blank) configuration for generation tasks and (target | source) for editing tasks. To stabilize the training of this compact model, we introduce a task-progressive joint pretraining strategy that sequentially targets T2I, editing, and joint tasks. After high-quality SFT and reinforcement learning, DreamLite achieves GenEval (0.72) for image generation and ImgEdit (4.11) for image editing, outperforming existing on-device models and remaining competitive with several server-side models. By employing step distillation, we further reduce denoising processing to just 4 steps, enabling our DreamLite could generate or edit a 1024 x 1024 image in less than 1s on a Xiaomi 14 smartphone. To the best of our knowledge, DreamLite is the first unified on-device diffusion model that supports both image generation and image editing.</p> + https://arxiv.org/abs/2603.28713 + Mon, 30 Mar 2026 17:30:25 +0000 + + + On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers + https://arxiv.org/abs/2603.28762 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28762.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generative path. In contrast, acting on spatially-committed intermediate latents tends to disrupt the forming visual structure, leading to artifacts. In this work, we propose to apply repulsion in the Contextual Space as a novel framework for achieving rich diversity in Diffusion Transformers. By intervening in the multimodal attention channels, we apply on-the-fly repulsion during the transformer's forward pass, injecting the intervention between blocks where text conditioning is enriched with emergent image structure. This allows for redirecting the guidance trajectory after it is structurally informed but before the composition is fixed. Our results demonstrate that repulsion in the Contextual Space produces significantly richer diversity without sacrificing visual fidelity or semantic adherence. Furthermore, our method is uniquely efficient, imposing a small computational overhead while remaining effective even in modern "Turbo" and distilled models where traditional trajectory-based interventions typically fail.</p> + https://arxiv.org/abs/2603.28762 + Mon, 30 Mar 2026 17:59:13 +0000 + + + PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models + https://arxiv.org/abs/2603.28763 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lorenza Prospero, Orest Kupyn, Ostap Viniavskyi, João F. Henriques, Christian Rupprecht</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Acquiring labeled datasets for 3D human mesh estimation is challenging due to depth ambiguities and the inherent difficulty of annotating 3D geometry from monocular images. Existing datasets are either real, with manually annotated 3D geometry and limited scale, or synthetic, rendered from 3D engines that provide precise labels but suffer from limited photorealism, low diversity, and high production costs. In this work, we explore a third path: generated data. We introduce PoseDreamer, a novel pipeline that leverages diffusion models to generate large-scale synthetic datasets with 3D mesh annotations. Our approach combines controllable image generation with Direct Preference Optimization for control alignment, curriculum-based hard sample mining, and multi-stage quality filtering. Together, these components naturally maintain correspondence between 3D labels and generated images, while prioritizing challenging samples to maximize dataset utility. Using PoseDreamer, we generate more than 500,000 high-quality synthetic samples, achieving a 76% improvement in image-quality metrics compared to rendering-based datasets. Models trained on PoseDreamer achieve performance comparable to or superior to those trained on real-world and traditional synthetic datasets. In addition, combining PoseDreamer with synthetic datasets results in better performance than combining real-world and synthetic datasets, demonstrating the complementary nature of our dataset. We will release the full dataset and generation code.</p> + https://arxiv.org/abs/2603.28763 + Mon, 30 Mar 2026 17:59:18 +0000 + + + Gen-Searcher: Reinforcing Agentic Search for Image Generation + https://arxiv.org/abs/2603.28767 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28767.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jiang, Hongyu Li, Dian Zheng, Chenyang Wang, Xiangyu Yue</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images. We further introduce KnowGen, a comprehensive benchmark that explicitly requires search-grounded external knowledge for image generation and evaluates models from multiple dimensions. Based on these resources, we train Gen-Searcher with SFT followed by agentic reinforcement learning with dual reward feedback, which combines text-based and image-based rewards to provide more stable and informative learning signals for GRPO training. Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE. We hope this work can serve as an open foundation for search agents in image generation, and we fully open-source our data, models, and code.</p> + https://arxiv.org/abs/2603.28767 + Mon, 30 Mar 2026 17:59:56 +0000 + + + OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training + https://arxiv.org/abs/2603.28858 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28858.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiyue Song, Masao Utiyama</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Continual pre-training is widely used to adapt LLMs to target languages and domains, yet the mixture ratio of training data remains a sensitive hyperparameter that is expensive to tune: they must be fixed before training begins, and a suboptimal choice can waste weeks of compute. In this work, we propose OptiMer, which decouples ratio selection from training: we train one CPT model per dataset, extract each model's distribution vector, which represents the parameter shift induced by that dataset, and search for optimal composition weights post-hoc via Bayesian optimization. Experiments on Gemma 3 27B across languages (Japanese, Chinese) and domains (Math, Code) show that OptiMer consistently outperforms data mixture and model averaging baselines with 15-35 times lower search cost. Key findings reveal that 1) the optimized weights can be interpreted as data mixture ratios, and retraining with these ratios improves data mixture CPT, and 2) the same vector pool can be re-optimized for a given objective without any retraining, producing target-tailored models on demand. Our work establishes that data mixture ratio selection, traditionally a pre-training decision, can be reformulated as a post-hoc optimization over distribution vectors, offering a more flexible paradigm for continual pre-training.</p> + https://arxiv.org/abs/2603.28858 + Mon, 30 Mar 2026 18:00:02 +0000 + + + The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning + https://arxiv.org/abs/2603.29025 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yubo Li, Lu Zhang, Tianchong Jiang, Ramayya Krishnan, Rema Padman</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint. We study this through a diagnose-measure-bridge-treat framework. Causal-behavioral analysis of the ``car wash problem'' across six models reveals approximately context-independent sigmoid heuristics: the distance cue exerts 8.7 to 38 times more influence than the goal, and token-level attribution shows patterns more consistent with keyword associations than compositional inference. The Heuristic Override Benchmark (HOB) -- 500 instances spanning 4 heuristic by 5 constraint families with minimal pairs and explicitness gradients -- demonstrates generality across 14 models: under strict evaluation (10/10 correct), no model exceeds 75%, and presence constraints are hardest (44%). A minimal hint (e.g., emphasizing the key object) recovers +15 pp on average, suggesting the failure lies in constraint inference rather than missing knowledge; 12/14 models perform worse when the constraint is removed (up to -39 pp), revealing conservative bias. Parametric probes confirm that the sigmoid pattern generalizes to cost, efficiency, and semantic-similarity heuristics; goal-decomposition prompting recovers +6 to 9 pp by forcing models to enumerate preconditions before answering. Together, these results characterize heuristic override as a systematic reasoning vulnerability and provide a benchmark for measuring progress toward resolving it.</p> + https://arxiv.org/abs/2603.29025 + Mon, 30 Mar 2026 21:36:09 +0000 + + + MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation + https://arxiv.org/abs/2603.29029 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29029.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bharath Krishnamurthy, Ajita Rattani</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal fusion enables controllable synthesis aligned with both high-level semantic intent and low-level structural layout. However, most existing approaches typically extend pre-trained text-to-image pipelines by appending auxiliary control modules or stitching together separate uni-modal networks. These ad hoc designs inherit architectural constraints, duplicate parameters, and often fail under conflicting modalities or mismatched latent spaces, limiting their ability to perform synergistic fusion across semantic and spatial domains. We introduce MMFace-DiT, a unified dual-stream diffusion transformer engineered for synergistic multimodal face synthesis. Its core novelty lies in a dual-stream transformer block that processes spatial (mask/sketch) and semantic (text) tokens in parallel, deeply fusing them through a shared Rotary Position-Embedded (RoPE) Attention mechanism. This design prevents modal dominance and ensures strong adherence to both text and structural priors to achieve unprecedented spatial-semantic consistency for controllable face generation. Furthermore, a novel Modality Embedder enables a single cohesive model to dynamically adapt to varying spatial conditions without retraining. MMFace-DiT achieves a 40% improvement in visual fidelity and prompt alignment over six state-of-the-art multimodal face generation models, establishing a flexible new paradigm for end-to-end controllable generative modeling. The code and dataset are available on our project page: https://vcbsl.github.io/MMFace-DiT/</p> + https://arxiv.org/abs/2603.29029 + Mon, 30 Mar 2026 21:44:18 +0000 + + + Video Models Reason Early: Exploiting Plan Commitment for Maze Solving + https://arxiv.org/abs/2603.30043 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.30043.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaleb Newman, Tyler Zhu, Olga Russakovsky</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Video diffusion models exhibit emergent reasoning capabilities like solving mazes and puzzles, yet little is understood about how they reason during generation. We take a first step towards understanding this and study the internal planning dynamics of video models using 2D maze solving as a controlled testbed. Our investigations reveal two findings. Our first finding is early plan commitment: video diffusion models commit to a high-level motion plan within the first few denoising steps, after which further denoising alters visual details but not the underlying trajectory. Our second finding is that path length, not obstacle density, is the dominant predictor of maze difficulty, with a sharp failure threshold at 12 steps. This means video models can only reason over long mazes by chaining together multiple sequential generations. To demonstrate the practical benefits of our findings, we introduce Chaining with Early Planning, or ChEaP, which only spends compute on seeds with promising early plans and chains them together to tackle complex mazes. This improves accuracy from 7% to 67% on long-horizon mazes and by 2.5x overall on hard tasks in Frozen Lake and VR-Bench across Wan2.2-14B and HunyuanVideo-1.5. Our analysis reveals that current video models possess deeper reasoning capabilities than previously recognized, which can be elicited more reliably with better inference-time scaling.</p> + https://arxiv.org/abs/2603.30043 + Tue, 31 Mar 2026 00:00:00 +0000 + + + AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation + https://arxiv.org/abs/2603.28068 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.28068.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaohe Liao, Kaixun Jiang, Zhihang Liu, Yujie Wei, Junqiu Yu, Quanhao Li, Hong-Tao Yu, Pandeng Li, Yuzheng Wang, Zhen Xing, Shiwei Zhang, Chen-Wei Xie, Yun Zheng, Xihui Liu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Although image generation has boosted various applications via its rapid evolution, whether the state-of-the-art models are able to produce ready-to-use academic illustrations for papers is still largely unexplored. Directly comparing or evaluating the illustration with VLM is native but requires oracle multi-modal understanding ability, which is unreliable for long and complex texts and illustrations. To address this, we propose AIBench, the first benchmark using VQA for evaluating logic correctness of the academic illustrations and VLMs for assessing aesthetics. In detail, we designed four levels of questions proposed from a logic diagram summarized from the method part of the paper, which query whether the generated illustration aligns with the paper on different scales. Our VQA-based approach raises more accurate and detailed evaluations on visual-logical consistency while relying less on the ability of the judger VLM. With our high-quality AIBench, we conduct extensive experiments and conclude that the performance gap between models on this task is significantly larger than general ones, reflecting their various complex reasoning and high-density generation ability. Further, the logic and aesthetics are hard to optimize simultaneously as in handcrafted illustrations. Additional experiments further state that test-time scaling on both abilities significantly boosts the performance on this task.</p> + https://arxiv.org/abs/2603.28068 + Tue, 31 Mar 2026 00:00:00 +0000 + + + ASI-Evolve: AI Accelerates AI + https://arxiv.org/abs/2603.29640 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29640.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixian Xu, Tiantian Mi, Yixiu Liu, Yang Nan, Zhimeng Zhou, Lyumanshan Ye, Lin Zhang, Yu Qiao, Pengfei Liu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-Evolve, an agentic framework for AI-for-AI research that closes this loop through a learn-design-experiment-analyze cycle. ASI-Evolve augments standard evolutionary agents with two key components: a cognition base that injects accumulated human priors into each round of exploration, and a dedicated analyzer that distills complex experimental outcomes into reusable insights for future iterations. To our knowledge, ASI-Evolve is the first unified framework to demonstrate AI-driven discovery across three central components of AI development: data, architectures, and learning algorithms. In neural architecture design, it discovered 105 SOTA linear attention architectures, with the best discovered model surpassing DeltaNet by +0.97 points, nearly 3x the gain of recent human-designed improvements. In pretraining data curation, the evolved pipeline improves average benchmark performance by +3.96 points, with gains exceeding 18 points on MMLU. In reinforcement learning algorithm design, discovered algorithms outperform GRPO by up to +12.5 points on AMC32, +11.67 points on AIME24, and +5.04 points on OlympiadBench. We further provide initial evidence that this AI-for-AI paradigm can transfer beyond the AI stack through experiments in mathematics and biomedicine. Together, these results suggest that ASI-Evolve represents a promising step toward enabling AI to accelerate AI across the foundational stages of development, offering early evidence for the feasibility of closed-loop AI research.</p> + https://arxiv.org/abs/2603.29640 + Tue, 31 Mar 2026 00:00:00 +0000 + + + WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation + https://arxiv.org/abs/2603.29089 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29089.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amogh Joshi, Julian Ost, Felix Heide</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a foundational property of flow matching - namely, defining a path of transport between two data distributions - we model 3D generation more generally as a problem of flowing through 3D data distributions, not limited to conditional denoising. We find that our latent-free flow approach generates causal and accurate 3D structure, and can use this as an intermediate distribution to guide the generation of more complex structure and high-quality texture - all while converging more rapidly than existing methods. We enable controllability over generated scenes with vectorized scene layout conditions for geometric structure control and visual texture control through scene attributes. We confirm the effectiveness of WorldFlow3D on both real outdoor driving scenes and synthetic indoor scenes, validating cross-domain generalizability and high-quality generation on real data distributions. We confirm favorable scene generation fidelity over approaches in all tested settings for unbounded scene generation. For more, see https://light.princeton.edu/worldflow3d.</p> + https://arxiv.org/abs/2603.29089 + Tue, 31 Mar 2026 00:08:17 +0000 + + + Extend3D: Town-Scale 3D Generation + https://arxiv.org/abs/2603.29387 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29387.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seungwoo Yoon, Jinmo Kim, Jaesik Park</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> In this paper, we propose Extend3D, a training-free pipeline for 3D scene generation from a single image, built upon an object-centric 3D generative model. To overcome the limitations of fixed-size latent spaces in object-centric models for representing wide scenes, we extend the latent space in the x and y directions. Then, by dividing the extended latent space into overlapping patches, we apply the object-centric 3D generative model to each patch and couple them at each time step. Since patch-wise 3D generation with image conditioning requires strict spatial alignment between image and latent patches, we initialize the scene using a point cloud prior from a monocular depth estimator and iteratively refine occluded regions through SDEdit. We discovered that treating the incompleteness of 3D structure as noise during 3D refinement enables 3D completion via a concept, which we term under-noising. Furthermore, to address the sub-optimality of object-centric models for sub-scene generation, we optimize the extended latent during denoising, ensuring that the denoising trajectories remain consistent with the sub-scene dynamics. To this end, we introduce 3D-aware optimization objectives for improved geometric structure and texture fidelity. We demonstrate that our method yields better results than prior methods, as evidenced by human preference and quantitative experiments.</p> + https://arxiv.org/abs/2603.29387 + Tue, 31 Mar 2026 07:55:04 +0000 + + + FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration + https://arxiv.org/abs/2603.29557 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29557.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyao Wang, Hongbo Wang, Longze Chen, Zhihao Yang, Guhong Chen, Hamid Alinejad-Rokny, Hui Li, Yuan Lin, Min Yang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Scientific idea generation (SIG) is critical to AI-driven autonomous research, yet existing approaches are often constrained by a static retrieval-then-generation paradigm, leading to homogeneous and insufficiently divergent ideas. In this work, we propose FlowPIE, a tightly coupled retrieval-generation framework that treats literature exploration and idea generation as a co-evolving process. FlowPIE expands literature trajectories via a flow-guided Monte Carlo Tree Search (MCTS) inspired by GFlowNets, using the quality of current ideas assessed by an LLM-based generative reward model (GRM) as a supervised signal to guide adaptive retrieval and construct a diverse, high-quality initial population. Based on this population, FlowPIE models idea generation as a test-time idea evolution process, applying selection, crossover, and mutation with the isolation island paradigm and GRM-based fitness computation to incorporate cross-domain knowledge. It effectively mitigates the information cocoons arising from over-reliance on parametric knowledge and static literature. Extensive evaluations demonstrate that FlowPIE consistently produces ideas with higher novelty, feasibility and diversity compared to strong LLM-based and agent-based frameworks, while enabling reward scaling during test time.</p> + https://arxiv.org/abs/2603.29557 + Tue, 31 Mar 2026 10:37:47 +0000 + + + Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis + https://arxiv.org/abs/2603.29620 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuang Chen, Quanxin Shou, Hangting Chen, Yucheng Zhou, Kaituo Feng, Wenbo Hu, Yi-Fan Zhang, Yunlong Lin, Wenxuan Huang, Mingyang Song, Dasen Dai, Bolin Jiang, Manyuan Zhang, Shi-Xue Zhang, Zhengkai Jiang, Lucas Wang, Zhao Zhong, Yu Cheng, Nanyun Peng</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, they still rely primarily on frozen parametric knowledge, which makes them struggle with real-world image generation involving long-tail and knowledge-intensive concepts. Inspired by the broad success of agents on real-world tasks, we explore agentic modeling to address this limitation. Specifically, we present Unify-Agent, a unified multimodal agent for world-grounded image synthesis, which reframes image generation as an agentic pipeline consisting of prompt understanding, multimodal evidence searching, grounded recaptioning, and final synthesis. To train our model, we construct a tailored multimodal data pipeline and curate 143K high-quality agent trajectories for world-grounded image synthesis, enabling effective supervision over the full agentic generation process. We further introduce FactIP, a benchmark covering 12 categories of culturally significant and long-tail factual concepts that explicitly requires external knowledge grounding. Extensive experiments show that our proposed Unify-Agent substantially improves over its base unified model across diverse benchmarks and real world generation tasks, while approaching the world knowledge capabilities of the strongest closed-source models. As an early exploration of agent-based modeling for world-grounded image synthesis, our work highlights the value of tightly coupling reasoning, searching, and generation for reliable open-world agentic image synthesis.</p> + https://arxiv.org/abs/2603.29620 + Tue, 31 Mar 2026 11:41:13 +0000 + + + CutClaw: Agentic Hours-Long Video Editing via Music Synchronization + https://arxiv.org/abs/2603.29664 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shifang Zhao, Yihan Hu, Ying Shan, Yunchao Wei, Xiaodong Cun</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Editing the video content with audio alignment forms a digital human-made art in current social media. However, the time-consuming and repetitive nature of manual video editing has long been a challenge for filmmakers and professional content creators alike. In this paper, we introduce CutClaw, an autonomous multi-agent framework designed to edit hours-long raw footage into meaningful short videos that leverages the capabilities of multiple Multimodal Language Models~(MLLMs) as an agent system. It produces videos with synchronized music, followed by instructions, and a visually appealing appearance. In detail, our approach begins by employing a hierarchical multimodal decomposition that captures both fine-grained details and global structures across visual and audio footage. Then, to ensure narrative consistency, a Playwriter Agent orchestrates the whole storytelling flow and structures the long-term narrative, anchoring visual scenes to musical shifts. Finally, to construct a short edited video, Editor and Reviewer Agents collaboratively optimize the final cut via selecting fine-grained visual content based on rigorous aesthetic and semantic criteria. We conduct detailed experiments to demonstrate that CutClaw significantly outperforms state-of-the-art baselines in generating high-quality, rhythm-aligned videos. The code is available at: https://github.com/GVCLab/CutClaw.</p> + https://arxiv.org/abs/2603.29664 + Tue, 31 Mar 2026 12:25:53 +0000 + + + Terminal Agents Suffice for Enterprise Automation + https://arxiv.org/abs/2604.00073 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00073.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Patrice Bechard, Orlando Marquez Ayala, Emily Chen, Jordan Skelton, Sagar Davasam, Srinivas Sunkara, Vikas Yadav, Sai Rajeswar</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> There has been growing interest in building agents that can interact with digital platforms to execute meaningful enterprise tasks autonomously. Among the approaches explored are tool-augmented agents built on abstractions such as Model Context Protocol (MCP) and web agents that operate through graphical interfaces. Yet, it remains unclear whether such complex agentic systems are necessary given their cost and operational overhead. We argue that a coding agent equipped only with a terminal and a filesystem can solve many enterprise tasks more effectively by interacting directly with platform APIs. We evaluate this hypothesis across diverse real-world systems and show that these low-level terminal agents match or outperform more complex agent architectures. Our findings suggest that simple programmatic interfaces, combined with strong foundation models, are sufficient for practical enterprise automation.</p> + https://arxiv.org/abs/2604.00073 + Tue, 31 Mar 2026 14:14:47 +0000 + + + Think Anywhere in Code Generation + https://arxiv.org/abs/2603.29957 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.29957.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xue Jiang, Tianyu Zhang, Ge Li, Mengyang Liu, Taozhi Chen, Zhenhua Xu, Binhua Li, Wenpin Jiao, Zhi Jin, Yongbin Li, Yihong Dong</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Recent advances in reasoning Large Language Models (LLMs) have primarily relied on upfront thinking, where reasoning occurs before final answer. However, this approach suffers from critical limitations in code generation, where upfront thinking is often insufficient as problems' full complexity only reveals itself during code implementation. Moreover, it cannot adaptively allocate reasoning effort throughout the code generation process where difficulty varies significantly. In this paper, we propose Think-Anywhere, a novel reasoning mechanism that enables LLMs to invoke thinking on-demand at any token position during code generation. We achieve Think-Anywhere by first teaching LLMs to imitate the reasoning patterns through cold-start training, then leveraging outcome-based RL rewards to drive the model's autonomous exploration of when and where to invoke reasoning. Extensive experiments on four mainstream code generation benchmarks (i.e., LeetCode, LiveCodeBench, HumanEval, and MBPP) show that Think-Anywhere achieves state-of-the-art performance over both existing reasoning methods and recent post-training approaches, while demonstrating consistent generalization across diverse LLMs. Our analysis further reveals that Think-Anywhere enables the model to adaptively invoke reasoning at high-entropy positions, providing enhanced interpretability.</p> + https://arxiv.org/abs/2603.29957 + Tue, 31 Mar 2026 16:24:03 +0000 + + + RawGen: Learning Camera Raw Image Generation + https://arxiv.org/abs/2604.00093 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00093.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyoung Kim, Junyong Lee, Abhijith Punnappurath, Mahmoud Afifi, Sangmin Han, Alex Levinshtein, Michael S. Brown</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Cameras capture scene-referred linear raw images, which are processed by onboard image signal processors (ISPs) into display-referred 8-bit sRGB outputs. Although raw data is more faithful for low-level vision tasks, collecting large-scale raw datasets remains a major bottleneck, as existing datasets are limited and tied to specific camera hardware. Generative models offer a promising way to address this scarcity -- however, existing diffusion frameworks are designed to synthesize photo-finished sRGB images rather than physically consistent linear representations. This paper presents RawGen, to our knowledge the first diffusion-based framework enabling text-to-raw generation for arbitrary target cameras, alongside sRGB-to-raw inversion. RawGen leverages the generative priors of large-scale sRGB diffusion models to synthesize physically meaningful linear outputs, such as CIE XYZ or camera-specific raw representations, via specialized processing in latent and pixel spaces. To handle unknown and diverse ISP pipelines and photo-finishing effects in diffusion-model training data, we build a many-to-one inverse-ISP dataset where multiple sRGB renditions of the same scene generated using diverse ISP parameters are anchored to a common scene-referred target. Fine-tuning a conditional denoiser and specialized decoder on this dataset allows RawGen to obtain camera-centric linear reconstructions that effectively invert the rendering pipeline. We demonstrate RawGen's superior performance over traditional inverse-ISP methods that assume a fixed ISP. Furthermore, we show that augmenting training pipelines with RawGen's scalable, text-driven synthetic data can benefit downstream low-level vision tasks.</p> + https://arxiv.org/abs/2604.00093 + Tue, 31 Mar 2026 18:12:48 +0000 + + + Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time + https://arxiv.org/abs/2604.00917 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Razvan Mihai Popescu, David Gros, Andrei Botocan, Rahul Pandita, Prem Devanbu, Maliheh Izadi</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> The rise of large language models for code has reshaped software development. Autonomous coding agents, able to create branches, open pull requests, and perform code reviews, now actively contribute to real-world projects. Their growing role offers a unique and timely opportunity to investigate AI-driven contributions and their effects on code quality, team dynamics, and software maintainability. In this work, we construct a novel dataset of approximately 110,000 open-source pull requests, including associated commits, comments, reviews, issues, and file changes, collectively representing millions of lines of source code. We compare five popular coding agents, including OpenAI Codex, Claude Code, GitHub Copilot, Google Jules, and Devin, examining how their usage differs in various development aspects such as merge frequency, edited file types, and developer interaction signals, including comments and reviews. Furthermore, we emphasize that code authoring and review are only a small part of the larger software engineering process, as the resulting code must also be maintained and updated over time. Hence, we offer several longitudinal estimates of survival and churn rates for agent-generated versus human-authored code. Ultimately, our findings indicate an increasing agent activity in open-source projects, although their contributions are associated with more churn over time compared to human-authored code.</p> + https://arxiv.org/abs/2604.00917 + Wed, 01 Apr 2026 00:00:00 +0000 + + + EgoSim: Egocentric World Simulator for Embodied Interaction Generation + https://arxiv.org/abs/2604.01001 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01001.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinkun Hao, Mingda Jia, Ruiyan Wang, Xihui Liu, Ran Yi, Lizhuang Ma, Jiangmiao Pang, Xudong Xu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation. Existing egocentric simulators either lack explicit 3D grounding, causing structural drift under viewpoint changes, or treat the scene as static, failing to update world states across multi-stage interactions. EgoSim addresses both limitations by modeling 3D scenes as updatable world states. We generate embodiment interactions via a Geometry-action-aware Observation Simulation model, with spatial consistency from an Interaction-aware State Updating module. To overcome the critical data bottleneck posed by the difficulty in acquiring densely aligned scene-interaction training pairs, we design a scalable pipeline that extracts static point clouds, camera trajectories, and embodiment actions from in-the-wild large-scale monocular egocentric videos. We further introduce EgoCap, a capture system that enables low-cost real-world data collection with uncalibrated smartphones. Extensive experiments demonstrate that EgoSim significantly outperforms existing methods in terms of visual quality, spatial consistency, and generalization to complex scenes and in-the-wild dexterous interactions, while supporting cross-embodiment transfer to robotic manipulation. Codes and datasets will be open soon. The project page is at egosimulator.github.io.</p> + https://arxiv.org/abs/2604.01001 + Wed, 01 Apr 2026 00:00:00 +0000 + + + All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models + https://arxiv.org/abs/2604.00479 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Tian, Shu Zou, Zhaoyuan Yang, Mengqi He, Peter Tu, Jing Zhang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent studies have demonstrated that Reinforcement Learning (RL), notably Group Relative Policy Optimization (GRPO), can intrinsically elicit and enhance the reasoning capabilities of Vision-Language Models (VLMs). However, despite the promise, the underlying mechanisms that drive the effectiveness of RL models as well as their limitations remain underexplored. In this paper, we highlight a fundamental behavioral distinction between RL and base models, where the former engages in deeper yet narrow reasoning, while base models, despite less refined along individual path, exhibit broader and more diverse thinking patterns. Through further analysis of training dynamics, we show that GRPO is prone to diversity collapse, causing models to prematurely converge to a limited subset of reasoning strategies while discarding the majority of potential alternatives, leading to local optima and poor scalability. To address this, we propose Multi-Group Policy Optimization (MUPO), a simple yet effective approach designed to incentivize divergent thinking across multiple solutions, and demonstrate its effectiveness on established benchmarks. Project page: https://xytian1008.github.io/MUPO/</p> + https://arxiv.org/abs/2604.00479 + Wed, 01 Apr 2026 04:52:21 +0000 + + + Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding + https://arxiv.org/abs/2604.00528 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haibo Wang, Zihao Lin, Zhiyang Xu, Lifu Huang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> 3D Visual Grounding (3D-VG) aims to localize objects in 3D scenes via natural language descriptions. While recent advancements leveraging Vision-Language Models (VLMs) have explored zero-shot possibilities, they typically suffer from a static workflow relying on preprocessed 3D point clouds, essentially degrading grounding into proposal matching. To bypass this reliance, our core motivation is to decouple the task: leveraging 2D VLMs to resolve complex spatial semantics, while relying on deterministic multi-view geometry to instantiate the 3D structure. Driven by this insight, we propose "Think, Act, Build (TAB)", a dynamic agentic framework that reformulates 3D-VG tasks as a generative 2D-to-3D reconstruction paradigm operating directly on raw RGB-D streams. Specifically, guided by a specialized 3D-VG skill, our VLM agent dynamically invokes visual tools to track and reconstruct the target across 2D frames. Crucially, to overcome the multi-view coverage deficit caused by strict VLM semantic tracking, we introduce the Semantic-Anchored Geometric Expansion, a mechanism that first anchors the target in a reference video clip and then leverages multi-view geometry to propagate its spatial location across unobserved frames. This enables the agent to "Build" the target's 3D representation by aggregating these multi-view features via camera parameters, directly mapping 2D visual cues to 3D coordinates. Furthermore, to ensure rigorous assessment, we identify flaws such as reference ambiguity and category errors in existing benchmarks and manually refine the incorrect queries. Extensive experiments on ScanRefer and Nr3D demonstrate that our framework, relying entirely on open-source models, significantly outperforms previous zero-shot methods and even surpasses fully supervised baselines.</p> + https://arxiv.org/abs/2604.00528 + Wed, 01 Apr 2026 06:12:16 +0000 + + + UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems + https://arxiv.org/abs/2604.00590 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingming Ha, Guanchen Wang, Linxun Chen, Xuan Rao, Yuexin Shi, Tianbao Ma, Zhaojie Liu, Yunqian Fan, Zilong Lu, Yanan Niu, Han Li, Kun Gai</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> In recent years, the scaling laws of recommendation models have attracted increasing attention, which govern the relationship between performance and parameters/FLOPs of recommenders. Currently, there are three mainstream architectures for achieving scaling in recommendation models, namely attention-based, TokenMixer-based, and factorization-machine-based methods, which exhibit fundamental differences in both design philosophy and architectural structure. In this paper, we propose a unified scaling architecture for recommendation systems, namely UniMixer, to improve scaling efficiency and establish a unified theoretical framework that unifies the mainstream scaling blocks. By transforming the rule-based TokenMixer to an equivalent parameterized structure, we construct a generalized parameterized feature mixing module that allows the token mixing patterns to be optimized and learned during model training. Meanwhile, the generalized parameterized token mixing removes the constraint in TokenMixer that requires the number of heads to be equal to the number of tokens. Furthermore, we establish a unified scaling module design framework for recommender systems, which bridges the connections among attention-based, TokenMixer-based, and factorization-machine-based methods. To further boost scaling ROI, a lightweight UniMixing module is designed, UniMixing-Lite, which further compresses the model parameters and computational cost while significantly improve the model performance. The scaling curves are shown in the following figure. Extensive offline and online experiments are conducted to verify the superior scaling abilities of UniMixer.</p> + https://arxiv.org/abs/2604.00590 + Wed, 01 Apr 2026 07:57:40 +0000 + + + A Survey of On-Policy Distillation for Large Language Models + https://arxiv.org/abs/2604.00626 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00626.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyang Song, Mao Zheng</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Knowledge distillation has become a primary mechanism for transferring reasoning and domain expertise from frontier Large Language Models (LLMs) to smaller, deployable students. However, the dominant paradigm remains off-policy: students train on static teacher-generated data and never encounter their own errors during learning. This train--test mismatch, an instance of exposure bias, causes prediction errors to compound autoregressively at inference time. On-Policy Distillation (OPD) addresses this by letting the student generate its own trajectories and receive teacher feedback on these self-generated outputs, grounding distillation in the theory of interactive imitation learning. Despite rapid growth spanning divergence minimization, reward-guided learning, and self-play, the OPD literature remains fragmented with no unified treatment. This survey provides the first comprehensive overview of OPD for LLMs. We introduce a unified f-divergence framework over on-policy samples and organize the landscape along three orthogonal dimensions: feedback signal (logit-based, outcome-based, or self-play), teacher access (white-box, black-box, or teacher-free), and loss granularity (token-level, sequence-level, or hybrid). We systematically analyze representative methods, examine industrial deployments, and identify open problems including distillation scaling laws, uncertainty-aware feedback, and agent-level distillation.</p> + https://arxiv.org/abs/2604.00626 + Wed, 01 Apr 2026 08:32:34 +0000 + + + Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants + https://arxiv.org/abs/2604.00842 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Deepak Nathani, Cheng Zhang, Chang Huan, Jiaming Shan, Yinfei Yang, Alkesh Patel, Zhe Gan, William Yang Wang, Michael Saxon, Xin Eric Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders their development. Existing approaches model apps as flat tool-calling APIs, failing to capture the stateful and sequential nature of user interaction in digital environments and making realistic user simulation infeasible. We introduce Proactive Agent Research Environment (Pare), a framework for building and evaluating proactive agents in digital environments. Pare models applications as finite state machines with stateful navigation and state-dependent action space for the user simulator, enabling active user simulation. Building on this foundation, we present Pare-Bench, a benchmark of 143 diverse tasks spanning communication, productivity, scheduling, and lifestyle apps, designed to test context observation, goal inference, intervention timing, and multi-app orchestration.</p> + https://arxiv.org/abs/2604.00842 + Wed, 01 Apr 2026 12:53:01 +0000 + + + Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers + https://arxiv.org/abs/2604.01128 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao, Kenta Watanabe, Toshihiko Yamasaki, Kiyoharu Aizawa</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> This paper introduces the first systematic evaluation framework for quantifying the quality and risks of papers written by modern coding agents. While AI-driven paper writing has become a growing concern, rigorous evaluation of the quality and potential risks of AI-written papers remains limited, and a unified understanding of their reliability is still lacking. We introduce Paper Reconstruction Evaluation (PaperRecon), an evaluation framework in which an overview (overview.md) is created from an existing paper, after which an agent generates a full paper based on the overview and minimal additional resources, and the result is subsequently compared against the original paper. PaperRecon disentangles the evaluation of the AI-written papers into two orthogonal dimensions, Presentation and Hallucination, where Presentation is evaluated using a rubric and Hallucination is assessed via agentic evaluation grounded in the original paper source. For evaluation, we introduce PaperWrite-Bench, a benchmark of 51 papers from top-tier venues across diverse domains published after 2025. Our experiments reveal a clear trade-off: while both ClaudeCode and Codex improve with model advances, ClaudeCode achieves higher presentation quality at the cost of more than 10 hallucinations per paper on average, whereas Codex produces fewer hallucinations but lower presentation quality. This work takes a first step toward establishing evaluation frameworks for AI-driven paper writing and improving the understanding of its risks within the research community.</p> + https://arxiv.org/abs/2604.01128 + Wed, 01 Apr 2026 16:48:04 +0000 + + + Reasoning Shift: How Context Silently Shortens LLM Reasoning + https://arxiv.org/abs/2604.01161 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01161.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gleb Rodionov</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting phenomenon: reasoning models tend to produce much shorter reasoning traces (up to 50%) for the same problem under different context conditions compared to the traces produced when the problem is presented in isolation. A finer-grained analysis reveals that this compression is associated with a decrease in self-verification and uncertainty management behaviors, such as double-checking. While this behavioral shift does not compromise performance on straightforward problems, it might affect performance on more challenging tasks. We hope our findings draw additional attention to both the robustness of reasoning models and the problem of context management for LLMs and LLM-based agents.</p> + https://arxiv.org/abs/2604.01161 + Wed, 01 Apr 2026 17:14:18 +0000 + + + Embarrassingly Simple Self-Distillation Improves Code Generation + https://arxiv.org/abs/2604.01193 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruixiang Zhang, Richard He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We answer in the affirmative with simple self-distillation (SSD): sample solutions from the model with certain temperature and truncation configurations, then fine-tune on those samples with standard supervised fine-tuning. SSD improves Qwen3-30B-Instruct from 42.4% to 55.3% pass@1 on LiveCodeBench v6, with gains concentrating on harder problems, and it generalizes across Qwen and Llama models at 4B, 8B, and 30B scale, including both instruct and thinking variants. To understand why such a simple method can work, we trace these gains to a precision-exploration conflict in LLM decoding and show that SSD reshapes token distributions in a context-dependent way, suppressing distractor tails where precision matters while preserving useful diversity where exploration matters. Taken together, SSD offers a complementary post-training direction for improving LLM code generation.</p> + https://arxiv.org/abs/2604.01193 + Wed, 01 Apr 2026 17:39:50 +0000 + + + Universal YOCO for Efficient Depth Scaling + https://arxiv.org/abs/2604.01220 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutao Sun, Li Dong, Tianzhu Ye, Shaohan Huang, Jianyong Wang, Furu Wei</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> The rise of test-time scaling has remarkably boosted the reasoning and agentic proficiency of Large Language Models (LLMs). Yet, standard Transformers struggle to scale inference-time compute efficiently, as conventional looping strategies suffer from high computational overhead and a KV cache that inflates alongside model depth. We present Universal YOCO (YOCO-U), which combines the YOCO decoder-decoder architecture with recursive computation to achieve a synergistic effect greater than either alone. Built on the YOCO framework, YOCO-U implements a Universal Self-Decoder that performs multiple iterations via parameter sharing, while confining the iterative process to shallow, efficient-attention layers. This combination yields a favorable capability-efficiency tradeoff that neither YOCO nor recursion achieves independently. The YOCO architecture provides a constant global KV cache and linear pre-filling, while partial recursion enhances representational depth with limited overhead. Together, YOCO-U improves token utility and scaling behavior while maintaining efficient inference. Empirical results confirm that YOCO-U remains highly competitive in general and long-context benchmarks, demonstrating that the integration of efficient-attention architectures and recursive computation is a promising direction for scalable LLMs.</p> + https://arxiv.org/abs/2604.01220 + Wed, 01 Apr 2026 17:58:21 +0000 + + + HippoCamp: Benchmarking Contextual Agents on Personal Computers + https://arxiv.org/abs/2604.01221 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhe Yang, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen, Yichi Zhang, Zujin Guo, Mengying Yu, Zinan Zhang, Jingkang Yang, Chen Change Loy, Ziwei Liu</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. Unlike existing agent benchmarks that focus on tasks like web interaction, tool use, or software automation in generic settings, HippoCamp evaluates agents in user-centric environments to model individual user profiles and search massive personal files for context-aware reasoning. Our benchmark instantiates device-scale file systems over real-world profiles spanning diverse modalities, comprising 42.4 GB of data across over 2K real-world files. Building upon the raw files, we construct 581 QA pairs to assess agents' capabilities in search, evidence perception, and multi-step reasoning. To facilitate fine-grained analysis, we provide 46.1K densely annotated structured trajectories for step-wise failure diagnosis. We evaluate a wide range of state-of-the-art multimodal large language models (MLLMs) and agentic methods on HippoCamp. Our comprehensive experiments reveal a significant performance gap: even the most advanced commercial models achieve only 48.3% accuracy in user profiling, struggling particularly with long-horizon retrieval and cross-modal reasoning within dense personal file systems. Furthermore, our step-wise failure diagnosis identifies multimodal perception and evidence grounding as the primary bottlenecks. Ultimately, HippoCamp exposes the critical limitations of current agents in realistic, user-centric environments and provides a robust foundation for developing next-generation personal AI assistants.</p> + https://arxiv.org/abs/2604.01221 + Wed, 01 Apr 2026 17:58:33 +0000 + + + VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification + https://arxiv.org/abs/2604.01569 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01569.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Meng, Tan Yue, Qi Xu, Haochen Wang, Zhongwei Ren, Weisong Liu, Yuhao Wang, Renrui Zhang, Yunhai Tong, Haodong Duan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual understanding and reasoning, and (2) answer correctness is often measured without verifying whether models identify the precise spatio-temporal evidence supporting their predictions. To address this, we present VideoZeroBench, a hierarchical benchmark designed for challenging long-video question answering that rigorously verifies spatio-temporal evidence. It comprises 500 manually annotated questions across 13 domains, paired with temporal intervals and spatial bounding boxes as evidence. To disentangle answering generation, temporal grounding, and spatial grounding, we introduce a five-level evaluation protocol that progressively tightens evidence requirements. Experiments show that even Gemini-3-Pro correctly answers fewer than 17% of questions under the standard end-to-end QA setting (Level-3). When grounding constraints are imposed, performance drops sharply: No model exceeds 1% accuracy when both correct answering and accurate spatio-temporal localization are required (Level-5), with most failing to achieve any correct grounded predictions. These results expose a significant gap between surface-level answer correctness and genuine evidence-based reasoning, revealing that grounded video understanding remains a bottleneck for long-video QA. We further analyze performance across minimal evidence spans, atomic abilities, and inference paradigms, providing insights for future research in grounded video reasoning. The benchmark and code will be made publicly available.</p> + https://arxiv.org/abs/2604.01569 + Thu, 02 Apr 2026 00:00:00 +0000 + + + DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data + https://arxiv.org/abs/2604.01666 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01666.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wonjoon Jin, Jiyun Won, Janghyeok Han, Qi Dai, Chong Luo, Seung-Hwan Baek, Sunghyun Cho</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in commonly used training datasets. To address this, we introduce DynaVid, a video synthesis framework that leverages synthetic motion data in training, which is represented as optical flow and rendered using computer graphics pipelines. This approach offers two key advantages. First, synthetic motion offers diverse motion patterns and precise control signals that are difficult to obtain from real data. Second, unlike rendered videos with artificial appearances, rendered optical flow encodes only motion and is decoupled from appearance, thereby preventing models from reproducing the unnatural look of synthetic videos. Building on this idea, DynaVid adopts a two-stage generation framework: a motion generator first synthesizes motion, and then a motion-guided video generator produces video frames conditioned on that motion. This decoupled formulation enables the model to learn dynamic motion patterns from synthetic data while preserving visual realism from real-world videos. We validate our framework on two challenging scenarios, vigorous human motion generation and extreme camera motion control, where existing datasets are particularly limited. Extensive experiments demonstrate that DynaVid improves the realism and controllability in dynamic motion generation and camera motion control.</p> + https://arxiv.org/abs/2604.01666 + Thu, 02 Apr 2026 00:00:00 +0000 + + + Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation + https://arxiv.org/abs/2604.02289 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02289.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chongjie Ye, Cheng Cao, Chuanyu Pan, Yiming Hao, Yihao Zhi, Yuanming Hu, Xiaoguang Han</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capability to 3D remains challenging due to limited data. Compared to abundant 2D imagery, high-quality 3D assets are scarce, making 3D synthesis under-constrained. Existing methods often rely on indirect pipelines that edit in 2D and lift results into 3D via optimization, sacrificing geometric consistency. We present Omni123, a 3D-native foundation model that unifies text-to-2D and text-to-3D generation within a single autoregressive framework. Our key insight is that cross-modal consistency between images and 3D can serve as an implicit structural constraint. By representing text, images, and 3D as discrete tokens in a shared sequence space, the model leverages abundant 2D data as a geometric prior to improve 3D representations. We introduce an interleaved X-to-X training paradigm that coordinates diverse cross-modal tasks over heterogeneous paired datasets without requiring fully aligned text-image-3D triplets. By traversing semantic-visual-geometric cycles (e.g., text to image to 3D to image) within autoregressive sequences, the model jointly enforces semantic alignment, appearance fidelity, and multi-view geometric consistency. Experiments show that Omni123 significantly improves text-guided 3D generation and editing, demonstrating a scalable path toward multimodal 3D world models.</p> + https://arxiv.org/abs/2604.02289 + Thu, 02 Apr 2026 00:00:00 +0000 + + + GPA: Learning GUI Process Automation from Demonstrations + https://arxiv.org/abs/2604.01676 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zirui Zhao, Jun Hao Liew, Yan Yang, Wenzhuo Yang, Ziyang Luo, Doyen Sahoo, Silvio Savarese, Junnan Li</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addressing the fragility of traditional RPA and the non-deterministic risks of current vision language model-based GUI agents, GPA introduces three core benefits: (1) Robustness via Sequential Monte Carlo-based localization to handle rescaling and detection uncertainty; (2) Deterministic and Reliability safeguarded by readiness calibration; and (3) Privacy through fast, fully local execution. This approach delivers the adaptability, robustness, and security required for enterprise workflows. It can also be used as an MCP/CLI tool by other agents with coding capabilities so that the agent only reasons and orchestrates while GPA handles the GUI execution. We conducted a pilot experiment to compare GPA with Gemini 3 Pro (with CUA tools) and found that GPA achieves higher success rate with 10 times faster execution speed in finishing long-horizon GUI tasks.</p> + https://arxiv.org/abs/2604.01676 + Thu, 02 Apr 2026 00:00:00 +0000 + + + UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving + https://arxiv.org/abs/2604.02190 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongkang Li, Lijun Zhou, Sixu Yan, Bencheng Liao, Tianyi Yan, Kaixin Xiong, Long Chen, Hongwei Xie, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Haiyang Sun, Xinggang Wang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have recently emerged in autonomous driving, with the promise of leveraging rich world knowledge to improve the cognitive capabilities of driving systems. However, adapting such models for driving tasks currently faces a critical dilemma between spatial perception and semantic reasoning. Consequently, existing VLA systems are forced into suboptimal compromises: directly adopting 2D Vision-Language Models yields limited spatial perception, whereas enhancing them with 3D spatial representations often impairs the native reasoning capacity of VLMs. We argue that this dilemma largely stems from the coupled optimization of spatial perception and semantic reasoning within shared model parameters. To overcome this, we propose UniDriveVLA, a Unified Driving Vision-Language-Action model based on Mixture-of-Transformers that addresses the perception-reasoning conflict via expert decoupling. Specifically, it comprises three experts for driving understanding, scene perception, and action planning, which are coordinated through masked joint attention. In addition, we combine a sparse perception paradigm with a three-stage progressive training strategy to improve spatial perception while maintaining semantic reasoning capability. Extensive experiments show that UniDriveVLA achieves state-of-the-art performance in open-loop evaluation on nuScenes and closed-loop evaluation on Bench2Drive. Moreover, it demonstrates strong performance across a broad range of perception, prediction, and understanding tasks, including 3D detection, online mapping, motion forecasting, and driving-oriented VQA, highlighting its broad applicability as a unified model for autonomous driving. Code and model have been released at https://github.com/xiaomi-research/unidrivevla</p> + https://arxiv.org/abs/2604.02190 + Thu, 02 Apr 2026 00:00:00 +0000 + + + Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory + https://arxiv.org/abs/2604.01007 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01007.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Liu, Zipeng Ling, Shi Qiu, Yanqing Liu, Siwei Han, Peng Xia, Haoqin Tu, Zeyu Zheng, Cihang Xie, Charles Fleming, Mingyu Ding, Huaxiu Yao</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space spanning architecture, retrieval strategies, prompt engineering, and data pipelines; this space is too large and interconnected for manual exploration or traditional AutoML to explore effectively. We deploy an autonomous research pipeline to discover Omni-SimpleMem, a unified multimodal memory framework for lifelong AI agents. Starting from a naïve baseline (F1=0.117 on LoCoMo), the pipeline autonomously executes {sim}50 experiments across two benchmarks, diagnosing failure modes, proposing architectural modifications, and repairing data pipeline bugs, all without human intervention in the inner loop. The resulting system achieves state-of-the-art on both benchmarks, improving F1 by +411% on LoCoMo (0.117to0.598) and +214% on Mem-Gallery (0.254to0.797) relative to the initial configurations. Critically, the most impactful discoveries are not hyperparameter adjustments: bug fixes (+175%), architectural changes (+44%), and prompt engineering (+188% on specific categories) each individually exceed the cumulative contribution of all hyperparameter tuning, demonstrating capabilities fundamentally beyond the reach of traditional AutoML. We provide a taxonomy of six discovery types and identify four properties that make multimodal memory particularly suited for autoresearch, offering guidance for applying autonomous research pipelines to other AI system domains. Code is available at this https://github.com/aiming-lab/SimpleMem.</p> + https://arxiv.org/abs/2604.01007 + Thu, 02 Apr 2026 00:00:00 +0000 + + + Therefore I am. I Think + https://arxiv.org/abs/2604.01202 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01202.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Esakkivel Esakkiraja, Sai Rajeswar, Denis Akhiyarov, Rajagopal Venkatesaramani</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We consider the question: when a large language reasoning model makes a choice, did it think first and then decide to, or decide first and then think? In this paper, we present evidence that detectable, early-encoded decisions shape chain-of-thought in reasoning models. Specifically, we show that a simple linear probe successfully decodes tool-calling decisions from pre-generation activations with very high confidence, and in some cases, even before a single reasoning token is produced. Activation steering supports this causally: perturbing the decision direction leads to inflated deliberation, and flips behavior in many examples (between 7 - 79% depending on model and benchmark). We also show through behavioral analysis that, when steering changes the decision, the chain-of-thought process often rationalizes the flip rather than resisting it. Together, these results suggest that reasoning models can encode action choices before they begin to deliberate in text.</p> + https://arxiv.org/abs/2604.01202 + Thu, 02 Apr 2026 00:00:00 +0000 + + + NearID: Identity Representation Learning via Near-identity Distractors + https://arxiv.org/abs/2604.01973 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01973.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aleksandar Cvejic, Rameen Abdal, Abdelrahman Eldesokey, Bernard Ghanem, Peter Wonka</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> When evaluating identity-focused tasks such as personalized generation and image editing, existing vision encoders entangle object identity with background context, leading to unreliable representations and metrics. We introduce the first principled framework to address this vulnerability using Near-identity (NearID) distractors, where semantically similar but distinct instances are placed on the exact same background as a reference image, eliminating contextual shortcuts and isolating identity as the sole discriminative signal. Based on this principle, we present the NearID dataset (19K identities, 316K matched-context distractors) together with a strict margin-based evaluation protocol. Under this setting, pre-trained encoders perform poorly, achieving Sample Success Rates (SSR), a strict margin-based identity discrimination metric, as low as 30.7% and often ranking distractors above true cross-view matches. We address this by learning identity-aware representations on a frozen backbone using a two-tier contrastive objective enforcing the hierarchy: same identity > NearID distractor > random negative. This improves SSR to 99.2%, enhances part-level discrimination by 28.0%, and yields stronger alignment with human judgments on DreamBench++, a human-aligned benchmark for personalization. Project page: https://gorluxor.github.io/NearID/</p> + https://arxiv.org/abs/2604.01973 + Thu, 02 Apr 2026 00:00:00 +0000 + + + LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model + https://arxiv.org/abs/2604.02097 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02097.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiachun Jin, Zetong Zhou, Xiao Yang, Hao Zhang, Pengfei Liu, Jun Zhu, Zhijie Deng</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and valuable, e.g., for solving understanding problems that require dense visual thinking, improving visual generation through self-reflection, or modeling visual dynamics of the physical world guided by stepwise action interventions. However, existing UMs necessitate pixel decoding as a bridge due to their disjoint visual representations for understanding and generation, which is both ineffective and inefficient. In this paper, we introduce LatentUM, a novel unified model that represents all modalities within a shared semantic latent space, eliminating the need for pixel-space mediation between visual understanding and generation. This design naturally enables flexible interleaved cross-modal reasoning and generation. Beyond improved computational efficiency, the shared representation substantially alleviates codec bias and strengthens cross-modal alignment, allowing LatentUM to achieve state-of-the-art performance on the Visual Spatial Planning benchmark, push the limits of visual generation through self-reflection, and support world modeling by predicting future visual states within the shared semantic latent space.</p> + https://arxiv.org/abs/2604.02097 + Thu, 02 Apr 2026 00:00:00 +0000 + + + VOID: Video Object and Interaction Deletion + https://arxiv.org/abs/2604.02296 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02296.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Saman Motamed, William Harvey, Benjamin Klein, Luc Van Gool, Zhuoning Yuan, Ta-Ying Cheng</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Existing video object removal methods excel at inpainting content "behind" the object and correcting appearance-level artifacts such as shadows and reflections. However, when the removed object has more significant interactions, such as collisions with other objects, current models fail to correct them and produce implausible results. We present VOID, a video object removal framework designed to perform physically-plausible inpainting in these complex scenarios. To train the model, we generate a new paired dataset of counterfactual object removals using Kubric and HUMOTO, where removing an object requires altering downstream physical interactions. During inference, a vision-language model identifies regions of the scene affected by the removed object. These regions are then used to guide a video diffusion model that generates physically consistent counterfactual outcomes. Experiments on both synthetic and real data show that our approach better preserves consistent scene dynamics after object removal compared to prior video object removal methods. We hope this framework sheds light on how to make video editing models better simulators of the world through high-level causal reasoning.</p> + https://arxiv.org/abs/2604.02296 + Thu, 02 Apr 2026 00:00:00 +0000 + + + CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery + https://arxiv.org/abs/2604.01658 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li, Cathy Wu, Bryan Kian Hsiang Low, Jinhua Zhao, Paul Pu Liang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems. CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate through shared persistent memory, asynchronous multi-agent execution, and heartbeat-based interventions. It also provides practical safeguards, including isolated workspaces, evaluator separation, resource management, and agent session and health management. Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks. On Anthropic's kernel engineering task, four co-evolving agents improve the best known score from 1363 to 1103 cycles. Mechanistic analyses further show how these gains arise from knowledge reuse and multi-agent exploration and communication. Together, these results suggest that greater agent autonomy and multi-agent evolution can substantially improve open-ended discovery. Code is available at https://github.com/Human-Agent-Society/CORAL.</p> + https://arxiv.org/abs/2604.01658 + Thu, 02 Apr 2026 00:00:00 +0000 + + + Steerable Visual Representations + https://arxiv.org/abs/2604.02327 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jona Ruthardt, Manu Gaur, Deva Ramanan, Makarand Tapaswi, Yuki M. Asano</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to focus on the most salient visual cues in the image, with no way to direct them toward less prominent concepts of interest. In contrast, Multimodal LLMs can be guided with textual prompts, but the resulting representations tend to be language-centric and lose their effectiveness for generic visual tasks. To address this, we introduce Steerable Visual Representations, a new class of visual representations, whose global and local features can be steered with natural language. While most vision-language models (e.g., CLIP) fuse text with visual features after encoding (late fusion), we inject text directly into the layers of the visual encoder (early fusion) via lightweight cross-attention. We introduce benchmarks for measuring representational steerability, and demonstrate that our steerable visual features can focus on any desired objects in an image while preserving the underlying representation quality. Our method also matches or outperforms dedicated approaches on anomaly detection and personalized object discrimination, exhibiting zero-shot generalization to out-of-distribution tasks.</p> + https://arxiv.org/abs/2604.02327 + Thu, 02 Apr 2026 00:00:00 +0000 + + + SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization + https://arxiv.org/abs/2604.02268 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is fundamentally limited: retrieval noise introduces irrelevant guidance, injected skill content imposes substantial token overhead, and the model never truly acquires the knowledge it merely follows. We ask whether skills can instead be internalized into model parameters, enabling zero-shot autonomous behavior without any runtime skill retrieval. We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization. SKILL0 introduces a training-time curriculum that begins with full skill context and progressively withdraws it. Skills are grouped offline by category and rendered with interaction history into a compact visual context, teaching he model tool invocation and multi-turn task completion. A Dynamic Curriculum then evaluates each skill file's on-policy helpfulness, retaining only those from which the current policy still benefits within a linearly decaying budget, until the agent operates in a fully zero-shot setting. Extensive agentic experiments demonstrate that SKILL0 achieves substantial improvements over the standard RL baseline (+9.7\% for ALFWorld and +6.6\% for Search-QA), while maintaining a highly efficient context of fewer than 0.5k tokens per step. Our code is available at https://github.com/ZJU-REAL/SkillZero.</p> + https://arxiv.org/abs/2604.02268 + Thu, 02 Apr 2026 00:00:00 +0000 + + + Generative World Renderer + https://arxiv.org/abs/2604.02329 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02329.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zheng-Hui Huang, Zhixiang Wang, Jiaming Tan, Ruihan Yu, Yidan Zhang, Bo Zheng, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang</p><p><b>Upvotes:</b> 87</p><p><b>Summary:</b> Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. To bridge this persistent domain gap, we introduce a large-scale, dynamic dataset curated from visually complex AAA games. Using a novel dual-screen stitched capture method, we extracted 4M continuous frames (720p/30 FPS) of synchronized RGB and five G-buffer channels across diverse scenes, visual effects, and environments, including adverse weather and motion-blur variants. This dataset uniquely advances bidirectional rendering: enabling robust in-the-wild geometry and material decomposition, and facilitating high-fidelity G-buffer-guided video generation. Furthermore, to evaluate the real-world performance of inverse rendering without ground truth, we propose a novel VLM-based assessment protocol measuring semantic, spatial, and temporal consistency. Experiments demonstrate that inverse renderers fine-tuned on our data achieve superior cross-dataset generalization and controllable generation, while our VLM evaluation strongly correlates with human judgment. Combined with our toolkit, our forward renderer enables users to edit styles of AAA games from G-buffers using text prompts.</p> + https://arxiv.org/abs/2604.02329 + Thu, 02 Apr 2026 00:00:00 +0000 + + + The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook + https://arxiv.org/abs/2604.02029 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02029.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinlei Yu, Zhangquan Chen, Yongbo He, Tianyu Fu, Cheng Yang, Chengming Xu, Yue Ma, Xiaobin Hu, Zhe Cao, Jie Xu, Guibin Zhang, Jiale Tao, Jiayi Zhang, Siyuan Ma, Kaituo Feng, Haojie Huang, Youxing Li, Ronghao Chen, Huacan Wang, Chenglin Wu, Zikun Su, Xiaogang Xu, Kelu Yao, Kun Wang, Chen Gao, Yue Liao, Ruqi Huang, Tao Jin, Cheng Tan, Jiangning Zhang, Wenqi Ren, Yanwei Fu, Yong Liu, Yu Wang, Xiangyu Yue, Yu-Gang Jiang, Shuicheng Yan</p><p><b>Upvotes:</b> 123</p><p><b>Summary:</b> Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal processes are more naturally carried out in continuous latent space than in human-readable verbal traces. This shift is driven by the structural limitations of explicit-space computation, including linguistic redundancy, discretization bottlenecks, sequential inefficiency, and semantic loss. This survey aims to provide a unified and up-to-date landscape of latent space in language-based models. We organize the survey into five sequential perspectives: Foundation, Evolution, Mechanism, Ability, and Outlook. We begin by delineating the scope of latent space, distinguishing it from explicit or verbal space and from the latent spaces commonly studied in generative visual models. We then trace the field's evolution from early exploratory efforts to the current large-scale expansion. To organize the technical landscape, we examine existing work through the complementary lenses of mechanism and ability. From the perspective of Mechanism, we identify four major lines of development: Architecture, Representation, Computation, and Optimization. From the perspective of Ability, we show how latent space supports a broad capability spectrum spanning Reasoning, Planning, Modeling, Perception, Memory, Collaboration, and Embodiment. Beyond consolidation, we discuss the key open challenges, and outline promising directions for future research. We hope this survey serves not only as a reference for existing work, but also as a foundation for understanding latent space as a general computational and systems paradigm for next-generation intelligence.</p> + https://arxiv.org/abs/2604.02029 + Thu, 02 Apr 2026 00:00:00 +0000 +