diff --git a/feed.xml b/feed.xml index f0610b2..f57421f 100644 --- a/feed.xml +++ b/feed.xml @@ -7,244 +7,160 @@ http://www.rssboard.org/rss-specification python-feedgen en - Thu, 26 Mar 2026 00:07:32 +0000 + Fri, 27 Mar 2026 00:06:26 +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> 14</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 + 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> 7</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 - SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment - https://arxiv.org/abs/2603.13669 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13669.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mahdi Naseri, Zhou Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> No-Reference Image Quality Assessment (NR-IQA) aims to estimate perceptual quality without access to a reference image of pristine quality. Learning an NR-IQA model faces a fundamental bottleneck: its need for a large number of costly human perceptual labels. We propose SHAMISA, a non-contrastive self-supervised framework that learns from unlabeled distorted images by leveraging explicitly structured relational supervision. Unlike prior methods that impose rigid, binary similarity constraints, SHAMISA introduces implicit structural associations, defined as soft, controllable relations that are both distortion-aware and content-sensitive, inferred from synthetic metadata and intrinsic feature structure. A key innovation is our compositional distortion engine, which generates an uncountable family of degradations from continuous parameter spaces, grouped so that only one distortion factor varies at a time. This enables fine-grained control over representational similarity during training: images with shared distortion patterns are pulled together in the embedding space, while severity variations produce structured, predictable shifts. We integrate these insights via dual-source relation graphs that encode both known degradation profiles and emergent structural affinities to guide the learning process throughout training. A convolutional encoder is trained under this supervision and then frozen for inference, with quality prediction performed by a linear regressor on its features. Extensive experiments on synthetic, authentic, and cross-dataset NR-IQA benchmarks demonstrate that SHAMISA achieves strong overall performance with improved cross-dataset generalization and robustness, all without human quality annotations or contrastive losses.</p> - https://arxiv.org/abs/2603.13669 - Sat, 14 Mar 2026 00:37:26 +0000 + PLDR-LLMs Reason At Self-Organized Criticality + https://arxiv.org/abs/2603.23539 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23539.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Burc Gokden</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We show that PLDR-LLMs pretrained at self-organized criticality exhibit reasoning at inference time. The characteristics of PLDR-LLM deductive outputs at criticality is similar to second-order phase transitions. At criticality, the correlation length diverges, and the deductive outputs attain a metastable steady state. The steady state behaviour suggests that deductive outputs learn representations equivalent to scaling functions, universality classes and renormalization groups from the training dataset, leading to generalization and reasoning capabilities in the process. We can then define an order parameter from the global statistics of the model's deductive output parameters at inference. The reasoning capabilities of a PLDR-LLM is better when its order parameter is close to zero at criticality. This observation is supported by the benchmark scores of the models trained at near-criticality and sub-criticality. Our results provide a self-contained explanation on how reasoning manifests in large language models, and the ability to reason can be quantified solely from global model parameter values of the deductive outputs at steady state, without any need for evaluation of curated benchmark datasets through inductive output for reasoning and comprehension.</p> + https://arxiv.org/abs/2603.23539 + Thu, 12 Mar 2026 19:09:06 +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> 4</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 + 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> 10</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 - 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> 8</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 + 6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models + https://arxiv.org/abs/2603.18742 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18742.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rundong Su, Jintao Zhang, Zhihang Yuan, Haojie Duanmu, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical way to reduce memory usage and boost computation speed. Existing quantization methods typically apply a static bit-width allocation, overlooking the quantization difficulty of activations across diffusion timesteps, leading to a suboptimal trade-off between efficiency and quality. In this paper, we propose a inference time NVFP4/INT8 Mixed-Precision Quantization framework. We find a strong linear correlation between a block's input-output difference and the quantization sensitivity of its internal linear layers. Based on this insight, we design a lightweight predictor that dynamically allocates NVFP4 to temporally stable layers to maximize memory compression, while selectively preserving INT8 for volatile layers to ensure robustness. This adaptive precision strategy enables aggressive quantization without compromising generation quality. Beside this, we observe that the residual between the input and output of a Transformer block exhibits high temporal consistency across timesteps. Leveraging this temporal redundancy, we introduce Temporal Delta Cache (TDC) to skip computations for these invariant blocks, further reducing the computational cost. Extensive experiments demonstrate that our method achieves 1.92times end-to-end acceleration and 3.32times memory reduction, setting a new baseline for efficient inference in Video DiTs.</p> + https://arxiv.org/abs/2603.18742 + Thu, 19 Mar 2026 10:45:11 +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> 36</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 + 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> 7</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 - Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction - https://arxiv.org/abs/2603.22330 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Chen, Zhenfeng Deng, Pan Deng, Yue Liao, Xiu Su, Peng Ye, Xihui Liu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Accurate prediction of RNA secondary structure underpins transcriptome annotation, mechanistic analysis of non-coding RNAs, and RNA therapeutic design. Recent gains from deep learning and RNA foundation models are difficult to interpret because current benchmarks may overestimate generalization across RNA families. We present the Comprehensive Hierarchical Annotation of Non-coding RNA Groups (CHANRG), a benchmark of 170{,}083 structurally non-redundant RNAs curated from more than 10 million sequences in Rfam~15.0 using structure-aware deduplication, genome-aware split design and multiscale structural evaluation. Across 29 predictors, foundation-model methods achieved the highest held-out accuracy but lost most of that advantage out of distribution, whereas structured decoders and direct neural predictors remained markedly more robust. This gap persisted after controlling for sequence length and reflected both loss of structural coverage and incorrect higher-order wiring. Together, CHANRG and a padding-free, symmetry-aware evaluation stack provide a stricter and batch-invariant framework for developing RNA structure predictors with demonstrable out-of-distribution robustness.</p> - https://arxiv.org/abs/2603.22330 - Fri, 20 Mar 2026 20:18:08 +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> 30</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 - Can AI Agents Answer Your Data Questions? A Benchmark for Data Agents - https://arxiv.org/abs/2603.20576 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.20576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruiying Ma, Shreya Shankar, Ruiqi Chen, Yiming Lin, Sepanta Zeighami, Rajoshi Ghosh, Abhinav Gupta, Anushrut Gupta, Tanmai Gopal, Aditya G. Parameswaran</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Users across enterprises increasingly rely on AI agents to query their data through natural language. However, building reliable data agents remains difficult because real-world data is often fragmented across multiple heterogeneous database systems, with inconsistent references and information buried in unstructured text. Existing benchmarks only tackle individual pieces of this problem -- e.g., translating natural-language questions into SQL queries, answering questions over small tables provided in context -- but do not evaluate the full pipeline of integrating, transforming, and analyzing data across multiple database systems. To fill this gap, we present the Data Agent Benchmark (DAB), grounded in a formative study of enterprise data agent workloads across six industries. DAB comprises 54 queries across 12 datasets, 9 domains, and 4 database management systems. On DAB, the best frontier model (Gemini-3-Pro) achieves only 38% pass@1 accuracy. We benchmark five frontier LLMs, analyze their failure modes, and distill takeaways for future data agent development. Our benchmark and experiment code are published at github.com/ucbepic/DataAgentBench.</p> - https://arxiv.org/abs/2603.20576 - Sat, 21 Mar 2026 00:14:53 +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> 14</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 - 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> 19</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 + 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> 9</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 - Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates - https://arxiv.org/abs/2603.22350 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22350.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Florin Adrian Chitan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Deterministic pre-execution safety gates evaluate whether individual agent actions are compatible with their assigned roles. While effective at per-action authorization, these systems are structurally blind to distributed attacks that decompose harmful intent across multiple individually-compliant steps. This paper introduces Session Risk Memory (SRM), a lightweight deterministic module that extends stateless execution gates with trajectory-level authorization. SRM maintains a compact semantic centroid representing the evolving behavioral profile of an agent session and accumulates a risk signal through exponential moving average over baseline-subtracted gate outputs. It operates on the same semantic vector representation as the underlying gate, requiring no additional model components, training, or probabilistic inference. We evaluate SRM on a multi-turn benchmark of 80 sessions containing slow-burn exfiltration, gradual privilege escalation, and compliance drift scenarios. Results show that ILION+SRM achieves F1 = 1.0000 with 0% false positive rate, compared to stateless ILION at F1 = 0.9756 with 5% FPR, while maintaining 100% detection rate for both systems. Critically, SRM eliminates all false positives with a per-turn overhead under 250 microseconds. The framework introduces a conceptual distinction between spatial authorization consistency (evaluated per action) and temporal authorization consistency (evaluated over trajectory), providing a principled basis for session-level safety in agentic systems.</p> - https://arxiv.org/abs/2603.22350 - Sun, 22 Mar 2026 08:30:28 +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> 3</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 - STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems - https://arxiv.org/abs/2603.22359 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22359.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alfred Shen, Aaron Shen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce STEM Agent (Self-adapting, Tool-enabled, Extensible, Multi-agent), a modular architecture inspired by biological pluripotency in which an undifferentiated agent core differentiates into specialized protocol handlers, tool bindings, and memory subsystems that compose into a fully functioning AI system. The framework unifies five interoperability protocols (A2A, AG-UI, A2UI, UCP, and AP2) behind a single gateway, introduces a Caller Profiler that continuously learns user preferences across more than twenty behavioral dimensions, externalizes all domain capabilities through the Model Context Protocol (MCP), and implements a biologically inspired skills acquisition system in which recurring interaction patterns crystallize into reusable agent skills through a maturation lifecycle analogous to cell differentiation. Complementing these capabilities, the memory system incorporates consolidation mechanisms, including episodic pruning, semantic deduplication, and pattern extraction, designed for sub-linear growth under sustained interaction. A comprehensive 413-test suite validates protocol handler behavior and component integration across all five architectural layers, completing in under three seconds.</p> - https://arxiv.org/abs/2603.22359 - Sun, 22 Mar 2026 20:50:53 +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> 34</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 - Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models - https://arxiv.org/abs/2603.21854 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.21854.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aryan Kasat, Smriti Singh, Aman Chadha, Vinija Jain</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Do large language models reason morally, or do they merely sound like they do? We investigate whether LLM responses to moral dilemmas exhibit genuine developmental progression through Kohlberg's stages of moral development, or whether alignment training instead produces reasoning-like outputs that superficially resemble mature moral judgment without the underlying developmental trajectory. Using an LLM-as-judge scoring pipeline validated across three judge models, we classify more than 600 responses from 13 LLMs spanning a range of architectures, parameter scales, and training regimes across six classical moral dilemmas, and conduct ten complementary analyses to characterize the nature and internal coherence of the resulting patterns. Our results reveal a striking inversion: responses overwhelmingly correspond to post-conventional reasoning (Stages 5-6) regardless of model size, architecture, or prompting strategy, the effective inverse of human developmental norms, where Stage 4 dominates. Most strikingly, a subset of models exhibit moral decoupling: systematic inconsistency between stated moral justification and action choice, a form of logical incoherence that persists across scale and prompting strategy and represents a direct reasoning consistency failure independent of rhetorical sophistication. Model scale carries a statistically significant but practically small effect; training type has no significant independent main effect; and models exhibit near-robotic cross-dilemma consistency producing logically indistinguishable responses across semantically distinct moral problems. We posit that these patterns constitute evidence for moral ventriloquism: the acquisition, through alignment training, of the rhetorical conventions of mature moral reasoning without the underlying developmental trajectory those conventions are meant to represent.</p> - https://arxiv.org/abs/2603.21854 - Mon, 23 Mar 2026 11:43:49 +0000 + Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning + https://arxiv.org/abs/2603.23404 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23404.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Hua, Yishu Yin, Yuhang Wu, Tai Wang, Yifei Huang, Miao Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the 3D environment depicted in video inputs. To bridge this gap, drawing inspiration from cognitive theories of allocentric spatial reasoning, we investigate how to enable MLLMs to model and reason over text-based spatial representations of video. Specifically, we introduce Textual Representation of Allocentric Context from Egocentric Video (TRACE), a prompting method that induces MLLMs to generate text-based representations of 3D environments as intermediate reasoning traces for more accurate spatial question answering. TRACE encodes meta-context, camera trajectories, and detailed object entities to support structured spatial reasoning over egocentric videos. Extensive experiments on VSI-Bench and OST-Bench demonstrate that TRACE yields notable and consistent improvements over prior prompting strategies across a diverse range of MLLM backbones, spanning different parameter scales and training schemas. We further present ablation studies to validate our design choices, along with detailed analyses that probe the bottlenecks of 3D spatial reasoning in MLLMs.</p> + https://arxiv.org/abs/2603.23404 + Tue, 24 Mar 2026 16:38:09 +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> 5</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 + UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Functionality Segmentation + https://arxiv.org/abs/2603.23478 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23478.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaying Lin, Dan Xu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Functionality segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interactive elements. Existing methods rely on fragmented pipelines that suffer from visual blindness during initial task parsing. We observe that these methods are limited by single-scale, passive and heuristic frame selection. We present UniFunc3D, a unified and training-free framework that treats the multimodal large language model as an active observer. By consolidating semantic, temporal, and spatial reasoning into a single forward pass, UniFunc3D performs joint reasoning to ground task decomposition in direct visual evidence. Our approach introduces active spatial-temporal grounding with a coarse-to-fine strategy. This allows the model to select correct video frames adaptively and focus on high-detail interactive parts while preserving the global context necessary for disambiguation. On SceneFun3D, UniFunc3D achieves state-of-the-art performance, surpassing both training-free and training-based methods by a large margin with a relative 59.9\% mIoU improvement, without any task-specific training. Code will be released on our project page: https://jiaying.link/unifunc3d.</p> + https://arxiv.org/abs/2603.23478 + Tue, 24 Mar 2026 17:42:31 +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> 9</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 + 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> 6</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 - Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models - https://arxiv.org/abs/2603.22042 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hayeon Kim, Ji Ha Jang, Junghun James Kim, Se Young Chun</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> While Vision-Language Models (VLMs) have achieved remarkable performance, their Euclidean embeddings remain limited in capturing hierarchical relationships such as part-to-whole or parent-child structures, and often face challenges in multi-object compositional scenarios. Hyperbolic VLMs mitigate this issue by better preserving hierarchical structures and modeling part-whole relations (i.e., whole scene and its part images) through entailment. However, existing approaches do not model that each part has a different level of semantic representativeness to the whole. We propose UNcertainty-guided Compositional Hyperbolic Alignment (UNCHA) for enhancing hyperbolic VLMs. UNCHA models part-to-whole semantic representativeness with hyperbolic uncertainty, by assigning lower uncertainty to more representative parts and higher uncertainty to less representative ones for the whole scene. This representativeness is then incorporated into the contrastive objective with uncertainty-guided weights. Finally, the uncertainty is further calibrated with an entailment loss regularized by entropy-based term. With the proposed losses, UNCHA learns hyperbolic embeddings with more accurate part-whole ordering, capturing the underlying compositional structure in an image and improving its understanding of complex multi-object scenes. UNCHA achieves state-of-the-art performance on zero-shot classification, retrieval, and multi-label classification benchmarks. Our code and models are available at: https://github.com/jeeit17/UNCHA.git.</p> - https://arxiv.org/abs/2603.22042 - Mon, 23 Mar 2026 14:41:20 +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> 13</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 - 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> 41</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 + SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision + https://arxiv.org/abs/2603.24036 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24036.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Avigail Cohen Rimon, Amir Mann, Mirela Ben Chen, Or Litany</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> 3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveraging the differentiability of the 3DGS renderer "in the wild" remains notoriously fragile. A fundamental bottleneck lies in the compact, local support of the Gaussian primitives. Standard photometric objectives implicitly rely on spatial overlap; if severe camera misalignment places the rendered object outside the target's local footprint, gradients strictly vanish, leaving the optimizer stranded. We introduce SpectralSplats, a robust tracking framework that resolves this "vanishing gradient" problem by shifting the optimization objective from the spatial to the frequency domain. By supervising the rendered image via a set of global complex sinusoidal features (Spectral Moments), we construct a global basin of attraction, ensuring that a valid, directional gradient toward the target exists across the entire image domain, even when pixel overlap is completely nonexistent. To harness this global basin without introducing periodic local minima associated with high frequencies, we derive a principled Frequency Annealing schedule from first principles, gracefully transitioning the optimizer from global convexity to precise spatial alignment. We demonstrate that SpectralSplats acts as a seamless, drop-in replacement for spatial losses across diverse deformation parameterizations (from MLPs to sparse control points), successfully recovering complex deformations even from severely misaligned initializations where standard appearance-based tracking catastrophically fails.</p> + https://arxiv.org/abs/2603.24036 + Wed, 25 Mar 2026 07:48:22 +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> 9</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 + 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 - 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> 4</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 + 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> 16</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 - 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> 110</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 + 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> 69</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 - 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> 3</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 + OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning + https://arxiv.org/abs/2603.24458 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24458.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaihang Pan, Qi Tian, Jianwei Zhang, Weijie Kong, Jiangfeng Xiong, Yanxin Long, Shixue Zhang, Haiyi Qiu, Tan Wang, Zheqi Lv, Yue Wu, Liefeng Bo, Siliang Tang, Zhao Zhong</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing efforts toward unified video generation still struggle to seamlessly integrate diverse tasks within a single framework. To bridge this gap, we propose OmniWeaving, an omni-level video generation model featuring powerful multimodal composition and reasoning-informed capabilities. By leveraging a massive-scale pretraining dataset that encompasses diverse compositional and reasoning-augmented scenarios, OmniWeaving learns to temporally bind interleaved text, multi-image, and video inputs while acting as an intelligent agent to infer complex user intentions for sophisticated video creation. Furthermore, we introduce IntelligentVBench, the first comprehensive benchmark designed to rigorously assess next-level intelligent unified video generation. Extensive experiments demonstrate that OmniWeaving achieves SoTA performance among open-source unified models. The codes and model will be made publicly available soon. Project Page: https://omniweaving.github.io.</p> + https://arxiv.org/abs/2603.24458 + Wed, 25 Mar 2026 16:08:18 +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> 7</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 + 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> 27</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 - 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> 4</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 + Toward Physically Consistent Driving Video World Models under Challenging Trajectories + https://arxiv.org/abs/2603.24506 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.24506.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Zhou, Zhenxin Zhu, Lingyi Du, Linye Lyu, Lijun Zhou, Zhanqian Wu, Hongcheng Luo, Zhuotao Tian, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun, Yu Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Video generation models have shown strong potential as world models for autonomous driving simulation. However, existing approaches are primarily trained on real-world driving datasets, which mostly contain natural and safe driving scenarios. As a result, current models often fail when conditioned on challenging or counterfactual trajectories-such as imperfect trajectories generated by simulators or planning systems-producing videos with severe physical inconsistencies and artifacts. To address this limitation, we propose PhyGenesis, a world model designed to generate driving videos with high visual fidelity and strong physical consistency. Our framework consists of two key components: (1) a physical condition generator that transforms potentially invalid trajectory inputs into physically plausible conditions, and (2) a physics-enhanced video generator that produces high-fidelity multi-view driving videos under these conditions. To effectively train these components, we construct a large-scale, physics-rich heterogeneous dataset. Specifically, in addition to real-world driving videos, we generate diverse challenging driving scenarios using the CARLA simulator, from which we derive supervision signals that guide the model to learn physically grounded dynamics under extreme conditions. This challenging-trajectory learning strategy enables trajectory correction and promotes physically consistent video generation. Extensive experiments demonstrate that PhyGenesis consistently outperforms state-of-the-art methods, especially on challenging trajectories. Our project page is available at: https://wm-research.github.io/PhyGenesis/.</p> + https://arxiv.org/abs/2603.24506 + Wed, 25 Mar 2026 16:47:39 +0000 - Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning - https://arxiv.org/abs/2603.22758 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.22758.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> WonJun Moon, Hyun Seok Seong, Jae-Pil Heo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Video Object-Centric Learning seeks to decompose raw videos into a small set of object slots, but existing slot-attention models often suffer from severe over-fragmentation. This is because the model is implicitly encouraged to occupy all slots to minimize the reconstruction objective, thereby representing a single object with multiple redundant slots. We tackle this limitation with a reconstruction-guided slot curriculum (SlotCurri). Training starts with only a few coarse slots and progressively allocates new slots where reconstruction error remains high, thus expanding capacity only where it is needed and preventing fragmentation from the outset. Yet, during slot expansion, meaningful sub-parts can emerge only if coarse-level semantics are already well separated; however, with a small initial slot budget and an MSE objective, semantic boundaries remain blurry. Therefore, we augment MSE with a structure-aware loss that preserves local contrast and edge information to encourage each slot to sharpen its semantic boundaries. Lastly, we propose a cyclic inference that rolls slots forward and then backward through the frame sequence, producing temporally consistent object representations even in the earliest frames. All combined, SlotCurri addresses object over-fragmentation by allocating representational capacity where reconstruction fails, further enhanced by structural cues and cyclic inference. Notable FG-ARI gains of +6.8 on YouTube-VIS and +8.3 on MOVi-C validate the effectiveness of SlotCurri. Our code is available at github.com/wjun0830/SlotCurri.</p> - https://arxiv.org/abs/2603.22758 - Tue, 24 Mar 2026 03:34:51 +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> 17</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 - - - ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment - https://arxiv.org/abs/2603.23376 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuzhi Chen, Ronghan Chen, Dongjie Huo, Yandan Yang, Dekang Qi, Haoyun Liu, Tong Lin, Shuang Zeng, Junjin Xiao, Xinyuan Chang, Feng Xiong, Xing Wei, Zhiheng Ma, Mu Xu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Video-based world models offer a powerful paradigm for embodied simulation and planning, yet state-of-the-art models often generate physically implausible manipulations - such as object penetration and anti-gravity motion - due to training on generic visual data and likelihood-based objectives that ignore physical laws. We present ABot-PhysWorld, a 14B Diffusion Transformer model that generates visually realistic, physically plausible, and action-controllable videos. Built on a curated dataset of three million manipulation clips with physics-aware annotation, it uses a novel DPO-based post-training framework with decoupled discriminators to suppress unphysical behaviors while preserving visual quality. A parallel context block enables precise spatial action injection for cross-embodiment control. To better evaluate generalization, we introduce EZSbench, the first training-independent embodied zero-shot benchmark combining real and synthetic unseen robot-task-scene combinations. It employs a decoupled protocol to separately assess physical realism and action alignment. ABot-PhysWorld achieves new state-of-the-art performance on PBench and EZSbench, surpassing Veo 3.1 and Sora v2 Pro in physical plausibility and trajectory consistency. We will release EZSbench to promote standardized evaluation in embodied video generation.</p> - https://arxiv.org/abs/2603.23376 - Tue, 24 Mar 2026 16:07:09 +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> 33</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> 22</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 - - - Regulating AI Agents - https://arxiv.org/abs/2603.23471 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23471.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kathrin Gardhouse, Amin Oueslati, Noam Kolt</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> AI agents -- systems that can independently take actions to pursue complex goals with only limited human oversight -- have entered the mainstream. These systems are now being widely used to produce software, conduct business activities, and automate everyday personal tasks. While AI agents implicate many areas of law, ranging from agency law and contracts to tort liability and labor law, they present particularly pressing questions for the most globally consequential AI regulation: the European Union's AI Act. Promulgated prior to the development and widespread use of AI agents, the EU AI Act faces significant obstacles in confronting the governance challenges arising from this transformative technology, such as performance failures in autonomous task execution, the risk of misuse of agents by malicious actors, and unequal access to the economic opportunities afforded by AI agents. We systematically analyze the EU AI Act's response to these challenges, focusing on both the substantive provisions of the regulation and, crucially, the institutional frameworks that aim to support its implementation. Our analysis of the Act's allocation of monitoring and enforcement responsibilities, reliance on industry self-regulation, and level of government resourcing illustrates how a regulatory framework designed for conventional AI systems can be ill-suited to AI agents. Taken together, our findings suggest that policymakers in the EU and beyond will need to change course, and soon, if they are to effectively govern the next generation of AI technology.</p> - https://arxiv.org/abs/2603.23471 - Tue, 24 Mar 2026 17:38:27 +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> 4</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> 42</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 - - - One View Is Enough! Monocular Training for In-the-Wild Novel View Generation - https://arxiv.org/abs/2603.23488 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23488.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez, David Picard</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Monocular novel-view synthesis has long required multi-view image pairs for supervision, limiting training data scale and diversity. We argue it is not necessary: one view is enough. We present OVIE, trained entirely on unpaired internet images. We leverage a monocular depth estimator as a geometric scaffold at training time: we lift a source image into 3D, apply a sampled camera transformation, and project to obtain a pseudo-target view. To handle disocclusions, we introduce a masked training formulation that restricts geometric, perceptual, and textural losses to valid regions, enabling training on 30 million uncurated images. At inference, OVIE is geometry-free, requiring no depth estimator or 3D representation. Trained exclusively on in-the-wild images, OVIE outperforms prior methods in a zero-shot setting, while being 600x faster than the second-best baseline. Code and models are publicly available at https://github.com/AdrienRR/ovie.</p> - https://arxiv.org/abs/2603.23488 - Tue, 24 Mar 2026 17:54:25 +0000 - - - VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions - https://arxiv.org/abs/2603.23495 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.23495.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adrian Bulat, Alberto Baldrati, Ioannis Maniadis Metaxas, Yassine Ouali, Georgios Tzimiropoulos</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance, especially on challenging tasks that require fine-grained understanding and reasoning. In this work, we challenge this paradigm by introducing VISion On Request (VISOR), a method that reduces inference cost without discarding visual information. Instead of compressing the image, VISOR improves efficiency by sparsifying the interaction between image and text tokens. Specifically, the language model attends to the full set of high-resolution visual tokens through a small, strategically placed set of attention layers: general visual context is provided by efficient cross-attention between text-image, while a few well-placed and dynamically selected self-attention layers refine the visual representations themselves, enabling complex, high-resolution reasoning when needed. Based on this principle, we first train a single universal network on a range of computational budgets by varying the number of self-attention layers, and then introduce a lightweight policy mechanism that dynamically allocates visual computation based on per-sample complexity. Extensive experiments show that VISOR drastically reduces computational cost while matching or exceeding state-of-the-art results across a diverse suite of benchmarks, and excels in challenging tasks that require detailed visual understanding.</p> - https://arxiv.org/abs/2603.23495 - Tue, 24 Mar 2026 17:58:17 +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> 66</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> 35</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> 29</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 + 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> 29</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