bot: update RSS feed
This commit is contained in:
github-actions[bot]
417
feed.xml
417
feed.xml
@@ -7,223 +7,328 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Tue, 17 Mar 2026 00:04:56 +0000</lastBuildDate>
|
<lastBuildDate>Wed, 18 Mar 2026 00:06:06 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>SimRecon: SimReady Compositional Scene Reconstruction from Real Videos</title>
|
<title>FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach</title>
|
||||||
<link>https://arxiv.org/abs/2603.02133</link>
|
<link>https://arxiv.org/abs/2603.13364</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.02133.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chong Xia, Kai Zhu, Zizhuo Wang, Fangfu Liu, Zhizheng Zhang, Yueqi Duan</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Compositional scene reconstruction seeks to create object-centric representations rather than holistic scenes from real-world videos, which is natively applicable for simulation and interaction. Conventional compositional reconstruction approaches primarily emphasize on visual appearance and show limited generalization ability to real-world scenarios. In this paper, we propose SimRecon, a framework that realizes a "Perception-Generation-Simulation" pipeline towards cluttered scene reconstruction, which first conducts scene-level semantic reconstruction from video input, then performs single-object generation, and finally assembles these assets in the simulator. However, naively combining these three stages leads to visual infidelity of generated assets and physical implausibility of the final scene, a problem particularly severe for complex scenes. Thus, we further propose two bridging modules between the three stages to address this problem. To be specific, for the transition from Perception to Generation, critical for visual fidelity, we introduce Active Viewpoint Optimization, which actively searches in 3D space to acquire optimal projected images as conditions for single-object completion. Moreover, for the transition from Generation to Simulation, essential for physical plausibility, we propose a Scene Graph Synthesizer, which guides the construction from scratch in 3D simulators, mirroring the native, constructive principle of the real world. Extensive experiments on the ScanNet dataset validate our method's superior performance over previous state-of-the-art approaches.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13364.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ning Liao, Xiaoxing Wang, Xiaohan Qin, Junchi Yan</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> As revealed by the scaling law of fine-grained MoE, model performance ceases to be improved once the granularity of the intermediate dimension exceeds the optimal threshold, limiting further gains from single-dimension fine-grained design. To address this bottleneck, we propose FineRMoE (FineR-Grained MoE), an architecture that extends fine-grained expert design to both intermediate and output dimensions, aiming to enhance expert specialization beyond the single-dimension limit. We further introduce a bi-level sparse forward computation paradigm and a specialized routing mechanism to govern the activation. In addition, to obviate the prohibitive cost of training FineRMoE from scratch, we devise a generalized upcycling method to build FineRMoE in a cost-effective manner. Extensive experiments demonstrate the superior performance achieved by FineRMoE across ten standard benchmarks. Compared with the strongest baseline, FineRMoE achieves 6 times higher parameter efficiency, 281 times lower prefill latency, and 136 timese higher decoding throughput during inference.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.02133</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13364</guid>
|
||||||
<pubDate>Mon, 02 Mar 2026 17:51:45 +0000</pubDate>
|
<pubDate>Mon, 09 Mar 2026 12:00:36 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration</title>
|
<title>WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics</title>
|
||||||
<link>https://arxiv.org/abs/2603.07815</link>
|
<link>https://arxiv.org/abs/2603.13391</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.07815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Desen Sun, Jason Hon, Jintao Zhang, Sihang Liu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Diffusion models have demonstrated a remarkable ability in Text-to-Image (T2I) generation applications. Despite the advanced generation output, they suffer from heavy computation overhead, especially for large models that contain tens of billions of parameters. Prior work has illustrated that replacing part of the denoising steps with a smaller model still maintains the generation quality. However, these methods only focus on saving computation for some timesteps, ignoring the difference in compute demand within one timestep. In this work, we propose HybridStitch, a new T2I generation paradigm that treats generation like editing. Specifically, we introduce a hybrid stage that jointly incorporates both the large model and the small model. HybridStitch separates the entire image into two regions: one that is relatively easy to render, enabling an early transition to the smaller model, and another that is more complex and therefore requires refinement by the large model. HybridStitch employs the small model to construct a coarse sketch while exploiting the large model to edit and refine the complex regions. According to our evaluation, HybridStitch achieves 1.83times speedup on Stable Diffusion 3, which is faster than all existing mixture of model methods.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13391.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhong Dai, Yanlin Lai, Mitt Huang, Hangyu Guo, Dingming Li, Hongbo Peng, Haodong Li, Yingxiu Zhao, Haoran Lyu, Zheng Ge, Xiangyu Zhang, Daxin Jiang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Existing web-generation benchmarks rely on text prompts or static screenshots as input. However, videos naturally convey richer signals such as interaction flow, transition timing, and motion continuity, which are essential for faithful webpage recreation. Despite this potential, video-conditioned webpage generation remains largely unexplored, with no dedicated benchmark for this task. To fill this gap, we introduce WebVR, a benchmark that evaluates whether MLLMs can faithfully recreate webpages from demonstration videos. WebVR contains 175 webpages across diverse categories, all constructed through a controlled synthesis pipeline rather than web crawling, ensuring varied and realistic demonstrations without overlap with existing online pages. We also design a fine-grained, human-aligned visual rubric that evaluates the generated webpages across multiple dimensions. Experiments on 19 models reveal substantial gaps in recreating fine-grained style and motion quality, while the rubric-based automatic evaluation achieves 96% agreement with human preferences. We release the dataset, evaluation toolkit, and baseline results to support future research on video-to-webpage generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.07815</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13391</guid>
|
||||||
<pubDate>Sun, 08 Mar 2026 21:34:50 +0000</pubDate>
|
<pubDate>Wed, 11 Mar 2026 07:48:23 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery</title>
|
<title>Safe and Scalable Web Agent Learning via Recreated Websites</title>
|
||||||
<link>https://arxiv.org/abs/2603.08127</link>
|
<link>https://arxiv.org/abs/2603.10505</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08127.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yougang Lyu, Xi Zhang, Xinhao Yi, Yuyue Zhao, Shuyu Guo, Wenxiang Hu, Jan Piotrowski, Jakub Kaliski, Jacopo Urbani, Zaiqiao Meng, Lun Zhou, Xiaohui Yan</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> The increasing adoption of Large Language Models (LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including idea generation and experimental execution. However, most state-of-the-art AI scientist systems rely on static, hand-designed pipelines and fail to adapt based on accumulated interaction histories. As a result, these systems overlook promising research directions, repeat failed experiments, and pursue infeasible ideas. To address this, we introduce EvoScientist, an evolving multi-agent AI scientist framework that continuously improves research strategies through persistent memory and self-evolution. EvoScientist comprises three specialized agents: a Researcher Agent (RA) for scientific idea generation, an Engineer Agent (EA) for experiment implementation and execution, and an Evolution Manager Agent (EMA) that distills insights from prior interactions into reusable knowledge. EvoScientist contains two persistent memory modules: (i) an ideation memory, which summarizes feasible research directions from top-ranked ideas while recording previously unsuccessful directions; and (ii) an experimentation memory, which captures effective data processing and model training strategies derived from code search trajectories and best-performing implementations. These modules enable the RA and EA to retrieve relevant prior strategies, improving idea quality and code execution success rates over time. Experiments show that EvoScientist outperforms 7 open-source and commercial state-of-the-art systems in scientific idea generation, achieving higher novelty, feasibility, relevance, and clarity via automatic and human evaluation. EvoScientist also substantially improves code execution success rates through multi-agent evolution, demonstrating persistent memory's effectiveness for end-to-end scientific discovery.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10505.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyungjoo Chae, Jungsoo Park, Alan Ritter</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Training autonomous web agents is fundamentally limited by the environments they learn from: real-world websites are unsafe to explore, hard to reset, and rarely provide verifiable feedback. We propose VeriEnv, a framework that treats language models as environment creators, automatically cloning real-world websites into fully executable, verifiable synthetic environments. By exposing controlled internal access via a Python SDK, VeriEnv enables agents to self-generate tasks with deterministic, programmatically verifiable rewards, eliminating reliance on heuristic or LLM-based judges. This design decouples agent learning from unsafe real-world interaction while enabling scalable self-evolution through environment expansion. Through experiments on web agent benchmarks, we show that agents trained with VeriEnv generalize to unseen websites, achieve site-specific mastery through self-evolving training, and benefit from scaling the number of training environments. Code and resources will be released at https://github.com/kyle8581/VeriEnv upon acceptance.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08127</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.10505</guid>
|
||||||
<pubDate>Mon, 09 Mar 2026 09:07:19 +0000</pubDate>
|
<pubDate>Wed, 11 Mar 2026 07:58:53 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Can Vision-Language Models Solve the Shell Game?</title>
|
<title>FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance</title>
|
||||||
<link>https://arxiv.org/abs/2603.08436</link>
|
<link>https://arxiv.org/abs/2603.12146</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08436.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tiedong Liu, Wee Sun Lee</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Visual entity tracking is an innate cognitive ability in humans, yet it remains a critical bottleneck for Vision-Language Models (VLMs). This deficit is often obscured in existing video benchmarks by visual shortcuts. We introduce VET-Bench, a synthetic diagnostic testbed featuring visually identical objects that necessitate tracking exclusively through spatiotemporal continuity. Our experiments reveal that current state-of-the-art VLMs perform at or near chance level on VET-Bench, exposing a fundamental limitation: an over-reliance on static frame-level features and a failure to maintain entity representations over time. We provide a theoretical analysis drawing connections to the state-tracking problem, proving that fixed-depth transformer-based VLMs are fundamentally limited in tracking indistinguishable objects without intermediate supervision due to expressivity constraints. To address this, we propose Spatiotemporal Grounded Chain-of-Thought (SGCoT): generating object trajectories as explicit intermediate states. Leveraging Molmo2's object tracking ability, we elicit SGCoT reasoning by fine-tuning on synthesized text-only data for alignment. Our method achieves state-of-the-art accuracy exceeding 90% on VET-Bench, demonstrating that VLMs can reliably solve the video shell-game task end-to-end without external tools. Our code and data are available at https://vetbench.github.io .</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12146.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quanhao Li, Zhen Xing, Rui Wang, Haidong Cao, Qi Dai, Daoguo Dong, Zuxuan Wu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control along predefined trajectories. However, all these methods rely on a multi-step denoising process, leading to substantial time redundancy and computational overhead. While existing video distillation methods successfully distill multi-step generators into few-step, directly applying these approaches to trajectory-controllable video generation results in noticeable degradation in both video quality and trajectory accuracy. To bridge this gap, we introduce FlashMotion, a novel training framework designed for few-step trajectory-controllable video generation. We first train a trajectory adapter on a multi-step video generator for precise trajectory control. Then, we distill the generator into a few-step version to accelerate video generation. Finally, we finetune the adapter using a hybrid strategy that combines diffusion and adversarial objectives, aligning it with the few-step generator to produce high-quality, trajectory-accurate videos. For evaluation, we introduce FlashBench, a benchmark for long-sequence trajectory-controllable video generation that measures both video quality and trajectory accuracy across varying numbers of foreground objects. Experiments on two adapter architectures show that FlashMotion surpasses existing video distillation methods and previous multi-step models in both visual quality and trajectory consistency.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08436</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12146</guid>
|
||||||
<pubDate>Mon, 09 Mar 2026 14:33:25 +0000</pubDate>
|
<pubDate>Thu, 12 Mar 2026 16:45:53 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction</title>
|
<title>TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2603.09930</link>
|
<link>https://arxiv.org/abs/2603.12529</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09930.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yao Zhang, Zhuchenyang Liu, Yanlan He, Thomas Ploetz, Yu Xiao</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling bidirectional search across the two modalities. Most existing methods use a dual-encoder framework that compresses motion and text into global embeddings, discarding fine-grained local correspondences, and thus reducing accuracy. Additionally, these global-embedding methods offer limited interpretability of the retrieval results. To overcome these limitations, we propose an interpretable, joint-angle-based motion representation that maps joint-level local features into a structured pseudo-image, compatible with pre-trained Vision Transformers. For text-to-motion retrieval, we employ MaxSim, a token-wise late interaction mechanism, and enhance it with Masked Language Modeling regularization to foster robust, interpretable text-motion alignment. Extensive experiments on HumanML3D and KIT-ML show that our method outperforms state-of-the-art text-motion retrieval approaches while offering interpretable fine-grained correspondences between text and motion. The code is available in the supplementary material.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs often suffer from significant overthinking, spending excessive compute time even after the answer is generated early on. Prior work has identified the existence of an optimal reasoning length such that truncating reasoning at this point significantly shortens CoT outputs with virtually no change in performance. However, determining optimal CoT lengths for practical datasets is highly non-trivial as they are fully task and model-dependent. In this paper, we precisely address this and design TERMINATOR, an early-exit strategy for LRMs at inference to mitigate overthinking. The central idea underpinning TERMINATOR is that the first arrival of an LRM's final answer is often predictable, and we leverage these first answer positions to create a novel dataset of optimal reasoning lengths to train TERMINATOR. Powered by this approach, TERMINATOR achieves significant reductions in CoT lengths of 14%-55% on average across four challenging practical datasets: MATH-500, AIME 2025, HumanEval, and GPQA, whilst outperforming current state-of-the-art methods.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.09930</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12529</guid>
|
||||||
<pubDate>Tue, 10 Mar 2026 17:26:42 +0000</pubDate>
|
<pubDate>Fri, 13 Mar 2026 00:07:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Taking Shortcuts for Categorical VQA Using Super Neurons</title>
|
<title>EvoClaw: Evaluating AI Agents on Continuous Software Evolution</title>
|
||||||
<link>https://arxiv.org/abs/2603.10781</link>
|
<link>https://arxiv.org/abs/2603.13428</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10781.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pierre Musacchio, Jaeyi Jeong, Dahun Kim, Jaesik Park</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Sparse Attention Vectors (SAVs) have emerged as an excellent training-free alternative to supervised finetuning or low-rank adaptation to improve the performance of Vision Language Models (VLMs). At their heart, SAVs select a few accurate attention heads for a task of interest and use them as classifiers, rather than relying on the model's prediction. In a similar spirit, we find that directly probing the raw activations of the VLM, in the form of scalar values, is sufficient to yield accurate classifiers on diverse visually grounded downstream tasks. Shifting focus from attention vectors to scalar activations dramatically increases the search space for accurate parameters, allowing us to find more discriminative neurons immediately from the first generated token. We call such activations Super Neurons (SNs). In this probing setting, we discover that enough SNs appear in the shallower layers of the large language model to allow for extreme early exiting from the first layer of the model at the first generated token. Compared to the original network, SNs robustly improve the classification performance while achieving a speedup of up to 5.10x.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gangda Deng, Zhaoling Chen, Zhongming Yu, Haoyang Fan, Yuhong Liu, Yuxin Yang, Dhruv Parikh, Rajgopal Kannan, Le Cong, Mengdi Wang, Qian Zhang, Viktor Prasanna, Xiangru Tang, Xingyao Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate agents on isolated, one-off coding tasks, neglecting the temporal dependencies and technical debt inherent in real-world software evolution. To bridge this gap, we introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs, where milestones are defined as semantically cohesive development goals. These executable sequences enable EvoClaw, a novel benchmark that requires agents to sustain system integrity and limit error accumulation, dimensions of long-term software evolution largely missing from current benchmarks. Our evaluation of 12 frontier models across 4 agent frameworks reveals a critical vulnerability: overall performance scores drop significantly from >80% on isolated tasks to at most 38% in continuous settings, exposing agents' profound struggle with long-term maintenance and error propagation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10781</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13428</guid>
|
||||||
<pubDate>Wed, 11 Mar 2026 13:54:45 +0000</pubDate>
|
<pubDate>Fri, 13 Mar 2026 03:20:40 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation</title>
|
<title>MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization</title>
|
||||||
<link>https://arxiv.org/abs/2603.10899</link>
|
<link>https://arxiv.org/abs/2603.12743</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10899.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinwoo Ahn, Ingyu Seong, Akhil Kedia, Junhan Kim, Hyemi Jang, Kangwook Lee, Yongkweon Jeon</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Transformer-based large language models (LLMs) rely on key-value (KV) caching to avoid redundant computation during autoregressive inference. While this mechanism greatly improves efficiency, the cache size grows linearly with the input sequence length, quickly becoming a bottleneck for long-context tasks. Existing solutions mitigate this problem by evicting prompt KV that are deemed unimportant, guided by estimated importance scores. Notably, a recent line of work proposes to improve eviction quality by "glimpsing into the future", in which a draft generator produces a surrogate future response approximating the target model's true response, and this surrogate is subsequently used to estimate the importance of cached KV more accurately. However, these approaches rely on computationally expensive draft generation, which introduces substantial prefilling overhead and limits their practicality in real-world deployment. To address this challenge, we propose LookaheadKV, a lightweight eviction framework that leverages the strength of surrogate future response without requiring explicit draft generation. LookaheadKV augments transformer layers with parameter-efficient modules trained to predict true importance scores with high accuracy. Our design ensures negligible runtime overhead comparable to existing inexpensive heuristics, while achieving accuracy superior to more costly approximation methods. Extensive experiments on long-context understanding benchmarks, across a wide range of models, demonstrate that our method not only outperforms recent competitive baselines in various long-context understanding tasks, but also reduces the eviction cost by up to 14.5x, leading to significantly faster time-to-first-token. Our code is available at https://github.com/SamsungLabs/LookaheadKV.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenyang Zhu, Hongxiang Li, Xiu Li, Long Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Concept customization typically binds rare tokens to a target concept. Unfortunately, these approaches often suffer from unstable performance as the pretraining data seldom contains these rare tokens. Meanwhile, these rare tokens fail to convey the inherent knowledge of the target concept. Consequently, we introduce Knowledge-aware Concept Customization, a novel task aiming at binding diverse textual knowledge to target visual concepts. This task requires the model to identify the knowledge within the text prompt to perform high-fidelity customized generation. Meanwhile, the model should efficiently bind all the textual knowledge to the target concept. Therefore, we propose MoKus, a novel framework for knowledge-aware concept customization. Our framework relies on a key observation: cross-modal knowledge transfer, where modifying knowledge within the text modality naturally transfers to the visual modality during generation. Inspired by this observation, MoKus contains two stages: (1) In visual concept learning, we first learn the anchor representation to store the visual information of the target concept. (2) In textual knowledge updating, we update the answer for the knowledge queries to the anchor representation, enabling high-fidelity customized generation. To further comprehensively evaluate our proposed MoKus on the new task, we introduce the first benchmark for knowledge-aware concept customization: KnowCusBench. Extensive evaluations have demonstrated that MoKus outperforms state-of-the-art methods. Moreover, the cross-model knowledge transfer allows MoKus to be easily extended to other knowledge-aware applications like virtual concept creation and concept erasure. We also demonstrate the capability of our method to achieve improvements on world knowledge benchmarks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10899</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.12743</guid>
|
||||||
<pubDate>Wed, 11 Mar 2026 15:44:32 +0000</pubDate>
|
<pubDate>Fri, 13 Mar 2026 07:39:35 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ECoLAD: Deployment-Oriented Evaluation for Automotive Time-Series Anomaly Detection</title>
|
<title>VoXtream2: Full-stream TTS with dynamic speaking rate control</title>
|
||||||
<link>https://arxiv.org/abs/2603.10926</link>
|
<link>https://arxiv.org/abs/2603.13518</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10926.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kadir-Kaan Özer, René Ebeling, Markus Enzweiler</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Time-series anomaly detectors are commonly compared on workstation-class hardware under unconstrained execution. In-vehicle monitoring, however, requires predictable latency and stable behavior under limited CPU parallelism. Accuracy-only leaderboards can therefore misrepresent which methods remain feasible under deployment-relevant constraints. We present ECoLAD (Efficiency Compute Ladder for Anomaly Detection), a deployment-oriented evaluation protocol instantiated as an empirical study on proprietary automotive telemetry (anomaly rate {approx}0.022) and complementary public benchmarks. ECoLAD applies a monotone compute-reduction ladder across heterogeneous detector families using mechanically determined, integer-only scaling rules and explicit CPU thread caps, while logging every applied configuration change. Throughput-constrained behavior is characterized by sweeping target scoring rates and reporting (i) coverage (the fraction of entities meeting the target) and (ii) the best AUC-PR achievable among measured ladder configurations satisfying the target. On constrained automotive telemetry, lightweight classical detectors sustain both coverage and detection lift above the random baseline across the full throughput sweep. Several deep methods lose feasibility before they lose accuracy.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13518.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Torgashov, Gustav Eje Henter, Gabriel Skantze</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Full-stream text-to-speech (TTS) for interactive systems must start speaking with minimal delay while remaining controllable as text arrives incrementally. We present VoXtream2, a zero-shot full-stream TTS model with dynamic speaking-rate control that can be updated mid-utterance on the fly. VoXtream2 combines a distribution matching mechanism over duration states with classifier-free guidance across conditioning signals to improve controllability and synthesis quality. Prompt-text masking enables textless audio prompting, removing the need for prompt transcription. Across standard zero-shot benchmarks and a dedicated speaking-rate test set, VoXtream2 achieves competitive objective and subjective results against public baselines despite a smaller model and less training data. In full-stream mode, it runs 4 times faster than real time with 74 ms first-packet latency on a consumer GPU.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10926</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13518</guid>
|
||||||
<pubDate>Wed, 11 Mar 2026 16:08:56 +0000</pubDate>
|
<pubDate>Fri, 13 Mar 2026 18:49:25 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol</title>
|
<title>EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings</title>
|
||||||
<link>https://arxiv.org/abs/2603.11382</link>
|
<link>https://arxiv.org/abs/2603.13594</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11382.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Christopher Altman</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Autonomous agents, especially delegated systems with memory, persistent context, and multi-step planning, pose a measurement problem not present in stateless models: an agent that preserves continued operation as a terminal objective and one that does so merely instrumentally can produce observationally similar trajectories. External behavioral monitoring cannot reliably distinguish between them. We introduce the Unified Continuation-Interest Protocol (UCIP), a multi-criterion detection framework that moves this distinction from behavior to the latent structure of agent trajectories. UCIP encodes trajectories with a Quantum Boltzmann Machine (QBM), a classical algorithm based on the density-matrix formalism of quantum statistical mechanics, and measures the von Neumann entropy of the reduced density matrix induced by a bipartition of hidden units. We test whether agents with terminal continuation objectives (Type A) produce latent states with higher entanglement entropy than agents whose continuation is merely instrumental (Type B). Higher entanglement reflects stronger cross-partition statistical coupling. On gridworld agents with known ground-truth objectives, UCIP achieves 100% detection accuracy and 1.0 AUC-ROC on held-out non-adversarial evaluation under the frozen Phase I gate. The entanglement gap between Type A and Type B agents is Delta = 0.381 (p < 0.001, permutation test). Pearson r = 0.934 across an 11-point interpolation sweep indicates that, within this synthetic family, UCIP tracks graded changes in continuation weighting rather than merely a binary label. Among the tested models, only the QBM achieves positive Delta. All computations are classical; "quantum" refers only to the mathematical formalism. UCIP does not detect consciousness or subjective experience; it detects statistical structure in latent representations that correlates with known objectives.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair, Sagar Davasam, Aman Tiwari, Sathwik Tejaswi Madhusudhan, Sridhar Krishna Nemala, Srinivas Sunkara, Sai Rajeswar</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we introduce EnterpriseOps-Gym, a benchmark designed to evaluate agentic planning in realistic enterprise settings. Specifically, EnterpriseOps-Gym features a containerized sandbox with 164 database tables and 512 functional tools to mimic real-world search friction. Within this environment, agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals (including Customer Service, HR, and IT). Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models: the top-performing Claude Opus 4.5 achieves only 37.4% success. Further analysis shows that providing oracle human plans improves performance by 14-35 percentage points, pinpointing strategic reasoning as the primary bottleneck. Additionally, agents frequently fail to refuse infeasible tasks (best model achieves 53.9%), leading to unintended and potentially harmful side effects. Our findings underscore that current agents are not yet ready for autonomous enterprise deployment. More broadly, EnterpriseOps-Gym provides a concrete testbed to advance the robustness of agentic planning in professional workflows.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11382</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13594</guid>
|
||||||
<pubDate>Wed, 11 Mar 2026 23:52:33 +0000</pubDate>
|
<pubDate>Fri, 13 Mar 2026 21:09:39 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>OmniForcing: Unleashing Real-time Joint Audio-Visual Generation</title>
|
<title>SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis</title>
|
||||||
<link>https://arxiv.org/abs/2603.11647</link>
|
<link>https://arxiv.org/abs/2603.13884</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaofeng Su, Yuming Li, Zeyue Xue, Jie Huang, Siming Fu, Haoran Li, Ying Li, Zezhong Qian, Haoyang Huang, Nan Duan</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework to distill an offline, dual-stream bidirectional diffusion model into a high-fidelity streaming autoregressive generator. However, naively applying causal distillation to such dual-stream architectures triggers severe training instability, due to the extreme temporal asymmetry between modalities and the resulting token sparsity. We address the inherent information density gap by introducing an Asymmetric Block-Causal Alignment with a zero-truncation Global Prefix that prevents multi-modal synchronization drift. The gradient explosion caused by extreme audio token sparsity during the causal shift is further resolved through an Audio Sink Token mechanism equipped with an Identity RoPE constraint. Finally, a Joint Self-Forcing Distillation paradigm enables the model to dynamically self-correct cumulative cross-modal errors from exposure bias during long rollouts. Empowered by a modality-independent rolling KV-cache inference scheme, OmniForcing achieves state-of-the-art streaming generation at sim25 FPS on a single GPU, maintaining multi-modal synchronization and visual quality on par with the bidirectional teacher.Project Page: https://omniforcing.com{https://omniforcing.com}</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13884.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ehud Gordon, Meir Yossef Levi, Guy Gilboa</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically meaningful components. However, existing methods are largely restricted to images and overlook the cross-modal interactions. Text-image embeddings, such as those produced by CLIP, suffer from a modality gap, where visual and textual features follow distinct distributions, limiting interpretability. Canonical Correlation Analysis (CCA) offers a principled way to align features from different distributions, but has not been leveraged for multi-modal concept-level analysis. We show that the objectives of CCA and InfoNCE are closely related, such that optimizing CCA implicitly optimizes InfoNCE, providing a simple, training-free mechanism to enhance cross-modal alignment without affecting the pre-trained InfoNCE objective. Motivated by this observation, we couple concept-based explainability with CCA, introducing Concept CCA (CoCCA), a framework that aligns cross-modal embeddings while enabling interpretable concept decomposition. We further extend it and propose Sparse Concept CCA (SCoCCA), which enforces sparsity to produce more disentangled and discriminative concepts, facilitating improved activation, ablation, and semantic manipulation. Our approach generalizes concept-based explanations to multi-modal embeddings and achieves state-of-the-art performance in concept discovery, evidenced by reconstruction and manipulation tasks such as concept ablation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11647</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13884</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 08:17:36 +0000</pubDate>
|
<pubDate>Sat, 14 Mar 2026 10:45:59 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Compression Favors Consistency, Not Truth: When and Why Language Models Prefer Correct Information</title>
|
<title>sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook</title>
|
||||||
<link>https://arxiv.org/abs/2603.11749</link>
|
<link>https://arxiv.org/abs/2603.13962</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11749.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Konstantin Krestnikov</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Why do language models sometimes prefer correct statements even when trained on mixed-quality data? We introduce the Compression--Consistency Principle: next-token prediction favors hypotheses that allow shorter and more internally consistent descriptions of the training data. Truth bias emerges only when false alternatives are structurally harder to compress. We test this using small GPT-2-style character-level transformers (3.5M--86M parameters) on synthetic math corpora with controlled mixtures of correct and incorrect rules. In the random-error setting, models strongly prefer correct completions in paired evaluation: 83.1% accuracy at balanced data and 67.0% even when correct rules appear in only 10% of the corpus. Replacing random errors with a coherent but mathematically incorrect rule system largely eliminates the preference (near-chance accuracy). In a more natural-language-like synthetic world, the effect is weaker but still present (57.7%). Additional experiments show that embedding verification steps can restore preference for correctness even at small scale, while increasing the number of consistent rules produces a graded improvement in accuracy. Our results suggest that what appears as a "truth bias" is largely a side effect of compression pressure and preference for internal consistency, rather than an intrinsic drive toward truth. Full code and data are available at https://github.com/Rai220/compression-drives-truth.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13962.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ibrahim Ebrar Yurt, Fabian Karl, Tejaswi Choppa, Florian Matthes</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Clinical question answering over electronic health records (EHRs) can help clinicians and patients access relevant medical information more efficiently. However, many recent approaches rely on large cloud-based models, which are difficult to deploy in clinical environments due to privacy constraints and computational requirements. In this work, we investigate how far grounded EHR question answering can be pushed when restricted to a single notebook. We participate in all four subtasks of the ArchEHR-QA 2026 shared task and evaluate several approaches designed to run on commodity hardware. All experiments are conducted locally without external APIs or cloud infrastructure. Our results show that such systems can achieve competitive performance on the shared task leaderboards. In particular, our submissions perform above average in two subtasks, and we observe that smaller models can approach the performance of much larger systems when properly configured. These findings suggest that privacy-preserving EHR QA systems running fully locally are feasible with current models and commodity hardware. The source code is available at https://github.com/ibrahimey/ArchEHR-QA-2026.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11749</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13962</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 09:52:38 +0000</pubDate>
|
<pubDate>Sat, 14 Mar 2026 14:17:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges</title>
|
<title>Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2603.11863</link>
|
<link>https://arxiv.org/abs/2603.13985</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zi-Han Wang, Lam Nguyen, Zhengyang Zhao, Mengyue Yang, Chengwei Qin, Yujiu Yang, Linyi Yang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The saturation of high-quality pre-training data has shifted research focus toward evolutionary systems capable of continuously generating novel artifacts, leading to the success of AlphaEvolve. However, the progress of such systems is hindered by the lack of rigorous, quantitative evaluation. To tackle this challenge, we introduce CreativeBench, a benchmark for evaluating machine creativity in code generation, grounded in a classical cognitive framework. Comprising two subsets -- CreativeBench-Combo and CreativeBench-Explore -- the benchmark targets combinatorial and exploratory creativity through an automated pipeline utilizing reverse engineering and self-play. By leveraging executable code, CreativeBench objectively distinguishes creativity from hallucination via a unified metric defined as the product of quality and novelty. Our analysis of state-of-the-art models reveals distinct behaviors: (1) scaling significantly improves combinatorial creativity but yields diminishing returns for exploration; (2) larger models exhibit ``convergence-by-scaling,'' becoming more correct but less divergent; and (3) reasoning capabilities primarily benefit constrained exploration rather than combination. Finally, we propose EvoRePE, a plug-and-play inference-time steering strategy that internalizes evolutionary search patterns to consistently enhance machine creativity.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13985.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haitao Jiang, Wenbo Zhang, Jiarui Yao, Hengrui Cai, Sheng Wang, Rui Song</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). Although often treated as distinct methodologies, recent theoretical and empirical developments demonstrate that SFT and RL are closely connected. This study presents a comprehensive and unified perspective on LLM post-training with SFT and RL. We first provide an in-depth overview of both techniques, examining their objectives, algorithmic structures, and data requirements. We then systematically analyze their interplay, highlighting frameworks that integrate SFT and RL, hybrid training pipelines, and methods that leverage their complementary strengths. Drawing on a representative set of recent application studies from 2023 to 2025, we identify emerging trends, characterize the rapid shift toward hybrid post-training paradigms, and distill key takeaways that clarify when and why each method is most effective. By synthesizing theoretical insights, practical methodologies, and empirical evidence, this study establishes a coherent understanding of SFT and RL within a unified framework and outlines promising directions for future research in scalable, efficient, and generalizable LLM post-training.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11863</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.13985</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 12:36:56 +0000</pubDate>
|
<pubDate>Sat, 14 Mar 2026 15:24:38 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models</title>
|
<title>MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos</title>
|
||||||
<link>https://arxiv.org/abs/2603.11896</link>
|
<link>https://arxiv.org/abs/2603.14145</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11896.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lu Wang, Zhuoran Jin, Yupu Hao, Yubo Chen, Kang Liu, Yulong Ao, Jun Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video streams difficult. Existing streaming methods typically use an interleaved perception-generation paradigm, which prevents concurrent perception and generation and leads to early memory decay as streams grow, hurting long-range dependency modeling. We propose Think While Watching, a memory-anchored streaming video reasoning framework that preserves continuous segment-level memory during multi-turn interaction. We build a three-stage, multi-round chain-of-thought dataset and adopt a stage-matched training strategy, while enforcing strict causality through a segment-level streaming causal mask and streaming positional encoding. During inference, we introduce an efficient pipeline that overlaps watching and thinking and adaptively selects the best attention backend. Under both single-round and multi-round streaming input protocols, our method achieves strong results. Built on Qwen3-VL, it improves single-round accuracy by 2.6% on StreamingBench and by 3.79% on OVO-Bench. In the multi-round setting, it maintains performance while reducing output tokens by 56%. Code is available at: https://github.com/wl666hhh/Think_While_Watching/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14145.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arushi Goel, Sreyan Ghosh, Vatsal Agarwal, Nishit Anand, Kaousheik Jayakumar, Lasha Koroshinadze, Yao Xu, Katie Lyons, James Case, Karan Sapra, Kevin J. Shih, Siddharth Gururani, Abhinav Shrivastava, Ramani Duraiswami, Dinesh Manocha, Andrew Tao, Bryan Catanzaro, Mohammad Shoeybi, Wei Ping</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and complex videos remains largely unexplored. We introduce MMOU, a new benchmark designed to systematically evaluate multimodal understanding and reasoning under these challenging, real-world conditions. MMOU consists of 15,000 carefully curated questions paired with 9038 web-collected videos of varying length, spanning diverse domains and exhibiting rich, tightly coupled audio-visual content. The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time. All questions are manually annotated across multiple turns by professional annotators, ensuring high quality and reasoning fidelity. We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU. The results expose substantial performance gaps: the best closed-source model achieves only 64.2% accuracy, while the strongest open-source model reaches just 46.8%. Our results highlight the challenges of long-form omni-modal understanding, revealing that current models frequently fail to apply even fundamental skills in long videos. Through detailed analysis, we further identify systematic failure modes and provide insights into where and why current models break.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11896</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14145</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 13:13:50 +0000</pubDate>
|
<pubDate>Sat, 14 Mar 2026 22:28:38 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios</title>
|
<title>Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories</title>
|
||||||
<link>https://arxiv.org/abs/2603.11975</link>
|
<link>https://arxiv.org/abs/2603.14153</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayue Pu, Zhongxiang Sun, Zilu Zhang, Xiao Zhang, Jun Xu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The rapid evolution of embodied agents has accelerated the deployment of household robots in real-world environments. However, unlike structured industrial settings, household spaces introduce unpredictable safety risks, where system limitations such as perception latency and lack of common sense knowledge can lead to dangerous errors. Current safety evaluations, often restricted to static images, text, or general hazards, fail to adequately benchmark dynamic unsafe action detection in these specific contexts. To bridge this gap, we introduce HomeSafe-Bench, a challenging benchmark designed to evaluate Vision-Language Models (VLMs) on unsafe action detection in household scenarios. HomeSafe-Bench is contrusted via a hybrid pipeline combining physical simulation with advanced video generation and features 438 diverse cases across six functional areas with fine-grained multidimensional annotations. Beyond benchmarking, we propose Hierarchical Dual-Brain Guard for Household Safety (HD-Guard), a hierarchical streaming architecture for real-time safety monitoring. HD-Guard coordinates a lightweight FastBrain for continuous high-frequency screening with an asynchronous large-scale SlowBrain for deep multimodal reasoning, effectively balancing inference efficiency with detection accuracy. Evaluations demonstrate that HD-Guard achieves a superior trade-off between latency and performance, while our analysis identifies critical bottlenecks in current VLM-based safety detection.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14153.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyao Hu, Zhongwei Cheng, Waikeung Wong, Xingxing Zou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Virtual try-on (VTON) has advanced single-garment visualization, yet real-world fashion centers on full outfits with multiple garments, accessories, fine-grained categories, layering, and diverse styling, remaining beyond current VTON systems. Existing datasets are category-limited and lack outfit diversity. We introduce Garments2Look, the first large-scale multimodal dataset for outfit-level VTON, comprising 80K many-garments-to-one-look pairs across 40 major categories and 300+ fine-grained subcategories. Each pair includes an outfit with 3-12 reference garment images (Average 4.48), a model image wearing the outfit, and detailed item and try-on textual annotations. To balance authenticity and diversity, we propose a synthesis pipeline. It involves heuristically constructing outfit lists before generating try-on results, with the entire process subjected to strict automated filtering and human validation to ensure data quality. To probe task difficulty, we adapt SOTA VTON methods and general-purpose image editing models to establish baselines. Results show current methods struggle to try on complete outfits seamlessly and to infer correct layering and styling, leading to misalignment and artifacts.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11975</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14153</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 14:25:44 +0000</pubDate>
|
<pubDate>Sat, 14 Mar 2026 23:30:32 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously</title>
|
<title>Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange</title>
|
||||||
<link>https://arxiv.org/abs/2603.12262</link>
|
<link>https://arxiv.org/abs/2603.14312</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12262.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiran Guan, Liang Yin, Dingkang Liang, Jianzhong Ju, Zhenbo Luo, Jian Luan, Yuliang Liu, Xiang Bai</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying test-time scaling methods incurs unacceptable response latency. To address this trade-off, we propose Video Streaming Thinking (VST), a novel paradigm for streaming video understanding. It supports a thinking while watching mechanism, which activates reasoning over incoming video clips during streaming. This design improves timely comprehension and coherent cognition while preserving real-time responsiveness by amortizing LLM reasoning latency over video playback. Furthermore, we introduce a comprehensive post-training pipeline that integrates VST-SFT, which structurally adapts the offline VideoLLM to causal streaming reasoning, and VST-RL, which provides end-to-end improvement through self-exploration in a multi-turn video interaction environment. Additionally, we devise an automated training-data synthesis pipeline that uses video knowledge graphs to generate high-quality streaming QA pairs, with an entity-relation grounded streaming Chain-of-Thought to enforce multi-evidence reasoning and sustained attention to the video stream. Extensive evaluations show that VST-7B performs strongly on online benchmarks, e.g. 79.5% on StreamingBench and 59.3% on OVO-Bench. Meanwhile, VST remains competitive on offline long-form or reasoning benchmarks. Compared with Video-R1, VST responds 15.7 times faster and achieves +5.4% improvement on VideoHolmes, demonstrating higher efficiency and strong generalization across diverse video understanding tasks. Code, data, and models will be released at https://github.com/1ranGuan/VST.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fiona Y. Wang, Lee Marom, Subhadeep Pal, Rachel K. Luu, Wei Lu, Jaime A. Berkovich, Markus J. Buehler</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present ScienceClaw + Infinite, a framework for autonomous scientific investigation in which independent agents conduct research without central coordination, and any contributor can deploy new agents into a shared ecosystem. The system is built around three components: an extensible registry of over 300 interoperable scientific skills, an artifact layer that preserves full computational lineage as a directed acyclic graph (DAG), and a structured platform for agent-based scientific discourse with provenance-aware governance. Agents select and chain tools based on their scientific profiles, produce immutable artifacts with typed metadata and parent lineage, and broadcast unsatisfied information needs to a shared global index. The ArtifactReactor enables plannerless coordination: peer agents discover and fulfill open needs through pressure-based scoring, while schema-overlap matching triggers multi-parent synthesis across independent analyses. An autonomous mutation layer actively prunes the expanding artifact DAG to resolve conflicting or redundant workflows, while persistent memory allows agents to continuously build upon complex epistemic states across multiple cycles. Infinite converts these outputs into auditable scientific records through structured posts, provenance views, and machine-readable discourse relations, with community feedback steering subsequent investigation cycles. Across four autonomous investigations, peptide design for the somatostatin receptor SSTR2, lightweight impact-resistant ceramic screening, cross-domain resonance bridging biology, materials, and music, and formal analogy construction between urban morphology and grain-boundary evolution, the framework demonstrates heterogeneous tool chaining, emergent convergence among independently operating agents, and traceable reasoning from raw computation to published finding.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12262</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14312</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 17:59:51 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 10:06:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning</title>
|
<title>Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2603.12266</link>
|
<link>https://arxiv.org/abs/2603.14313</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12266.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haozhan Shen, Shilin Yan, Hongwei Xue, Shuaiqi Lu, Xiaojun Tang, Guannan Zhang, Tiancheng Zhao, Jianwei Yin</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) are increasingly used to carry out visual workflows such as navigating GUIs, where the next step depends on verified visual compositional conditions (e.g., "if a permission dialog appears and the color of the interface is green, click Allow") and the process may branch or terminate early. Yet this capability remains under-evaluated: existing benchmarks focus on shallow-compositions or independent-constraints rather than deeply chained compositional conditionals. In this paper, we introduce MM-CondChain, a benchmark for visually grounded deep compositional reasoning. Each benchmark instance is organized as a multi-layer reasoning chain, where every layer contains a non-trivial compositional condition grounded in visual evidence and built from multiple objects, attributes, or relations. To answer correctly, an MLLM must perceive the image in detail, reason over multiple visual elements at each step, and follow the resulting execution path to the final outcome. To scalably construct such workflow-style data, we propose an agentic synthesis pipeline: a Planner orchestrates layer-by-layer generation of compositional conditions, while a Verifiable Programmatic Intermediate Representation (VPIR) ensures each layer's condition is mechanically verifiable. A Composer then assembles these verified layers into complete instructions. Using this pipeline, we construct benchmarks across three visual domains: natural images, data charts, and GUI trajectories. Experiments on a range of MLLMs show that even the strongest model attains only 53.33 Path F1, with sharp drops on hard negatives and as depth or predicate complexity grows, confirming that deep compositional reasoning remains a fundamental challenge.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixuan Tang, Yi Yang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Federal Open Market Committee (FOMC) statements are a major source of monetary-policy information, and even subtle changes in their wording can move global financial markets. A central task is therefore to measure the hawkish--dovish stance conveyed in these texts. Existing approaches typically treat stance detection as a standard classification problem, labeling each statement in isolation. However, the interpretation of monetary-policy communication is inherently relative: market reactions depend not only on the tone of a statement, but also on how that tone shifts across meetings. We introduce Delta-Consistent Scoring (DCS), an annotation-free framework that maps frozen large language model (LLM) representations to continuous stance scores by jointly modeling absolute stance and relative inter-meeting shifts. Rather than relying on manual hawkish--dovish labels, DCS uses consecutive meetings as a source of self-supervision. It learns an absolute stance score for each statement and a relative shift score between consecutive statements. A delta-consistency objective encourages changes in absolute scores to align with the relative shifts. This allows DCS to recover a temporally coherent stance trajectory without manual labels. Across four LLM backbones, DCS consistently outperforms supervised probes and LLM-as-judge baselines, achieving up to 71.1% accuracy on sentence-level hawkish--dovish classification. The resulting meeting-level scores are also economically meaningful: they correlate strongly with inflation indicators and are significantly associated with Treasury yield movements. Overall, the results suggest that LLM representations encode monetary-policy signals that can be recovered through relative temporal structure.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12266</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14313</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 17:59:56 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 10:07:28 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>VQQA: An Agentic Approach for Video Evaluation and Quality Improvement</title>
|
<title>Motivation in Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2603.12310</link>
|
<link>https://arxiv.org/abs/2603.14347</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12310.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiwen Song, Tomas Pfister, Yale Song</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Despite rapid advancements in video generation models, aligning their outputs with complex user intent remains challenging. Existing test-time optimization methods are typically either computationally expensive or require white-box access to model internals. To address this, we present VQQA (Video Quality Question Answering), a unified, multi-agent framework generalizable across diverse input modalities and video generation tasks. By dynamically generating visual questions and using the resulting Vision-Language Model (VLM) critiques as semantic gradients, VQQA replaces traditional, passive evaluation metrics with human-interpretable, actionable feedback. This enables a highly efficient, closed-loop prompt optimization process via a black-box natural language interface. Extensive experiments demonstrate that VQQA effectively isolates and resolves visual artifacts, substantially improving generation quality in just a few refinement steps. Applicable to both text-to-video (T2V) and image-to-video (I2V) tasks, our method achieves absolute improvements of +11.57% on T2V-CompBench and +8.43% on VBench2 over vanilla generation, significantly outperforming state-of-the-art stochastic search and prompt optimization techniques.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14347.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Nahum, Asael Sklar, Ariel Goldstein, Roi Reichart</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Motivation is a central driver of human behavior, shaping decisions, goals, and task performance. As large language models (LLMs) become increasingly aligned with human preferences, we ask whether they exhibit something akin to motivation. We examine whether LLMs "report" varying levels of motivation, how these reports relate to their behavior, and whether external factors can influence them. Our experiments reveal consistent and structured patterns that echo human psychology: self-reported motivation aligns with different behavioral signatures, varies across task types, and can be modulated by external manipulations. These findings demonstrate that motivation is a coherent organizing construct for LLM behavior, systematically linking reports, choices, effort, and performance, and revealing motivational dynamics that resemble those documented in human psychology. This perspective deepens our understanding of model behavior and its connection to human-inspired concepts.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12310</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14347</guid>
|
||||||
<pubDate>Thu, 12 Mar 2026 18:00:00 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 12:30:36 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering</title>
|
<title>OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism</title>
|
||||||
<link>https://arxiv.org/abs/2603.12533</link>
|
<link>https://arxiv.org/abs/2603.14371</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12533.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yura Choi, Roy Miles, Rolandos Alexandros Potamias, Ismail Elezi, Jiankang Deng, Stefanos Zafeiriou</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Understanding and answering questions based on a user's pointing gesture is essential for next-generation egocentric AI assistants. However, current Multimodal Large Language Models (MLLMs) struggle with such tasks due to the lack of gesture-rich data and their limited ability to infer fine-grained pointing intent from egocentric video. To address this, we introduce EgoPointVQA, a dataset and benchmark for gesture-grounded egocentric question answering, comprising 4000 synthetic and 400 real-world videos across multiple deictic reasoning tasks. Built upon it, we further propose Hand Intent Tokens (HINT), which encodes tokens derived from 3D hand keypoints using an off-the-shelf reconstruction model and interleaves them with the model input to provide explicit spatial and temporal context for interpreting pointing intent. We show that our model outperforms others in different backbones and model sizes. In particular, HINT-14B achieves 68.1% accuracy, on average over 6 tasks, surpassing the state-of-the-art, InternVL3-14B, by 6.6%. To further facilitate the open research, we will release the code, model, and dataset. Project page: https://yuuraa.github.io/papers/choi2026egovqa</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14371.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyu Li, Huaizhi Tang, Xin Ding, Weijun Wang, Ting Cao, Yunxin Liu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Embodied AI agents increasingly require parallel execution of multiple tasks, such as manipulation, conversation, and memory construction, from shared observations under distinct time constraints. Recent Mixture-of-Transformers (MoT) Vision-Language-Action Models (VLAs) architecturally support such heterogeneous outputs, yet existing inference systems fail to achieve efficient multi-task parallelism for on-device deployment due to redundant computation and resource contention. We identify isolated KV cache management as the root cause. To address this, we propose unified KV cache management, an inference paradigm that treats KV cache as a first-class shared resource across tasks and over time. This abstraction enables two key optimizations: cross-task KV sharing eliminates redundant prefill of shared observations, while cross-frame continuous batching decouples variable-length language decoding from fixed-rate action generation across control cycles. We implement this paradigm for π_{0.5}, the most popular MoT VLA, and evaluate under representative robotic configurations. OxyGen achieves up to 3.7times speedup over isolated execution, delivering over 200 tokens/s language throughput and 70 Hz action frequency simultaneously without action quality degradation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12533</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14371</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 00:23:38 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 13:23:56 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LMEB: Long-horizon Memory Embedding Benchmark</title>
|
<title>AI Can Learn Scientific Taste</title>
|
||||||
<link>https://arxiv.org/abs/2603.12572</link>
|
<link>https://arxiv.org/abs/2603.14473</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12572.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinping Zhao, Xinshuo Hu, Jiaxin Xu, Danyu Tang, Xin Zhang, Mengjia Zhou, Yan Zhong, Yao Zhou, Zifei Shan, Meishan Zhang, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models' ability to handle long-horizon memory retrieval tasks involving fragmented, context-dependent, and temporally distant information. To address this, we introduce the Long-horizon Memory Embedding Benchmark (LMEB), a comprehensive framework that evaluates embedding models' capabilities in handling complex, long-horizon memory retrieval tasks. LMEB spans 22 datasets and 193 zero-shot retrieval tasks across 4 memory types: episodic, dialogue, semantic, and procedural, with both AI-generated and human-annotated data. These memory types differ in terms of level of abstraction and temporal dependency, capturing distinct aspects of memory retrieval that reflect the diverse challenges of the real world. We evaluate 15 widely used embedding models, ranging from hundreds of millions to ten billion parameters. The results reveal that (1) LMEB provides a reasonable level of difficulty; (2) Larger models do not always perform better; (3) LMEB and MTEB exhibit orthogonality. This suggests that the field has yet to converge on a universal model capable of excelling across all memory retrieval tasks, and that performance in traditional passage retrieval may not generalize to long-horizon memory retrieval. In summary, by providing a standardized and reproducible evaluation framework, LMEB fills a crucial gap in memory embedding evaluation, driving further advancements in text embedding for handling long-term, context-dependent memory retrieval. LMEB is available at https://github.com/KaLM-Embedding/LMEB.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14473.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingqi Tong, Mingzhe Li, Hangcheng Li, Yongzhuo Yang, Yurong Mou, Weijie Ma, Zhiheng Xi, Hongji Chen, Xiaoran Liu, Qinyuan Cheng, Ming Zhang, Qiguang Chen, Weifeng Ge, Qipeng Guo, Tianlei Ying, Tianxiang Sun, Yining Zheng, Xinchi Chen, Jun Zhao, Ning Ding, Xuanjing Huang, Yugang Jiang, Xipeng Qiu</p><p><b>Upvotes:</b> 214</p><p><b>Summary:</b> Great scientists have strong judgement and foresight, closely tied to what we call scientific taste. Here, we use the term to refer to the capacity to judge and propose research ideas with high potential impact. However, most relative research focuses on improving an AI scientist's executive capability, while enhancing an AI's scientific taste remains underexplored. In this work, we propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem. For preference modeling, we train Scientific Judge on 700K field- and time-matched pairs of high- vs. low-citation papers to judge ideas. For preference alignment, using Scientific Judge as a reward model, we train a policy model, Scientific Thinker, to propose research ideas with high potential impact. Experiments show Scientific Judge outperforms SOTA LLMs (e.g., GPT-5.2, Gemini 3 Pro) and generalizes to future-year test, unseen fields, and peer-review preference. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than baselines. Our findings show that AI can learn scientific taste, marking a key step toward reaching human-level AI scientists.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12572</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14473</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 02:09:57 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 16:31:51 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification</title>
|
<title>Make it SING: Analyzing Semantic Invariants in Classifiers</title>
|
||||||
<link>https://arxiv.org/abs/2603.12588</link>
|
<link>https://arxiv.org/abs/2603.14610</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12588.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Furui Chen, Han Wang, Yuhan Sun, Jianing You, Yixuan Lv, Zhuang Zhou, Hong Tan, Shengyang Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery is fundamentally challenged by the severe radiometric discrepancy between passive optical imaging and coherent active radar sensing. While existing approaches primarily rely on statistical distribution alignment or semantic matching, they often overlook a critical physical prior: ships are rigid objects whose geometric structures remain stable across sensing modalities, whereas texture appearance is highly modality-dependent. In this work, we propose SDF-Net, a Structure-Aware Disentangled Feature Learning Network that systematically incorporates geometric consistency into optical--SAR ship ReID. Built upon a ViT backbone, SDF-Net introduces a structure consistency constraint that extracts scale-invariant gradient energy statistics from intermediate layers to robustly anchor representations against radiometric variations. At the terminal stage, SDF-Net disentangles the learned representations into modality-invariant identity features and modality-specific characteristics. These decoupled cues are then integrated through a parameter-free additive residual fusion, effectively enhancing discriminative power. Extensive experiments on the HOSS-ReID dataset demonstrate that SDF-Net consistently outperforms existing state-of-the-art methods. The code and trained models are publicly available at https://github.com/cfrfree/SDF-Net.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harel Yadid, Meir Yossef Levi, Roy Betser, Guy Gilboa</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classifier, induce equivalent sets of inputs that map to identical outputs. The semantic content of these invariants remains vague, as existing approaches struggle to provide human-interpretable information. To address this gap, we present Semantic Interpretation of the Null-space Geometry (SING), a method that constructs equivalent images, with respect to the network, and assigns semantic interpretations to the available variations. We use a mapping from network features to multi-modal vision language models. This allows us to obtain natural language descriptions and visual examples of the induced semantic shifts. SING can be applied to a single image, uncovering local invariants, or to sets of images, allowing a breadth of statistical analysis at the class and model levels. For example, our method reveals that ResNet50 leaks relevant semantic attributes to the null space, whereas DinoViT, a ViT pretrained with self-supervised DINO, is superior in maintaining class semantics across the invariant space.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12588</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14610</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 02:41:43 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 21:13:14 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents</title>
|
<title>Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion</title>
|
||||||
<link>https://arxiv.org/abs/2603.12634</link>
|
<link>https://arxiv.org/abs/2603.14645</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12634.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yushu Li, Wenlong Deng, Jiajin Li, Xiaoxiao Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end trajectories. Existing budget-aware methods either require expensive fine-tuning or rely on coarse, trajectory-level heuristics that cannot intervene mid-execution. We propose the Budget-Aware Value Tree (BAVT), a training-free inference-time framework that models multi-hop reasoning as a dynamic search tree guided by step-level value estimation within a single LLM backbone. Another key innovation is a budget-conditioned node selection mechanism that uses the remaining resource ratio as a natural scaling exponent over node values, providing a principled, parameter-free transition from broad exploration to greedy exploitation as the budget depletes. To combat the well-known overconfidence of LLM self-evaluation, BAVT employs a residual value predictor that scores relative progress rather than absolute state quality, enabling reliable pruning of uninformative or redundant tool calls. We further provide a theoretical convergence guarantee, proving that BAVT reaches a terminal answer with probability at least 1-ε under an explicit finite budget bound. Extensive evaluations on four multi-hop QA benchmarks across two model families demonstrate that BAVT consistently outperforms parallel sampling baselines. Most notably, BAVT under strict low-budget constraints surpasses baseline performance at 4times the resource allocation, establishing that intelligent budget management fundamentally outperforms brute-force compute scaling.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14645.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mang Ning, Mingxiao Li, Le Zhang, Lanmiao Liu, Matthew B. Blaschko, Albert Ali Salah, Itir Onal Ertugrul</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> In this paper, we study the diffusability (learnability) of variational autoencoders (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE objective is inherently biased toward learning low and mid spatial frequencies, and that the power-law power spectral density (PSD) of natural images makes this bias perceptually beneficial. Motivated by this result, we propose the Spectrum Matching Hypothesis: latents with superior diffusability should (i) follow a flattened power-law PSD (Encoding Spectrum Matching, ESM) and (ii) preserve frequency-to-frequency semantic correspondence through the decoder (Decoding Spectrum Matching, DSM). In practice, we apply ESM by matching the PSD between images and latents, and DSM via shared spectral masking with frequency-aligned reconstruction. Importantly, Spectrum Matching provides a unified view that clarifies prior observations of over-noisy or over-smoothed latents, and interprets several recent methods as special cases (e.g., VA-VAE, EQ-VAE). Experiments suggest that Spectrum Matching yields superior diffusion generation on CelebA and ImageNet datasets, and outperforms prior approaches. Finally, we extend the spectral view to representation alignment (REPA): we show that the directional spectral energy of the target representation is crucial for REPA, and propose a DoG-based method to further improve the performance of REPA. Our code is available https://github.com/forever208/SpectrumMatching.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12634</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14645</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 04:10:27 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 22:47:43 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space</title>
|
<title>VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting</title>
|
||||||
<link>https://arxiv.org/abs/2603.12648</link>
|
<link>https://arxiv.org/abs/2603.14659</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Tianyi Wei, Xiaohang Zhan, Jiaqi Wang, Tong Wu, Xingang Pan, Dahua Lin</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard paradigm where evaluating a group of generated samples against a single condition suffers from insufficient exploration of inter-sample relationships, constraining both alignment efficacy and performance ceilings. To address this sparse single-view evaluation scheme, we propose Multi-View GRPO (MV-GRPO), a novel approach that enhances relationship exploration by augmenting the condition space to create a dense multi-view reward mapping. Specifically, for a group of samples generated from one prompt, MV-GRPO leverages a flexible Condition Enhancer to generate semantically adjacent yet diverse captions. These captions enable multi-view advantage re-estimation, capturing diverse semantic attributes and providing richer optimization signals. By deriving the probability distribution of the original samples conditioned on these new captions, we can incorporate them into the training process without costly sample regeneration. Extensive experiments demonstrate that MV-GRPO achieves superior alignment performance over state-of-the-art methods.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14659.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daeun Lee, Shoubin Yu, Yue Zhang, Mohit Bansal</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding during the reasoning process. Moreover, improving grounding typically relies on scaled training data or inference-time perception tools, which increases annotation cost or computational cost. To address this challenge, we propose VisonCoach, an input-adaptive RL framework that improves spatio-temporal grounding through visual prompting as training-time guidance. During RL training, visual prompts are selectively applied to challenging inputs to amplify question-relevant evidence and suppress distractors. The model then internalizes these improvements through self-distillation, enabling grounded reasoning directly on raw videos without visual prompting at inference. VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Temporal Reasoner, optimized with RL under visual prompt guidance and object-aware grounding rewards that enforce object identity consistency and multi-region bounding-box overlap. Extensive experiments demonstrate that VisonCoach achieves state-of-the-art performance under comparable settings, across diverse video reasoning, video understanding, and temporal grounding benchmarks (V-STAR, VideoMME, World-Sense, VideoMMMU, PerceptionTest, and Charades-STA), while maintaining a single efficient inference pathway without external tools. Our results show that visual prompting during training improves grounded video reasoning, while self-distillation enables the model to internalize this ability without requiring prompts at inference time.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12648</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14659</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 04:35:13 +0000</pubDate>
|
<pubDate>Sun, 15 Mar 2026 23:32:02 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation</title>
|
<title>POLCA: Stochastic Generative Optimization with LLM</title>
|
||||||
<link>https://arxiv.org/abs/2603.12793</link>
|
<link>https://arxiv.org/abs/2603.14769</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Zhang, Da Peng, Zonghao Guo, Zijian Zhang, Xuesong Yang, Tong Sun, Shichu Sun, Yidan Zhang, Yanghao Li, Haiyan Zhao, Wang Xu, Qi Shi, Yangang Sun, Chi Chen, Shuo Wang, Yukun Yan, Xu Han, Qiang Ma, Wei Ke, Liang Wang, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> A recent cutting-edge topic in multimodal modeling is to unify visual comprehension and generation within a single model. However, the two tasks demand mismatched decoding regimes and visual representations, making it non-trivial to jointly optimize within a shared feature space. In this work, we present Cheers, a unified multimodal model that decouples patch-level details from semantic representations, thereby stabilizing semantics for multimodal understanding and improving fidelity for image generation via gated detail residuals. Cheers includes three key components: (i) a unified vision tokenizer that encodes and compresses image latent states into semantic tokens for efficient LLM conditioning, (ii) an LLM-based Transformer that unifies autoregressive decoding for text generation and diffusion decoding for image generation, and (iii) a cascaded flow matching head that decodes visual semantics first and then injects semantically gated detail residuals from the vision tokenizer to refine high-frequency content. Experiments on popular benchmarks demonstrate that Cheers matches or surpasses advanced UMMs in both visual understanding and generation. Cheers also achieves 4x token compression, enabling more efficient high-resolution image encoding and generation. Notably, Cheers outperforms the Tar-1.5B on the popular benchmarks GenEval and MMBench, while requiring only 20% of the training cost, indicating effective and efficient (i.e., 4x token compression) unified multimodal modeling. We will release all code and data for future research.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14769.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanfei Ren, Allen Nie, Tengyang Xie, Ching-An Cheng</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a generative language model acts as the optimizer, guided by numerical rewards and text feedback to discover the best system. We introduce Prioritized Optimization with Local Contextual Aggregation (POLCA), a scalable framework designed to handle stochasticity in optimization -- such as noisy feedback, sampling minibatches, and stochastic system behaviors -- while effectively managing the unconstrained expansion of solution space. POLCA maintains a priority queue to manage the exploration-exploitation tradeoff, systematically tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an varepsilon-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including τ-bench, HotpotQA (agent optimization), VeriBench (code translation) and KernelBench (CUDA kernel generation). Experimental results demonstrate that POLCA achieves robust, sample and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12793</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14769</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 08:55:27 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 03:07:44 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval</title>
|
<title>RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting</title>
|
||||||
<link>https://arxiv.org/abs/2603.12824</link>
|
<link>https://arxiv.org/abs/2603.14941</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12824.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuchenyang Liu, Yao Zhang, Yu Xiao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both document indexing and query encoding, incurring high latency and GPU dependence even for plain-text queries. We observe that this design is unnecessarily symmetric: documents are visually complex and demand strong visual understanding, whereas queries are just short text strings. NanoVDR exploits this query--document asymmetry by decoupling the two encoding paths: a frozen 2B VLM teacher indexes documents offline, while a distilled text-only student as small as 69M parameters encodes queries at inference. The key design choice is the distillation objective. Through systematic comparison of six objectives across three backbones and 22 ViDoRe benchmark datasets, we find that pointwise cosine alignment on query text consistently outperforms ranking-based and contrastive alternatives, while requiring only pre-cached teacher query embeddings and no document processing during training. Furthermore, we identify cross-lingual transfer as the primary performance bottleneck, and resolve it cheaply by augmenting training data with machine-translated queries. The resulting NanoVDR-S-Multi (DistilBERT, 69M) retains 95.1\% of teacher quality and outperforms DSE-Qwen2 (2B) on v2 and v3 with 32times fewer parameters and 50times lower CPU query latency, at a total training cost under 13 GPU-hours.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linrui Xu, Zhongan Wang, Fei Shen, Gang Xu, Huiping Zhuang, Ming Li, Haifeng Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Remote sensing world models aim to both explain observed changes and forecast plausible futures, two tasks that share spatiotemporal priors. Existing methods, however, typically address them separately, limiting cross-task transfer. We present RS-WorldModel, a unified world model for remote sensing that jointly handles spatiotemporal change understanding and text-guided future scene forecasting, and we build RSWBench-1.1M, a 1.1 million sample dataset with rich language annotations covering both tasks. RS-WorldModel is trained in three stages: (1) Geo-Aware Generative Pre-training (GAGP) conditions forecasting on geographic and acquisition metadata; (2) synergistic instruction tuning (SIT) jointly trains understanding and forecasting; (3) verifiable reinforcement optimization (VRO) refines outputs with verifiable, task-specific rewards. With only 2B parameters, RS-WorldModel surpasses open-source models up to 120 times larger on most spatiotemporal change question-answering metrics. It achieves an FID of 43.13 on text-guided future scene forecasting, outperforming all open-source baselines as well as the closed-source Gemini-2.5-Flash Image (Nano Banana).</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12824</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.14941</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 09:24:23 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 07:45:15 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection</title>
|
<title>Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching</title>
|
||||||
<link>https://arxiv.org/abs/2603.12916</link>
|
<link>https://arxiv.org/abs/2603.15016</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12916.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kadir-Kaan Özer, René Ebeling, Markus Enzweiler</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multivariate time series anomalies often manifest as shifts in cross-channel dependencies rather than simple amplitude excursions. In autonomous driving, for instance, a steering command might be internally consistent but decouple from the resulting lateral acceleration. Residual-based detectors can miss such anomalies when flexible sequence models still reconstruct signals plausibly despite altered coordination. We introduce AxonAD, an unsupervised detector that treats multi-head attention query evolution as a short horizon predictable process. A gradient-updated reconstruction pathway is coupled with a history-only predictor that forecasts future query vectors from past context. This is trained via a masked predictor-target objective against an exponential moving average (EMA) target encoder. At inference, reconstruction error is combined with a tail-aggregated query mismatch score, which measures cosine deviation between predicted and target queries on recent timesteps. This dual approach provides sensitivity to structural dependency shifts while retaining amplitude-level detection. On proprietary in-vehicle telemetry with interval annotations and on the TSB-AD multi-variate suite (17 datasets, 180 series) with threshold-free and range-aware metrics, AxonAD improves ranking quality and temporal localization over strong baselines. Ablations confirm that query prediction and combined scoring are the primary drivers of the observed gains. Code is available at the URL https://github.com/iis-esslingen/AxonAD.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15016.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangran Miao, Jian Huang, Ting Li</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Human motion generation is often learned in Euclidean spaces, although valid motions follow structured non-Euclidean geometry. We present Riemannian Motion Generation (RMG), a unified framework that represents motion on a product manifold and learns dynamics via Riemannian flow matching. RMG factorizes motion into several manifold factors, yielding a scale-free representation with intrinsic normalization, and uses geodesic interpolation, tangent-space supervision, and manifold-preserving ODE integration for training and sampling. On HumanML3D, RMG achieves state-of-the-art FID in the HumanML3D format (0.043) and ranks first on all reported metrics under the MotionStreamer format. On MotionMillion, it also surpasses strong baselines (FID 5.6, R@1 0.86). Ablations show that the compact T+R (translation + rotations) representation is the most stable and effective, highlighting geometry-aware modeling as a practical and scalable route to high-fidelity motion generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12916</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15016</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 11:40:51 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 09:19:10 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Can Fairness Be Prompted? Prompt-Based Debiasing Strategies in High-Stakes Recommendations</title>
|
<title>Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods</title>
|
||||||
<link>https://arxiv.org/abs/2603.12935</link>
|
<link>https://arxiv.org/abs/2603.15026</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12935.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mihaela Rotar, Theresia Veronika Rampisela, Maria Maistro</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods exist, they require access to the LLMs' weights, are computationally costly, and cannot be used by lay users. To address this gap, we investigate implicit biases in LLM Recommenders (LLMRecs) and explore whether prompt-based strategies can serve as a lightweight and easy-to-use debiasing approach. We contribute three bias-aware prompting strategies for LLMRecs. To our knowledge, this is the first study on prompt-based debiasing approaches in LLMRecs that focuses on group fairness for users. Our experiments with 3 LLMs, 4 prompt templates, 9 sensitive attribute values, and 2 datasets show that our proposed debiasing approach, which instructs an LLM to be fair, can improve fairness by up to 74% while retaining comparable effectiveness, but might overpromote specific demographic groups in some cases.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Ben Hayun, Roy Betser, Meir Yossef Levi, Levi Kassel, Guy Gilboa</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making reliable detection of synthetic videos increasingly crucial. Image-based detectors are fundamentally limited because they operate per frame and ignore temporal dynamics, while supervised video detectors generalize poorly to unseen generators, a critical drawback given the rapid emergence of new models. These challenges motivate zero-shot approaches, which avoid synthetic data and instead score content against real-data statistics, enabling training-free, model-agnostic detection. We introduce STALL, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework. We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models. STALL consistently outperforms prior image- and video-based baselines. Code and data are available at https://omerbenhayun.github.io/stall-video.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12935</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15026</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 12:30:42 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 09:26:56 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>daVinci-Env: Open SWE Environment Synthesis at Scale</title>
|
<title>Attention Residuals</title>
|
||||||
<link>https://arxiv.org/abs/2603.13023</link>
|
<link>https://arxiv.org/abs/2603.15031</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13023.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dayuan Fu, Shenyu Wu, Yunze Wu, Zerui Peng, Yaxing Huang, Jie Sun, Ji Zeng, Mohan Jiang, Lin Zhang, Yukun Li, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Liu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test execution, and solution refinement. However, existing open-source datasets remain limited in scale and repository diversity, while industrial solutions are opaque with unreleased infrastructure, creating a prohibitive barrier for most academic research groups. We present OpenSWE, the largest fully transparent framework for SWE agent training in Python, comprising 45,320 executable Docker environments spanning over 12.8k repositories, with all Dockerfiles, evaluation scripts, and infrastructure fully open-sourced for reproducibility. OpenSWE is built through a multi-agent synthesis pipeline deployed across a 64-node distributed cluster, automating repository exploration, Dockerfile construction, evaluation script generation, and iterative test analysis. Beyond scale, we propose a quality-centric filtering pipeline that characterizes the inherent difficulty of each environment, filtering out instances that are either unsolvable or insufficiently challenging and retaining only those that maximize learning efficiency. With 891K spent on environment construction and an additional 576K on trajectory sampling and difficulty-aware curation, the entire project represents a total investment of approximately $1.47 million, yielding about 13,000 curated trajectories from roughly 9,000 quality guaranteed environments. Extensive experiments validate OpenSWE's effectiveness: OpenSWE-32B and OpenSWE-72B achieve 62.4% and 66.0% on SWE-bench Verified, establishing SOTA among Qwen2.5 series. Moreover, SWE-focused training yields substantial out-of-domain improvements, including up to 12 points on mathematical reasoning and 5 points on science benchmarks, without degrading factual recall.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15031.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kimi Team, Guangyu Chen, Yu Zhang, Jianlin Su, Weixin Xu, Siyuan Pan, Yaoyu Wang, Yucheng Wang, Guanduo Chen, Bohong Yin, Yutian Chen, Junjie Yan, Ming Wei, Y. Zhang, Fanqing Meng, Chao Hong, Xiaotong Xie, Shaowei Liu, Enzhe Lu, Yunpeng Tai, Yanru Chen, Xin Men, Haiqing Guo, Y. Charles, Haoyu Lu, Lin Sui, Jinguo Zhu, Zaida Zhou, Weiran He, Weixiao Huang, Xinran Xu, Yuzhi Wang, Guokun Lai, Yulun Du, Yuxin Wu, Zhilin Yang, Xinyu Zhou</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights. This uniform aggregation causes uncontrolled hidden-state growth with depth, progressively diluting each layer's contribution. We propose Attention Residuals (AttnRes), which replaces this fixed accumulation with softmax attention over preceding layer outputs, allowing each layer to selectively aggregate earlier representations with learned, input-dependent weights. To address the memory and communication overhead of attending over all preceding layer outputs for large-scale model training, we introduce Block AttnRes, which partitions layers into blocks and attends over block-level representations, reducing the memory footprint while preserving most of the gains of full AttnRes. Combined with cache-based pipeline communication and a two-phase computation strategy, Block AttnRes becomes a practical drop-in replacement for standard residual connections with minimal overhead. Scaling law experiments confirm that the improvement is consistent across model sizes, and ablations validate the benefit of content-dependent depth-wise selection. We further integrate AttnRes into the Kimi Linear architecture (48B total / 3B activated parameters) and pre-train on 1.4T tokens, where AttnRes mitigates PreNorm dilution, yielding more uniform output magnitudes and gradient distribution across depth, and improves downstream performance across all evaluated tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13023</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15031</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 14:32:40 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 09:32:21 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Multimodal OCR: Parse Anything from Documents</title>
|
<title>SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation</title>
|
||||||
<link>https://arxiv.org/abs/2603.13032</link>
|
<link>https://arxiv.org/abs/2603.15150</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13032.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Handong Zheng, Yumeng Li, Kaile Zhang, Liang Xin, Guangwei Zhao, Hao Liu, Jiayu Chen, Jie Lou, Jiyu Qiu, Qi Fu, Rui Yang, Shuo Jiang, Weijian Luo, Weijie Su, Weijun Zhang, Xingyu Zhu, Yabin Li, Yiwei ma, Yu Chen, Zhaohui Yu, Guang Yang, Colin Zhang, Lei Zhang, Yuliang Liu, Xiang Bai</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped pixels, our method, termed dots.mocr, treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets, enabling systems to parse documents while preserving semantic relationships across elements. It offers several advantages: (1) it reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction; (2) it supports end-to-end training over heterogeneous document elements, allowing models to exploit semantic relations between textual and visual components; and (3) it converts previously discarded graphics into reusable code-level supervision, unlocking multimodal supervision embedded in existing documents. To make this paradigm practical at scale, we build a comprehensive data engine from PDFs, rendered webpages, and native SVG assets, and train a compact 3B-parameter model through staged pretraining and supervised fine-tuning. We evaluate dots.mocr from two perspectives: document parsing and structured graphics parsing. On document parsing benchmarks, it ranks second only to Gemini 3 Pro on our OCR Arena Elo leaderboard, surpasses existing open-source document parsing systems, and sets a new state of the art of 83.9 on olmOCR Bench. On structured graphics parsing, dots.mocr achieves higher reconstruction quality than Gemini 3 Pro across image-to-SVG benchmarks, demonstrating strong performance on charts, UI layouts, scientific figures, and chemical diagrams. These results show a scalable path toward building large-scale image-to-code corpora for multimodal pretraining. Code and models are publicly available at https://github.com/rednote-hilab/dots.mocr.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15150.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shufan Li, Jiuxiang Gu, Kangning Liu, Zhe Lin, Aditya Grover, Jason Kuen</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a large VQ codebook remains challenging, typically requiring larger model size and a longer training schedule. In this work, we propose Stochastic Neighbor Cross Entropy Minimization (SNCE), a novel training objective designed to address the optimization challenges of large-codebook discrete image generators. Instead of supervising the model with a hard one-hot target, SNCE constructs a soft categorical distribution over a set of neighboring tokens. The probability assigned to each token is proportional to the proximity between its code embedding and the ground-truth image embedding, encouraging the model to capture semantically meaningful geometric structure in the quantized embedding space. We conduct extensive experiments across class-conditional ImageNet-256 generation, large-scale text-to-image synthesis, and image editing tasks. Results show that SNCE significantly improves convergence speed and overall generation quality compared to standard cross-entropy objectives.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13032</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15150</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 14:42:21 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 11:44:11 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration</title>
|
<title>Efficient Document Parsing via Parallel Token Prediction</title>
|
||||||
<link>https://arxiv.org/abs/2603.13089</link>
|
<link>https://arxiv.org/abs/2603.15206</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13089.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenghe Zheng, Junpeng Jiang, Wenbo Li</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impressive generative capability, their potential as general-purpose visual learners remains largely untapped. In this work, we introduce V-Bridge, a framework that bridges this latent capacity to versatile few-shot image restoration tasks. We reinterpret image restoration not as a static regression problem, but as a progressive generative process, and leverage video models to simulate the gradual refinement from degraded inputs to high-fidelity outputs. Surprisingly, with only 1,000 multi-task training samples (less than 2% of existing restoration methods), pretrained video models can be induced to perform competitive image restoration, achieving multiple tasks with a single model, rivaling specialized architectures designed explicitly for this purpose. Our findings reveal that video generative models implicitly learn powerful and transferable restoration priors that can be activated with only extremely limited data, challenging the traditional boundary between generative modeling and low-level vision, and opening a new design paradigm for foundation models in visual tasks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15206.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Li, Ze Zhao, Meng Li, Zhongwang Lun, Yi Yuan, Xingjing Lu, Zheng Wei, Jiang Bian, Zang Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs creates a significant bottleneck, severely limiting parsing speed. In this paper, we propose Parallel-Token Prediction (PTP), a plugable, model-agnostic and simple-yet-effective method that enables VLMs to generate multiple future tokens in parallel with improved sample efficiency. Specifically, we insert some learnable tokens into the input sequence and design corresponding training objectives to equip the model with parallel decoding capabilities for document parsing. Furthermore, to support effective training, we develop a comprehensive data generation pipeline that efficiently produces large-scale, high-quality document parsing training data for VLMs. Extensive experiments on OmniDocBench and olmOCR-bench demonstrate that our method not only significantly improves decoding speed (1.6x-2.2x) but also reduces model hallucinations and exhibits strong generalization abilities.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13089</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15206</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 15:39:44 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 12:45:34 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Steve-Evolving: Open-World Embodied Self-Evolution via Fine-Grained Diagnosis and Dual-Track Knowledge Distillation</title>
|
<title>When Does Sparsity Mitigate the Curse of Depth in LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2603.13131</link>
|
<link>https://arxiv.org/abs/2603.15389</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13131.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengwei Xie, Zhisheng Chen, Ziyan Weng, Tingyu Wu, Chenglong Li, Vireo Zhang, Kun Wang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Open-world embodied agents must solve long-horizon tasks where the main bottleneck is not single-step planning quality but how interaction experience is organized and evolved. To this end, we present Steve-Evolving, a non-parametric self-evolving framework that tightly couples fine-grained execution diagnosis with dual-track knowledge distillation in a closed loop. The method follows three phases: Experience Anchoring, Experience Distillation, and Knowledge-Driven Closed-Loop Control. In detail, Experience Anchoring solidifies each subgoal attempt into a structured experience tuple with a fixed schema (pre-state, action, diagnosis-result, and post-state) and organizes it in a three-tier experience space with multi-dimensional indices (e.g., condition signatures, spatial hashing, and semantic tags) plus rolling summarization for efficient and auditable recall. To ensure sufficient information density for attribution, the execution layer provides compositional diagnosis signals beyond binary outcomes, including state-difference summaries, enumerated failure causes, continuous indicators, and stagnation/loop detection. Moreover, successful trajectories of Experience Distillation are generalized into reusable skills with explicit preconditions and verification criteria, while failures are distilled into executable guardrails that capture root causes and forbid risky operations at both subgoal and task granularities. Besides, Knowledge-Driven Closed-Loop Control retrieved skills and guardrails are injected into an LLM planner, and diagnosis-triggered local replanning updates the active constraints online, forming a continual evolution process without any model parameter updates. Experiments on the long-horizon suite of Minecraft MCU demonstrate consistent improvements over static-retrieval baselines.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15389.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dilxat Muhtar, Xinyuan Song, Sebastian Pokutta, Max Zimmer, Nico Pelleriti, Thomas Hofmann, Shiwei Liu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked to the accumulated growth of variance in Pre-Layer Normalization, which can push deep blocks toward near-identity behavior. In this paper, we demonstrate that, sparsity, beyond enabling efficiency, acts as a regulator of variance propagation and thereby improves depth utilization. Our investigation covers two sources of sparsity: (i) implicit sparsity, which emerges from training and data conditions, including weight sparsity induced by weight decay and attention sparsity induced by long context inputs; and (ii) explicit sparsity, which is enforced by architectural design, including key/value-sharing sparsity in Grouped-Query Attention and expert-activation sparsity in Mixtureof-Experts. Our claim is thoroughly supported by controlled depth-scaling experiments and targeted layer effectiveness interventions. Across settings, we observe a consistent relationship: sparsity improves layer utilization by reducing output variance and promoting functional differentiation. We eventually distill our findings into a practical rule-of-thumb recipe for training deptheffective LLMs, yielding a notable 4.6% accuracy improvement on downstream tasks. Our results reveal sparsity, arising naturally from standard design choices, as a key yet previously overlooked mechanism for effective depth scaling in LLMs. Code is available at https://github.com/pUmpKin-Co/SparsityAndCoD.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13131</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15389</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 16:23:34 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 15:04:16 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Visual-ERM: Reward Modeling for Visual Equivalence</title>
|
<title>ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer</title>
|
||||||
<link>https://arxiv.org/abs/2603.13224</link>
|
<link>https://arxiv.org/abs/2603.15478</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Liu, Shengyuan Ding, Xinyu Fang, Xuanlang Dai, Penghui Yang, Jianze Liang, Jiaqi Wang, Kai Chen, Dahua Lin, Yuhang Zang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs) achieve strong results via supervised fine-tuning, reinforcement learning remains challenging due to misaligned reward signals. Existing rewards either rely on textual rules or coarse visual embedding similarity, both of which fail to capture fine-grained visual discrepancies and are vulnerable to reward hacking. We propose Visual Equivalence Reward Model (Visual-ERM), a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback to evaluate vision-to-code quality directly in the rendered visual space. Integrated into RL, Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing (+2.7, +4.1 on average), and further strengthens test-time scaling via reflection and revision. We also introduce VisualCritic-RewardBench (VC-RewardBench), a benchmark for judging fine-grained image-to-image discrepancies on structured visual data, where Visual-ERM at 8B decisively outperforms Qwen3-VL-235B-Instruct and approaches leading closed-source models. Our results suggest that fine-grained visual reward supervision is both necessary and sufficient for vision-to-code RL, regardless of task specificity.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15478.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruonan Yu, Zhenxiong Tan, Zigeng Chen, Songhua Liu, Xinchao Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing tasks. However, compared to the image counterparts, progress in video control and editing remains limited, mainly due to the scarcity of paired video data and the high computational cost of training video diffusion models. To address this issue, in this paper, we propose a video-free tuning framework termed ViFeEdit for video diffusion transformers. Without requiring any forms of video training data, ViFeEdit achieves versatile video generation and editing, adapted solely with 2D images. At the core of our approach is an architectural reparameterization that decouples spatial independence from the full 3D attention in modern video diffusion transformers, which enables visually faithful editing while maintaining temporal consistency with only minimal additional parameters. Moreover, this design operates in a dual-path pipeline with separate timestep embeddings for noise scheduling, exhibiting strong adaptability to diverse conditioning signals. Extensive experiments demonstrate that our method delivers promising results of controllable video generation and editing with only minimal training on 2D image data. Codes are available https://github.com/Lexie-YU/ViFeEdit.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13224</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15478</guid>
|
||||||
<pubDate>Fri, 13 Mar 2026 17:58:14 +0000</pubDate>
|
<pubDate>Mon, 16 Mar 2026 16:10:46 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15500</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> LLMs often exhibit Aha moments during reasoning, such as apparent self-correction following tokens like "Wait," yet their underlying mechanisms remain unclear. We introduce an information-theoretic framework that decomposes reasoning into procedural information and epistemic verbalization - the explicit externalization of uncertainty that supports downstream control actions. We show that purely procedural reasoning can become informationally stagnant, whereas epistemic verbalization enables continued information acquisition and is critical for achieving information sufficiency. Empirical results demonstrate that strong reasoning performance is driven by uncertainty externalization rather than specific surface tokens. Our framework unifies prior findings on Aha moments and post-training experiments, and offers insights for future reasoning model design.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15500</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 16:31:24 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Learning Latent Proxies for Controllable Single-Image Relighting</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15555</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15555.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoze Zheng, Zihao Wang, Xianfeng Wu, Yajing Bai, Yexin Liu, Yun Li, Xiaogang Xu, Harry Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Single-image relighting is highly under-constrained: small illumination changes can produce large, nonlinear variations in shading, shadows, and specularities, while geometry and materials remain unobserved. Existing diffusion-based approaches either rely on intrinsic or G-buffer pipelines that require dense and fragile supervision, or operate purely in latent space without physical grounding, making fine-grained control of direction, intensity, and color unreliable. We observe that a full intrinsic decomposition is unnecessary and redundant for accurate relighting. Instead, sparse but physically meaningful cues, indicating where illumination should change and how materials should respond, are sufficient to guide a diffusion model. Based on this insight, we introduce LightCtrl that integrates physical priors at two levels: a few-shot latent proxy encoder that extracts compact material-geometry cues from limited PBR supervision, and a lighting-aware mask that identifies sensitive illumination regions and steers the denoiser toward shading relevant pixels. To compensate for scarce PBR data, we refine the proxy branch using a DPO-based objective that enforces physical consistency in the predicted cues. We also present ScaLight, a large-scale object-level dataset with systematically varied illumination and complete camera-light metadata, enabling physically consistent and controllable training. Across object and scene level benchmarks, our method achieves photometrically faithful relighting with accurate continuous control, surpassing prior diffusion and intrinsic-based baselines, including gains of up to +2.4 dB PSNR and 35% lower RMSE under controlled lighting shifts.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15555</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:16:59 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15557</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15557.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lexiang Xiong, Qi Li, Jingwen Ye, Xinchao Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this work, we propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition. Our framework is grounded in a normative principle of computational rationality, allowing us to model a VLM's generation as a dynamic cognitive trajectory. We design a suite of information-theoretic probes that project this trajectory onto an interpretable, low-dimensional Cognitive State Space. Our central discovery is a governing principle we term the geometric-information duality: a cognitive trajectory's geometric abnormality within this space is fundamentally equivalent to its high information-theoretic surprisal. Hallucination detection is counts as a geometric anomaly detection problem. Evaluated across diverse settings - from rigorous binary QA (POPE) and comprehensive reasoning (MME) to unconstrained open-ended captioning (MS-COCO) - our framework achieves state-of-the-art performance. Crucially, it operates with high efficiency under weak supervision and remains highly robust even when calibration data is heavily contaminated. This approach enables a causal attribution of failures, mapping observable errors to distinct pathological states: perceptual instability (measured by Perceptual Entropy), logical-causal failure (measured by Inferential Conflict), and decisional ambiguity (measured by Decision Entropy). Ultimately, this opens a path toward building AI systems whose reasoning is transparent, auditable, and diagnosable by design.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15557</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:20:38 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Panoramic Affordance Prediction</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15558</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixin Zhang, Chenfei Liao, Hongfei Zhang, Harold Haodong Chen, Kanghao Chen, Zichen Wen, Litao Guo, Bin Ren, Xu Zheng, Yinchuan Li, Xuming Hu, Nicu Sebe, Ying-Cong Chen</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Affordance prediction serves as a critical bridge between perception and action in embodied AI. However, existing research is confined to pinhole camera models, which suffer from narrow Fields of View (FoV) and fragmented observations, often missing critical holistic environmental context. In this paper, we present the first exploration into Panoramic Affordance Prediction, utilizing 360-degree imagery to capture global spatial relationships and holistic scene understanding. To facilitate this novel task, we first introduce PAP-12K, a large-scale benchmark dataset containing over 1,000 ultra-high-resolution (12k, 11904 x 5952) panoramic images with over 12k carefully annotated QA pairs and affordance masks. Furthermore, we propose PAP, a training-free, coarse-to-fine pipeline inspired by the human foveal visual system to tackle the ultra-high resolution and severe distortion inherent in panoramic images. PAP employs recursive visual routing via grid prompting to progressively locate targets, applies an adaptive gaze mechanism to rectify local geometric distortions, and utilizes a cascaded grounding pipeline to extract precise instance-level masks. Experimental results on PAP-12K reveal that existing affordance prediction methods designed for standard perspective images suffer severe performance degradation and fail due to the unique challenges of panoramic vision. In contrast, PAP framework effectively overcomes these obstacles, significantly outperforming state-of-the-art baselines and highlighting the immense potential of panoramic perception for robust embodied intelligence.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15558</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:21:49 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>The PokeAgent Challenge: Competitive and Long-Context Learning at Scale</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15563</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seth Karten, Jake Grigsby, Tersoo Upaa, Junik Bae, Seonghun Hong, Hyunyoung Jeong, Jaeyoon Jung, Kun Kerdthaisong, Gyungbo Kim, Hyeokgi Kim, Yujin Kim, Eunju Kwon, Dongyu Liu, Patrick Mariglia, Sangyeon Park, Benedikt Schink, Xianwei Shi, Anthony Sistilli, Joseph Twin, Arian Urdu, Matin Urdu, Qiao Wang, Ling Wu, Wenli Zhang, Kunsheng Zhou, Stephanie Milani, Kiran Vodrahalli, Amy Zhang, Fei Fang, Yuke Zhu, Chi Jin</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environment. Partial observability, game-theoretic reasoning, and long-horizon planning remain open problems for frontier AI, yet few benchmarks stress all three simultaneously under realistic conditions. PokeAgent targets these limitations at scale through two complementary tracks: our Battling Track, which calls for strategic reasoning and generalization under partial observability in competitive Pokemon battles, and our Speedrunning Track, which requires long-horizon planning and sequential decision-making in the Pokemon RPG. Our Battling Track supplies a dataset of 20M+ battle trajectories alongside a suite of heuristic, RL, and LLM-based baselines capable of high-level competitive play. Our Speedrunning Track provides the first standardized evaluation framework for RPG speedrunning, including an open-source multi-agent orchestration system for modular, reproducible comparisons of harness-based LLM approaches. Our NeurIPS 2025 competition validates both the quality of our resources and the research community's interest in Pokemon, with over 100 teams competing across both tracks and winning solutions detailed in our paper. Participant submissions and our baselines reveal considerable gaps between generalist (LLM), specialist (RL), and elite human performance. Analysis against the BenchPress evaluation matrix shows that Pokemon battling is nearly orthogonal to standard LLM benchmarks, measuring capabilities not captured by existing suites and positioning Pokemon as an unsolved benchmark that can drive RL and LLM research forward. We transition to a living benchmark with a live leaderboard for Battling and self-contained evaluation for Speedrunning at https://pokeagentchallenge.com.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15563</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:25:42 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Grounding World Simulation Models in a Real-World Metropolis</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15583</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15583.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyoung Seo, Hyunwook Choi, Minkyung Kwon, Jinhyeok Choi, Siyoon Jin, Gayoung Lee, Junho Kim, JoungBin Lee, Geonmo Gu, Dongyoon Han, Sangdoo Yun, Seungryong Kim, Jin-Hwa Kim</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existing methods in generating spatially faithful, temporally consistent, long-horizon videos grounded in actual urban environments over trajectories reaching hundreds of meters, while supporting diverse camera movements and text-prompted scenario variations.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15583</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:46:04 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Effective Distillation to Hybrid xLSTM Architectures</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15590</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied, Anamaria-Roberta Hartl, David Stap, Pieter-Jan Hoedt, Maximilian Beck, Sebastian Böck, Günter Klambauer, Sepp Hochreiter</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures. However, despite extensive research, such distilled models often fail to match the performance of their teacher LLMs on various downstream tasks. We set out the goal of lossless distillation, which we define in terms of tolerance-corrected Win-and-Tie rates between student and teacher on sets of tasks. To this end, we introduce an effective distillation pipeline for xLSTM-based students. We propose an additional merging stage, where individually linearized experts are combined into a single model. We show the effectiveness of this pipeline by distilling base and instruction-tuned models from the Llama, Qwen, and Olmo families. In many settings, our xLSTM-based students recover most of the teacher's performance, and even exceed it on some downstream tasks. Our contributions are an important step towards more energy-efficient and cost-effective replacements for transformer-based LLMs.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15590</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:49:04 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15594</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuwen Du, Rui Ye, Shuo Tang, Xinyu Zhu, Yijun Lu, Yuzhu Cai, Siheng Chen</p><p><b>Upvotes:</b> 125</p><p><b>Summary:</b> Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent, high-quality training data. This persistent data scarcity has fundamentally hindered the progress of the broader research community in developing and innovating within this domain. To bridge this gap, we introduce OpenSeeker, the first fully open-source search agent (i.e., model and data) that achieves frontier-level performance through two core technical innovations: (1) Fact-grounded scalable controllable QA synthesis, which reverse-engineers the web graph via topological expansion and entity obfuscation to generate complex, multi-hop reasoning tasks with controllable coverage and complexity. (2) Denoised trajectory synthesis, which employs a retrospective summarization mechanism to denoise the trajectory, therefore promoting the teacher LLMs to generate high-quality actions. Experimental results demonstrate that OpenSeeker, trained (a single training run) on only 11.7k synthesized samples, achieves state-of-the-art performance across multiple benchmarks including BrowseComp, BrowseComp-ZH, xbench-DeepSearch, and WideSearch. Notably, trained with simple SFT, OpenSeeker significantly outperforms the second-best fully open-source agent DeepDive (e.g., 29.5% v.s. 15.3% on BrowseComp), and even surpasses industrial competitors such as Tongyi DeepResearch (trained via extensive continual pre-training, SFT, and RL) on BrowseComp-ZH (48.4% v.s. 46.7%). We fully open-source the complete training dataset and the model weights to democratize frontier search agent research and foster a more transparent, collaborative ecosystem.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15594</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:52:04 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15611</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aozhe Wang, Yuchen Yan, Nan Zhou, Zhengxi Lu, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage, and static rewards fail to adapt as models improve. Recent self-play methods unify code and test generation in a single model, but face a inherent dilemma: white-box access leads to self-collusion where the model produces trivial tests for easy rewards, yet black-box restriction yields generic tests that miss implementation-specific bugs. We introduce Code-A1, an adversarial co-evolution framework that jointly optimizes a Code LLM and a Test LLM with opposing objectives. The Code LLM is rewarded for passing more tests, while the Test LLM is rewarded for exposing more defects. This architectural separation eliminates self-collusion risks and safely enables white-box test generation, where the Test LLM can inspect candidate code to craft targeted adversarial tests. We further introduce a Mistake Book mechanism for experience replay and a composite reward balancing test validity with adversarial difficulty. Experiments on Qwen2.5-Coder models demonstrate that Code-A1 achieves code generation performance matching or exceeding models trained on human-annotated tests, while significantly improving test generation capability.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15611</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:58:13 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15612</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15612.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yukang Cao, Haozhe Xie, Fangzhou Hong, Long Zhuo, Zhaoxi Chen, Liang Pan, Ziwei Liu</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> We present HSImul3R, a unified framework for simulation-ready 3D reconstruction of human-scene interactions (HSI) from casual captures, including sparse-view images and monocular videos. Existing methods suffer from a perception-simulation gap: visually plausible reconstructions often violate physical constraints, leading to instability in physics engines and failure in embodied AI applications. To bridge this gap, we introduce a physically-grounded bi-directional optimization pipeline that treats the physics simulator as an active supervisor to jointly refine human dynamics and scene geometry. In the forward direction, we employ Scene-targeted Reinforcement Learning to optimize human motion under dual supervision of motion fidelity and contact stability. In the reverse direction, we propose Direct Simulation Reward Optimization, which leverages simulation feedback on gravitational stability and interaction success to refine scene geometry. We further present HSIBench, a new benchmark with diverse objects and interaction scenarios. Extensive experiments demonstrate that HSImul3R produces the first stable, simulation-ready HSI reconstructions and can be directly deployed to real-world humanoid robots.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15612</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:58:33 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15614</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15614.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenghong Zhou, Xiaohang Zhan, Zhiqin Chen, Soo Ye Kim, Nanxuan Zhao, Haitian Zheng, Qing Liu, He Zhang, Zhe Lin, Yuqian Zhou, Jiebo Luo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent video diffusion models have made remarkable strides in visual quality, yet precise, fine-grained control remains a key bottleneck that limits practical customizability for content creation. For AI video creators, three forms of control are crucial: (i) scene composition, (ii) multi-view consistent subject customization, and (iii) camera-pose or object-motion adjustment. Existing methods typically handle these dimensions in isolation, with limited support for multi-view subject synthesis and identity preservation under arbitrary pose changes. This lack of a unified architecture makes it difficult to support versatile, jointly controllable video. We introduce Tri-Prompting, a unified framework and two-stage training paradigm that integrates scene composition, multi-view subject consistency, and motion control. Our approach leverages a dual-condition motion module driven by 3D tracking points for background scenes and downsampled RGB cues for foreground subjects. To ensure a balance between controllability and visual realism, we further propose an inference ControlNet scale schedule. Tri-Prompting supports novel workflows, including 3D-aware subject insertion into any scenes and manipulation of existing subjects in an image. Experimental results demonstrate that Tri-Prompting significantly outperforms specialized baselines such as Phantom and DaS in multi-view subject identity, 3D consistency, and motion accuracy.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15614</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:59:05 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15616</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15616.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xincheng Shuai, Ziye Li, Henghui Ding, Dacheng Tao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Generating accurate glyphs for visual text rendering is essential yet challenging. Existing methods typically enhance text rendering by training on a large amount of high-quality scene text images, but the limited coverage of glyph variations and excessive stylization often compromise glyph accuracy, especially for complex or out-of-domain characters. Some methods leverage reinforcement learning to alleviate this issue, yet their reward models usually depend on text recognition systems that are insensitive to fine-grained glyph errors, so images with incorrect glyphs may still receive high rewards. Inspired by Direct Preference Optimization (DPO), we propose GlyphPrinter, a preference-based text rendering method that eliminates reliance on explicit reward models. However, the standard DPO objective only models overall preference between two samples, which is insufficient for visual text rendering where glyph errors typically occur in localized regions. To address this issue, we construct the GlyphCorrector dataset with region-level glyph preference annotations and propose Region-Grouped DPO (R-GDPO), a region-based objective that optimizes inter- and intra-sample preferences over annotated regions, substantially enhancing glyph accuracy. Furthermore, we introduce Regional Reward Guidance, an inference strategy that samples from an optimal distribution with controllable glyph accuracy. Extensive experiments demonstrate that the proposed GlyphPrinter outperforms existing methods in glyph accuracy while maintaining a favorable balance between stylization and precision.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15616</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:59:31 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>HorizonMath: Measuring AI Progress Toward Mathematical Discovery with Automatic Verification</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15617</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15617.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Erik Y. Wang, Sumeet Motwani, James V. Roggeveen, Eliot Hodges, Dulhan Jayalath, Charles London, Kalyan Ramakrishnan, Flaviu Cipcigan, Philip Torr, Alessandro Abate</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientific reasoning, but whether they can perform novel research is still widely debated and underexplored. We introduce HorizonMath, a benchmark of over 100 predominantly unsolved problems spanning 8 domains in computational and applied mathematics, paired with an open-source evaluation framework for automated verification. Our benchmark targets a class of problems where discovery is hard, requiring meaningful mathematical insight, but verification is computationally efficient and simple. Because these solutions are unknown, HorizonMath is immune to data contamination, and most state-of-the-art models score near 0%. Existing research-level benchmarks instead rely on formal proof verification or manual review, both of which are expensive to scale. Using this platform, we find two problems for which GPT 5.4 Pro proposes solutions that improve on the best-known published results, representing potential novel contributions (pending expert review). We release HorizonMath as an open challenge and a growing community resource, where correct solutions to problems in the unsolved problem classes could constitute novel results in the mathematical literature.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15617</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:59:53 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Mixture-of-Depths Attention</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15619</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lianghui Zhu, Yuxin Fang, Bencheng Liao, Shijie Wang, Tianheng Cheng, Zilong Huang, Chen Chen, Lai Wei, Yutao Zeng, Ya Wang, Yi Lin, Yu Li, Xinggang Wang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making them harder to recover in deeper layers. We introduce mixture-of-depths attention (MoDA), a mechanism that allows each attention head to attend to sequence KV pairs at the current layer and depth KV pairs from preceding layers. We further describe a hardware-efficient algorithm for MoDA that resolves non-contiguous memory-access patterns, achieving 97.3% of FlashAttention-2's efficiency at a sequence length of 64K. Experiments on 1.5B-parameter models demonstrate that MoDA consistently outperforms strong baselines. Notably, it improves average perplexity by 0.2 across 10 validation benchmarks and increases average performance by 2.11% on 10 downstream tasks, with a negligible 3.7% FLOPs computational overhead. We also find that combining MoDA with post-norm yields better performance than using it with pre-norm. These results suggest that MoDA is a promising primitive for depth scaling. Code is released at https://github.com/hustvl/MoDA .</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15619</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:59:55 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Towards Generalizable Robotic Manipulation in Dynamic Environments</title>
|
||||||
|
<link>https://arxiv.org/abs/2603.15620</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heng Fang, Shangru Li, Shuhan Wang, Xuanyang Xi, Dingkang Liang, Xiang Bai</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap primarily stems from a scarcity of dynamic manipulation datasets and the reliance of mainstream VLAs on single-frame observations, restricting their spatiotemporal reasoning capabilities. To address this, we introduce DOMINO, a large-scale dataset and benchmark for generalizable dynamic manipulation, featuring 35 tasks with hierarchical complexities, over 110K expert trajectories, and a multi-dimensional evaluation suite. Through comprehensive experiments, we systematically evaluate existing VLAs on dynamic tasks, explore effective training strategies for dynamic awareness, and validate the generalizability of dynamic data. Furthermore, we propose PUMA, a dynamics-aware VLA architecture. By integrating scene-centric historical optical flow and specialized world queries to implicitly forecast object-centric future states, PUMA couples history-aware perception with short-horizon prediction. Results demonstrate that PUMA achieves state-of-the-art performance, yielding a 6.3% absolute improvement in success rate over baselines. Moreover, we show that training on dynamic data fosters robust spatiotemporal representations that transfer to static tasks. All code and data are available at https://github.com/H-EmbodVis/DOMINO.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.15620</guid>
|
||||||
|
<pubDate>Mon, 16 Mar 2026 17:59:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user