bot: update RSS feed
This commit is contained in:
github-actions[bot]
482
feed.xml
482
feed.xml
@@ -7,293 +7,363 @@
|
|||||||
<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>Fri, 17 Oct 2025 00:02:46 +0000</lastBuildDate>
|
<lastBuildDate>Sat, 18 Oct 2025 00:02:26 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs</title>
|
<title>When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA</title>
|
||||||
<link>https://arxiv.org/abs/2510.04767</link>
|
<link>https://arxiv.org/abs/2510.04849</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04767.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wonjun Kang, Kevin Galim, Seunghyuk Oh, Minjae Lee, Yuchen Zeng, Shuibai Zhang, Coleman Hooper, Yuezhou Hu, Hyung Il Koo, Nam Ik Cho, Kangwook Lee</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inference through parallel decoding. Despite this promise, the conditional independence assumption in dLLMs causes parallel decoding to ignore token dependencies, inevitably degrading generation quality when these dependencies are strong. However, existing works largely overlook these inherent challenges, and evaluations on standard benchmarks (e.g., math and coding) are not sufficient to capture the quality degradation caused by parallel decoding. To address this gap, we first provide an information-theoretic analysis of parallel decoding. We then conduct case studies on analytically tractable synthetic list operations from both data distribution and decoding strategy perspectives, offering quantitative insights that highlight the fundamental limitations of parallel decoding. Building on these insights, we propose ParallelBench, the first benchmark specifically designed for dLLMs, featuring realistic tasks that are trivial for humans and autoregressive LLMs yet exceptionally challenging for dLLMs under parallel decoding. Using ParallelBench, we systematically analyze both dLLMs and autoregressive LLMs, revealing that: (i) dLLMs under parallel decoding can suffer dramatic quality degradation in real-world scenarios, and (ii) current parallel decoding strategies struggle to adapt their degree of parallelism based on task difficulty, thus failing to achieve meaningful speedup without compromising quality. Our findings underscore the pressing need for innovative decoding methods that can overcome the current speed-quality trade-off. We release our benchmark to help accelerate the development of truly efficient dLLMs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elisei Rykov, Kseniia Petrushina, Maksim Savkin, Valerii Olisov, Artem Vazhentsev, Kseniia Titova, Alexander Panchenko, Vasily Konovalov, Julia Belikova</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Hallucination detection remains a fundamental challenge for the safe and reliable deployment of large language models (LLMs), especially in applications requiring factual accuracy. Existing hallucination benchmarks often operate at the sequence level and are limited to English, lacking the fine-grained, multilingual supervision needed for a comprehensive evaluation. In this work, we introduce PsiloQA, a large-scale, multilingual dataset annotated with span-level hallucinations across 14 languages. PsiloQA is constructed through an automated three-stage pipeline: generating question-answer pairs from Wikipedia using GPT-4o, eliciting potentially hallucinated answers from diverse LLMs in a no-context setting, and automatically annotating hallucinated spans using GPT-4o by comparing against golden answers and retrieved context. We evaluate a wide range of hallucination detection methods -- including uncertainty quantification, LLM-based tagging, and fine-tuned encoder models -- and show that encoder-based models achieve the strongest performance across languages. Furthermore, PsiloQA demonstrates effective cross-lingual generalization and supports robust knowledge transfer to other benchmarks, all while being significantly more cost-efficient than human-annotated datasets. Our dataset and results advance the development of scalable, fine-grained hallucination detection in multilingual settings.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04767</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.04849</guid>
|
||||||
<pubDate>Mon, 06 Oct 2025 12:41:31 +0000</pubDate>
|
<pubDate>Mon, 06 Oct 2025 14:36:30 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation</title>
|
<title>SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis</title>
|
||||||
<link>https://arxiv.org/abs/2510.07414</link>
|
<link>https://arxiv.org/abs/2510.06694</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mufei Li, Dongqi Fu, Limei Wang, Si Zhang, Hanqing Zeng, Kaan Sancak, Ruizhong Qiu, Haoyu Wang, Xiaoxin He, Xavier Bresson, Yinglong Xia, Chonglin Sun, Pan Li</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased retrieval and agentic workflows. We argue that haystack engineering is necessary to construct noisy long contexts that faithfully capture key real-world factors -- distraction from heterogeneous biased retrievers and cascading errors in agentic workflows -- to test models' long-context robustness. We instantiate it through HaystackCraft, a new NIAH benchmark built on the full English Wikipedia hyperlink network with multi-hop questions. HaystackCraft evaluates how heterogeneous retrieval strategies (e.g., sparse, dense, hybrid, and graph-based) affect distractor composition, haystack ordering, and downstream LLM performance. HaystackCraft further extends NIAH to dynamic, LLM-dependent settings that simulate agentic operations, where models refine queries, reflect on their past reasonings, and decide when to stop. Experiments with 15 long-context models show that (1) while stronger dense retrievers can introduce more challenging distractors, graph-based reranking simultaneously improves retrieval effectiveness and mitigates more harmful distractors; (2) in agentic tests, even advanced models like Gemini 2.5 Pro and GPT-5 suffer cascading failures from self-generated distractors or struggle to perform early stops. These results highlight persistent challenges in agentic long-context reasoning and establish HaystackCraft as a valuable testbed for future progress.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06694.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jipeng Lyu, Jiahua Dong, Yu-Xiong Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging due to the difficulty of capturing accurate deformations while maintaining computational efficiency. We propose SCas4D, a cascaded optimization framework that leverages structural patterns in 3D Gaussian Splatting for dynamic scenes. The key idea is that real-world deformations often exhibit hierarchical patterns, where groups of Gaussians share similar transformations. By progressively refining deformations from coarse part-level to fine point-level, SCas4D achieves convergence within 100 iterations per time frame and produces results comparable to existing methods with only one-twentieth of the training iterations. The approach also demonstrates effectiveness in self-supervised articulated object segmentation, novel view synthesis, and dense point tracking tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07414</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.06694</guid>
|
||||||
<pubDate>Wed, 08 Oct 2025 18:12:10 +0000</pubDate>
|
<pubDate>Wed, 08 Oct 2025 06:39:33 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving</title>
|
<title>Large Language Models Do NOT Really Know What They Don't Know</title>
|
||||||
<link>https://arxiv.org/abs/2510.07944</link>
|
<link>https://arxiv.org/abs/2510.09033</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07944.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianrui Zhang, Yichen Liu, Zilin Guo, Yuxin Guo, Jingcheng Ni, Chenjing Ding, Dan Xu, Lewei Lu, Zehuan Wu</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Generative models have been widely applied to world modeling for environment simulation and future state prediction. With advancements in autonomous driving, there is a growing demand not only for high-fidelity video generation under various controls, but also for producing diverse and meaningful information such as depth estimation. To address this, we propose CVD-STORM, a cross-view video diffusion model utilizing a spatial-temporal reconstruction Variational Autoencoder (VAE) that generates long-term, multi-view videos with 4D reconstruction capabilities under various control inputs. Our approach first fine-tunes the VAE with an auxiliary 4D reconstruction task, enhancing its ability to encode 3D structures and temporal dynamics. Subsequently, we integrate this VAE into the video diffusion process to significantly improve generation quality. Experimental results demonstrate that our model achieves substantial improvements in both FID and FVD metrics. Additionally, the jointly-trained Gaussian Splatting Decoder effectively reconstructs dynamic scenes, providing valuable geometric information for comprehensive scene understanding.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09033.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chi Seng Cheang, Hou Pong Chan, Wenxuan Zhang, Yang Deng</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent work suggests that large language models (LLMs) encode factuality signals in their internal representations, such as hidden states, attention weights, or token probabilities, implying that LLMs may "know what they don't know". However, LLMs can also produce factual errors by relying on shortcuts or spurious associations. These error are driven by the same training objective that encourage correct predictions, raising the question of whether internal computations can reliably distinguish between factual and hallucinated outputs. In this work, we conduct a mechanistic analysis of how LLMs internally process factual queries by comparing two types of hallucinations based on their reliance on subject information. We find that when hallucinations are associated with subject knowledge, LLMs employ the same internal recall process as for correct responses, leading to overlapping and indistinguishable hidden-state geometries. In contrast, hallucinations detached from subject knowledge produce distinct, clustered representations that make them detectable. These findings reveal a fundamental limitation: LLMs do not encode truthfulness in their internal states but only patterns of knowledge recall, demonstrating that "LLMs don't really know what they don't know".</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07944</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.09033</guid>
|
||||||
<pubDate>Thu, 09 Oct 2025 08:41:58 +0000</pubDate>
|
<pubDate>Fri, 10 Oct 2025 06:09:04 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Don't Throw Away Your Pretrained Model</title>
|
<title>RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2510.09913</link>
|
<link>https://arxiv.org/abs/2510.10390</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shangbin Feng, Wenhao Yu, Yike Wang, Hongming Zhang, Yulia Tsvetkov, Dong Yu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best of both worlds through model collaboration, where different models in the training pipeline collaborate and complement each other. Since LM responses feature interleaving skills that favor different models, we propose Switch Generation, where pretrained and aligned model versions take turns to ``speak'' in a response sequence. Specifically, we train a switcher LM by learning from outcomes of choosing different models to generate the next segment across diverse queries and contexts. At inference time, the switcher LM guides different model checkpoints to dynamically generate the next segment where their strengths are most needed. Extensive experiments with 8 model collaboration baselines and 18 datasets show that 1) model collaboration consistently outperforms individual models on 16 out of 18 tasks, and 2) Switch Generation further outperforms baselines by 12.9% on average. Further analysis reveals that Switch Generation discovers compositional skills to solve problems where individual models struggle and generalizes to unseen models and tasks, reusing and repurposing by-products in expensive model training pipelines that are otherwise discarded.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10390.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer, Virginia Smith, Mona T. Diab</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this setting, with refusal accuracy dropping below 50% on multi-document tasks, while exhibiting either dangerous overconfidence or overcaution. Static benchmarks fail to reliably evaluate this capability, as models exploit dataset-specific artifacts and memorize test instances. We introduce RefusalBench, a generative methodology that programmatically creates diagnostic test cases through controlled linguistic perturbation. Our framework employs 176 distinct perturbation strategies across six categories of informational uncertainty and three intensity levels. Evaluation of over 30 models uncovers systematic failure patterns: refusal comprises separable detection and categorization skills, and neither scale nor extended reasoning improves performance. We find that selective refusal is a trainable, alignment-sensitive capability, offering a clear path for improvement. We release two benchmarks -- RefusalBench-NQ (single document) and RefusalBench-GaRAGe (multi-document) -- and our complete generation framework to enable continued, dynamic evaluation of this critical capability.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09913</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.10390</guid>
|
||||||
<pubDate>Fri, 10 Oct 2025 23:12:20 +0000</pubDate>
|
<pubDate>Sun, 12 Oct 2025 00:53:42 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model</title>
|
<title>FML-bench: A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth</title>
|
||||||
<link>https://arxiv.org/abs/2510.10274</link>
|
<link>https://arxiv.org/abs/2510.10472</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10274.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinliang Zheng, Jianxiong Li, Zhihao Wang, Dongxiu Liu, Xirui Kang, Yuchun Feng, Yinan Zheng, Jiayin Zou, Yilun Chen, Jia Zeng, Ya-Qin Zhang, Jiangmiao Pang, Jingjing Liu, Tai Wang, Xianyuan Zhan</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich, diverse robotic data sources, we propose a novel Soft Prompt approach with minimally added parameters, by infusing prompt learning concepts into cross-embodiment robot learning and introducing separate sets of learnable embeddings for each distinct data source. These embeddings serve as embodiment-specific prompts, which in unity empower VLA models with effective exploitation of varying cross-embodiment features. Our new X-VLA, a neat flow-matching-based VLA architecture, relies exclusively on soft-prompted standard Transformer encoders, enjoying both scalability and simplicity. Evaluated across 6 simulations as well as 3 real-world robots, our 0.9B instantiation-X-VLA-0.9B simultaneously achieves SOTA performance over a sweep of benchmarks, demonstrating superior results on a wide axes of capabilities, from flexible dexterity to quick adaptation across embodiments, environments, and tasks. Website: https://thu-air-dream.github.io/X-VLA/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiran Zou, Hou Hei Lam, Wenhao Zhao, Yiming Tang, Tingting Chen, Samson Yu, Tianyi Zhang, Chang Liu, Xiangyang Ji, Dianbo Liu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models (LLMs) have sparked growing interest in automatic machine learning research agents. Among them, agents capable of autonomously proposing ideas and conducting machine learning experiments are particularly promising, as they maximize research automation and accelerate scientific progress by iteratively refining ideas based on experimental results. However, comprehensively evaluating such agents remains challenging. Existing benchmarks tend to overemphasize engineering aspects while neglecting academic rigor, creating barriers that obscure a clear assessment of an agent's scientific capabilities in machine learning research. They also suffer from limited task diversity, an overemphasis on application-oriented tasks over fundamental research problems, and limited scalability to realistic research settings. To address these limitations, we introduce FML-bench, a benchmark designed to evaluate automatic machine learning research agents on 8 diverse and fundamental machine learning research problems. It reduces coding burden, emphasizes fundamental problems rather than specific use cases, offers high task diversity, and is extensible to real-world machine learning GitHub repositories. Furthermore, we present a unified evaluation framework with five complementary metrics, designed to comprehensively assess agent performance on our benchmark. We evaluate state-of-the-art automatic research agents on FML-bench, and find that agents employing broad research exploration strategies outperform those focusing on narrow but deep exploration. These findings suggest that emphasizing the breadth of exploration may lead to more effective research outcomes than focusing solely on incremental refinement. Our benchmark is available at https://github.com/qrzou/FML-bench.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.10274</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.10472</guid>
|
||||||
<pubDate>Sat, 11 Oct 2025 16:20:17 +0000</pubDate>
|
<pubDate>Sun, 12 Oct 2025 06:41:05 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning</title>
|
<title>VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2510.10494</link>
|
<link>https://arxiv.org/abs/2510.10518</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10494.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Martina G. Vilas, Safoora Yousefi, Besmira Nushi, Eric Horvitz, Vidhisha Balachandran</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting productive paths can substantially reduce wasted computation and improve overall efficiency. We introduce Latent-Trajectory signals that characterize the temporal evolution of a model's internal representations during the generation of intermediate reasoning tokens. By measuring the overall change in latent representations between the start and end of reasoning, the change accumulated across intermediate steps, and the extent to which these changes advance toward the final state, we show that these signals predict solution accuracy more reliably than both cross-layer metrics and output-based confidence measures. When used to guide answer selection across multiple sampled generations, Latent-Trajectory signals make test-time scaling more effective and efficient than majority voting, reducing token usage by up to 70% while preserving and even improving accuracy by 2.6% on average. Moreover, these predictive signals often emerge early in the reasoning trace, enabling early selection and allocation of compute to the most promising candidates. Our findings contribute not only practical strategies for inference-time efficiency, but also a deeper interpretability perspective on how reasoning processes are represented and differentiated in latent space.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10518.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qunzhong Wang, Jie Liu, Jiajun Liang, Yilei Jiang, Yuanxing Zhang, Jinyuan Chen, Yaozhi Zheng, Xintao Wang, Pengfei Wan, Xiangyu Yue, Jiaheng Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer frames and causing loss of fine-grained details; and (2) all visual information is packed into the initial prompt, exacerbating hallucination and forgetting during chain-of-thought reasoning. To overcome these issues, we introduce VideoReward Thinker (VR-Thinker), a thinking-with-image framework that equips the RM with visual reasoning operations (e.g., select frame) and a configurable visual memory window. This allows the RM to actively acquire and update visual evidence within context limits, improving reasoning fidelity and reliability. We activate visual reasoning via a reinforcement fine-tuning pipeline: (i) Cold Start with curated visual chain-of-thought data to distill basic reasoning skills and operation formatting; (ii) select samples whose per-dimension and overall judgments are all correct, then conduct Rejection sampling Fine-Tuning on these high-quality traces to further enhance reasoning; and (iii) apply Group Relative Policy Optimization (GRPO) to strengthen reasoning. Our approach delivers state-of-the-art accuracy among open-source models on video preference benchmarks, especially for longer videos: a 7B VR-Thinker achieves 80.5% on VideoGen Reward, 82.3% on GenAI-Bench, and 75.6% on MJ-Bench-Video. These results validate the effectiveness and promise of thinking-with-image multimodal reward modeling.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.10494</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.10518</guid>
|
||||||
<pubDate>Sun, 12 Oct 2025 08:03:56 +0000</pubDate>
|
<pubDate>Sun, 12 Oct 2025 09:29:50 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search</title>
|
<title>AnyUp: Universal Feature Upsampling</title>
|
||||||
<link>https://arxiv.org/abs/2510.10581</link>
|
<link>https://arxiv.org/abs/2510.12764</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10581.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multi-agent systems powered by Large Language Models excel at complex tasks through coordinated collaboration, yet they face high failure rates in multi-turn deep search scenarios. Existing temporal attribution methods struggle to accurately diagnose root causes, particularly when errors propagate across multiple agents. Attempts to automate failure attribution by analyzing action sequences remain ineffective due to their inability to account for information dependencies that span agents. This paper identifies two core challenges: (i) distinguishing symptoms from root causes in multi-agent error propagation, and (ii) tracing information dependencies beyond temporal order. To address these issues, we introduce GraphTracer, a framework that redefines failure attribution through information flow analysis. GraphTracer constructs Information Dependency Graphs (IDGs) to explicitly capture how agents reference and build on prior outputs. It localizes root causes by tracing through these dependency structures instead of relying on temporal sequences. GraphTracer also uses graph-aware synthetic data generation to target critical nodes, creating realistic failure scenarios. Evaluations on the Who\&When benchmark and integration into production systems demonstrate that GraphTracer-8B achieves up to 18.18\% higher attribution accuracy compared to state-of-the-art models and enables 4.8\% to 14.2\% performance improvements in deployed multi-agent frameworks, establishing a robust solution for multi-agent system debugging.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12764.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona, Michael Oechsle, Federico Tombari, Bernt Schiele, Jan Eric Lenssen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an inference-time feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiments, AnyUp sets a new state of the art for upsampled features, generalizes to different feature types, and preserves feature semantics while being efficient and easy to apply to a wide range of downstream tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.10581</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.12764</guid>
|
||||||
<pubDate>Sun, 12 Oct 2025 12:55:42 +0000</pubDate>
|
<pubDate>Tue, 14 Oct 2025 17:45:17 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication</title>
|
<title>VLA-0: Building State-of-the-Art VLAs with Zero Modification</title>
|
||||||
<link>https://arxiv.org/abs/2510.10611</link>
|
<link>https://arxiv.org/abs/2510.13054</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heng Zhang, Yuling Shi, Xiaodong Gu, Zijian Zhang, Haochen You, Lubin Gan, Yilei Yuan, Jin Huang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) Ineffective group collaboration modeling, as they rely on pairwise edge representations in graph structures, limiting their ability to capture relationships among multiple agents; and (ii) Limited task-adaptiveness in communication topology design, leading to excessive communication cost for simple tasks and insufficient coordination for complex scenarios. These issues restrict the scalability and practical deployment of adaptive collaboration frameworks. To address these challenges, we propose HyperAgent, a hypergraph-based framework that optimizes communication topologies and effectively captures group collaboration patterns using direct hyperedge representations. Unlike edge-based approaches, HyperAgent uses hyperedges to link multiple agents within the same subtask and employs hypergraph convolutional layers to achieve one-step information aggregation in collaboration groups. Additionally, it incorporates a variational autoencoder framework with sparsity regularization to dynamically adjust hypergraph topologies based on task complexity. Experiments highlight the superiority of HyperAgent in both performance and efficiency. For instance, on GSM8K, HyperAgent achieves 95.07\% accuracy while reducing token consumption by 25.33\%, demonstrating the potential of hypergraph-based optimization for multi-agent communication.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13054.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ankit Goyal, Hugo Hadfield, Xuning Yang, Valts Blukis, Fabio Ramos</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Vision-Language-Action models (VLAs) hold immense promise for enabling generalist robot manipulation. However, the best way to build them remains an open question. Current approaches often add complexity, such as modifying the existing vocabulary of a Vision-Language Model (VLM) with action tokens or introducing special action heads. Curiously, the simplest strategy of representing actions directly as text has remained largely unexplored. This work introduces VLA-0 to investigate this idea. We find that VLA-0 is not only effective; it is surprisingly powerful. With the right design, VLA-0 outperforms more involved models. On LIBERO, a popular benchmark for evaluating VLAs, VLA-0 outperforms all existing methods trained on the same robotic data, including pi_0.5-KI, OpenVLA-OFT and SmolVLA. Furthermore, without large-scale robotics-specific training, it outperforms methods trained on large-scale robotic data, like pi_0.5-KI, pi_0, GR00T-N1 and MolmoAct. These findings also translate to the real world, where VLA-0 outperforms SmolVLA, a VLA model pre-trained on large-scale real data. This paper summarizes our unexpected findings and spells out the specific techniques required to unlock the high performance of this simple yet potent VLA design. Visual results, code, and trained models are provided here: https://vla0.github.io/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.10611</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13054</guid>
|
||||||
<pubDate>Sun, 12 Oct 2025 13:47:42 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 00:31:10 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training</title>
|
<title>RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems</title>
|
||||||
<link>https://arxiv.org/abs/2510.12831</link>
|
<link>https://arxiv.org/abs/2510.13910</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12831.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taicheng Guo, Hai Wang, ChaoChun Liu, Mohsen Golalikhani, Xin Chen, Xiangliang Zhang, Chandan K. Reddy</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multi-turn Text-to-SQL aims to translate a user's conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text translation task and follow a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs. We present MTSQL-R1, an agentic training framework for long-horizon multi-turn Text-to-SQL. We cast the task as a Markov Decision Process (MDP) in which an agent interacts with (i) a database for execution feedback and (ii) a persistent dialogue memory for coherence verification, performing an iterative propose to execute -> verify -> refine cycle until all checks pass. Experiments on COSQL and SPARC demonstrate that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing. Full recipes (including code, trained models, logs, reasoning trajectories, etc.) will be released after the internal review to contribute to community research.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13910.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingru Lin, Chen Zhang, Stephen Y. Liu, Haizhou Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retrieving external information. Recent work extends this paradigm through agentic RAG systems, where LLMs act as agents to iteratively plan, retrieve, and reason over complex queries. However, these systems still struggle with challenging multi-hop questions, and their intermediate reasoning capabilities remain underexplored. To address this, we propose RAGCap-Bench, a capability-oriented benchmark for fine-grained evaluation of intermediate tasks in agentic RAG workflows. We analyze outputs from state-of-the-art systems to identify common tasks and the core capabilities required for their execution, then construct a taxonomy of typical LLM errors to design targeted evaluation questions. Experiments show that "slow-thinking" models with stronger RAGCap performance achieve better end-to-end results, underscoring the benchmark's validity and the importance of enhancing these intermediate capabilities.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.12831</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13910</guid>
|
||||||
<pubDate>Sun, 12 Oct 2025 16:12:05 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 04:13:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model</title>
|
<title>Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference</title>
|
||||||
<link>https://arxiv.org/abs/2510.10921</link>
|
<link>https://arxiv.org/abs/2510.13161</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10921.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Ji Ao, Dawei Leng, Yuhui Yin</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often struggle to capture fine-grained details in object attributes, spatial relations, and linguistic expressions, with limited support for bilingual comprehension. To address these challenges, we introduce FG-CLIP 2, a bilingual vision-language model designed to advance fine-grained alignment for both English and Chinese. Our approach leverages rich fine-grained supervision, including region-text matching and long-caption modeling, alongside multiple discriminative objectives. We further introduce the Textual Intra-modal Contrastive (TIC) loss to better distinguish semantically similar captions. Trained on a carefully curated mixture of large-scale English and Chinese data, FG-CLIP 2 achieves powerful bilingual performance. To enable rigorous evaluation, we present a new benchmark for Chinese multimodal understanding, featuring long-caption retrieval and bounding box classification. Extensive experiments on 29 datasets across 8 tasks show that FG-CLIP 2 outperforms existing methods, achieving state-of-the-art results in both languages. We release the model, code, and benchmark to facilitate future research on bilingual fine-grained alignment.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13161.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikhil Bhendawade, Kumari Nishu, Arnav Kundu, Chris Bartels, Minsik Cho, Irina Belousova</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces additional latency overhead exacerbating the speed-accuracy tradeoff. Prior methods (Medusa, Hydra, EAGLE) partially reduce draft cost but either degrade acceptance or introduce overheads that limit scaling. We present Mirror Speculative Decoding (Mirror-SD), an inference algorithm that breaks the latency-acceptance tradeoff. Mirror-SD launches branch-complete rollouts from early-exit signals in parallel with the target model's suffix and explicitly maps computation across heterogeneous accelerators (GPU and NPU) to exploit cross-device parallelism. The draft speculates forward continuations for the target to verify, while the target simultaneously speculates correction paths for the draft, converting speculation into two complementary execution pipelines. To further cut draft latency without weakening acceptance semantics, we add speculative streaming so the draft emits multiple tokens per step. This dual strategy of parallel heterogeneous execution plus multi-token speculative streaming pushes speculative decoding toward its ideal regime of high acceptance with low overhead. On SpecBench with server-scale models from 14B to 66B parameters, Mirror-SD delivers consistent end-to-end gains, achieving 2.8x-5.8x wall-time speedups across diverse tasks and a 30% average relative improvement over the strongest baseline, EAGLE3.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.10921</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13161</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 02:32:07 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 05:22:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Evaluating Language Models' Evaluations of Games</title>
|
<title>Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms</title>
|
||||||
<link>https://arxiv.org/abs/2510.10930</link>
|
<link>https://arxiv.org/abs/2510.13913</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10930.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Katherine M. Collins, Cedegao E. Zhang, Graham Todd, Lance Ying, Mauricio Barba da Costa, Ryan Liu, Prafull Sharma, Adrian Weller, Ionatan Kuperwajs, Lionel Wong, Joshua B. Tenenbaum, Thomas L. Griffiths</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how models play games such as chess and Go. In this paper, we advocate for a new paradigm that assesses AI systems' evaluation of games. First, we introduce a formalism for evaluating such evaluations. We then leverage a large-scale dataset of over 100 novel board games and over 450 human judgments to compare evaluations produced by modern language and reasoning models against those of people and symbolic computational agents. We consider two kinds of evaluative queries: assessing the payoff (or fairness) and the funness of games. These queries span two dimensions relevant to the design of evaluations of AI evaluations: how complex a query is to compute and how difficult a query is to quantify. Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models. However, we observe a non-monotonic relationship: as models get closer to game-theoretic optimal, their fit to human data weakens. We also observe more "jaggedness" across models for assessing funness, in line with the greater difficulty of quantifying this query. Across queries and games, reasoning models show highly variable and unpredictable resource usage when assessing queries, pointing to the importance of imbuing more resource-rational meta-reasoning in language and reasoning models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shrey Pandit, Xuan-Phi Nguyen, Yifei Ming, Austin Xu, Jiayu Wang, Caiming Xiong, Shafiq Joty</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underlying language models are often not optimized for long-horizon reasoning and exploration. Prior work has proposed workflows for constructing instruction-tuning datasets, often leveraging knowledge graphs. However, such methods typically lack fine-grained control over difficulty and quality, yielding synthetic data that falls short of capturing the complexity required for long-horizon reasoning. Furthermore, many studies conflate data and training effects by comparing models trained under different optimization recipes, making it difficult to isolate and evaluate the effectiveness of the data itself. We introduce a two-pronged data synthesis pipeline that generates question - answer pairs by progressively increasing task complexity until a frontier baseline web agent fails. The baseline agent plays multiple roles in this process: attempting the questions, validating factuality, checking for alternative answers, and enforcing filtering. To evaluate the effectiveness of our synthesis methods, we adopt a controlled training setup based on distillation from strong web agents. Experiments across multiple web-based benchmarks show that our dataset - despite being smaller - enables the training of more effective web agents than existing datasets. In particular, our data exhibits twice the diversity in tool-use actions, allowing models trained on it to achieve stronger performance while avoiding repetitive tool-calling behaviors.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.10930</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13913</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 02:45:37 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 06:34:46 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Revisiting Model Interpolation for Efficient Reasoning</title>
|
<title>LLM-guided Hierarchical Retrieval</title>
|
||||||
<link>https://arxiv.org/abs/2510.10977</link>
|
<link>https://arxiv.org/abs/2510.13217</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.10977.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taiqiang Wu, Runming Yang, Tao Liu, Jiahao Wang, Ngai Wong</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically revisit the simplest merging method that interpolates two weights directly. Particularly, we observe that model interpolation follows a three-stage evolutionary paradigm with distinct behaviors on the reasoning trajectory. These dynamics provide a principled guide for navigating the performance-cost trade-off. Empirical results demonstrate that a strategically interpolated model surprisingly surpasses sophisticated model merging baselines on both efficiency and effectiveness. We further validate our findings with extensive ablation studies on model layers, modules, and decoding strategies. Ultimately, this work demystifies model interpolation and offers a practical framework for crafting models with precisely targeted reasoning capabilities. Code is available at https://github.com/wutaiqiang/MI{Github}.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13217.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nilesh Gupta, Wei-Cheng Chang, Ngot Bui, Cho-Jui Hsieh, Inderjit S. Dhillon</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Modern IR systems are increasingly tasked with answering complex, multi-faceted queries that require deep reasoning rather than simple keyword or semantic matching. While LLM-based IR has shown great promise, the prevailing retrieve-then-rerank paradigm inherits the limitations of embedding-based retrieval; parametric generative approaches are difficult to update with new information; and long-context methods that place the entire corpus in context are computationally infeasible for large document collections. To address these challenges, we introduce LATTICE, a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity by imposing a semantic tree structure on the corpus. Our approach consists of two stages: (1) an offline phase that organizes the corpus into a semantic hierarchy via either a bottom-up agglomerative strategy or a top-down divisive strategy using multi-level summaries and (2) an online traversal phase where a search LLM navigates this tree. A central challenge in such LLM-guided search is that the model's relevance judgments are noisy, context-dependent, and unaware of the hierarchy, making cross-branch and cross-level comparisons difficult. To overcome this, we propose a traversal algorithm that estimates calibrated latent relevance scores from local LLM outputs and aggregates them into a global path relevance metric. Our training-free framework achieves state-of-the-art zero-shot performance on the reasoning-intensive BRIGHT benchmark, demonstrating up to 9% improvement in Recall@100 and 5% in nDCG@10 over the next best zero-shot baseline. Furthermore, compared to the fine-tuned SOTA method DIVER-v2, LATTICE attains comparable results on BRIGHT subsets that use a static corpus for evaluation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.10977</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13217</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 03:30:01 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 07:05:17 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Stronger Together: On-Policy Reinforcement Learning for Collaborative LLMs</title>
|
<title>VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator</title>
|
||||||
<link>https://arxiv.org/abs/2510.11062</link>
|
<link>https://arxiv.org/abs/2510.13454</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujie Zhao, Lanxiang Hu, Yang Wang, Minmin Hou, Hao Zhang, Ke Ding, Jishen Zhao</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through role-based orchestration, while RL uses environmental rewards to learn stronger policies, such as GRPO-style optimization. However, applying on-policy RL to MAS remains underexplored and presents unique challenges. Algorithmically, standard GRPO grouping assumptions break down because prompts vary by role and by turn. System-wise, the training stack must support MAS-workflow rollouts and on-policy updates for both single-policy and multi-policy models. We propose AT-GRPO, which includes (i) an agent- and turn-wise grouped RL algorithm tailored to MAS and (ii) a training system that supports both single- and multi-policy regimes. Across game, planning, coding, and math tasks, AT-GRPO delivers substantial gains. On long-horizon planning, it increases accuracy from a 14.0 to 47.0 percent single-agent RL baseline to 96.0 to 99.5 percent. It also improves reasoning performance, with average gains of 3.87 to 7.62 percent on coding tasks and 9.0 to 17.93 percent on math. Code and environments are available at: https://github.com/pettingllms-ai/PettingLLMs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13454.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyojun Go, Dominik Narnhofer, Goutam Bhat, Prune Truong, Federico Tombari, Konrad Schindler</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The rapid progress of large, pretrained models for both visual content generation and 3D reconstruction opens up new possibilities for text-to-3D generation. Intuitively, one could obtain a formidable 3D scene generator if one were able to combine the power of a modern latent text-to-video model as "generator" with the geometric abilities of a recent (feedforward) 3D reconstruction system as "decoder". We introduce VIST3A, a general framework that does just that, addressing two main challenges. First, the two components must be joined in a way that preserves the rich knowledge encoded in their weights. We revisit model stitching, i.e., we identify the layer in the 3D decoder that best matches the latent representation produced by the text-to-video generator and stitch the two parts together. That operation requires only a small dataset and no labels. Second, the text-to-video generator must be aligned with the stitched 3D decoder, to ensure that the generated latents are decodable into consistent, perceptually convincing 3D scene geometry. To that end, we adapt direct reward finetuning, a popular technique for human preference alignment. We evaluate the proposed VIST3A approach with different video generators and 3D reconstruction models. All tested pairings markedly improve over prior text-to-3D models that output Gaussian splats. Moreover, by choosing a suitable 3D base model, VIST3A also enables high-quality text-to-pointmap generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11062</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13454</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 06:55:09 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 11:55:08 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling</title>
|
<title>LLMs Can Get "Brain Rot"!</title>
|
||||||
<link>https://arxiv.org/abs/2510.11170</link>
|
<link>https://arxiv.org/abs/2510.13928</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11170.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Scalena, Leonidas Zotos, Elisabetta Fersini, Malvina Nissim, Ahmet Üstün</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computation is often required to generate multiple candidate sequences from the same prompt. This enables exploration of different reasoning paths toward the correct solution, however, allocates the same compute budget for each prompt. Grounded on the assumption that different prompts carry different degrees of complexity, and thus different computation needs, we propose EAGer, a training-free generation method that leverages model uncertainty through token-wise entropy distribution to reduce redundant computation and concurrently improve overall performance. EAGer allows branching to multiple reasoning paths only in the presence of high-entropy tokens, and then reallocates the saved compute budget to the instances where exploration of alternative paths is most needed. We find that across multiple open-source models on complex reasoning benchmarks such as AIME 2025, EAGer can reallocate the budget without accessing target labels, achieving the best efficiency-performance trade-off in terms of reasoning length and Pass@k. When target labels are accessible, EAGer generates up to 65% fewer tokens (hence saving compute) and achieves up to 37% improvement in Pass@k compared to the Full Parallel Sampling.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13928.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo Xing, Junyuan Hong, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, Zhangyang Wang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We propose and test the LLM Brain Rot Hypothesis: continual exposure to junk web text induces lasting cognitive decline in large language models (LLMs). To causally isolate data quality, we run controlled experiments on real Twitter/X corpora, constructing junk and reversely controlled datasets via two orthogonal operationalizations: M1 (engagement degree) and M2 (semantic quality), with matched token scale and training operations across conditions. Contrary to the control group, continual pre-training of 4 LLMs on the junk dataset causes non-trivial declines (Hedges' g>0.3) on reasoning, long-context understanding, safety, and inflating "dark traits" (e.g., psychopathy, narcissism). The gradual mixtures of junk and control datasets also yield dose-response cognition decay: for example, under M1, ARC-Challenge with Chain Of Thoughts drops 74.9 rightarrow 57.2 and RULER-CWE 84.4 rightarrow 52.3 as junk ratio rises from 0% to 100%. Error forensics reveal several key insights. First, we identify thought-skipping as the primary lesion: models increasingly truncate or skip reasoning chains, explaining most of the error growth. Second, partial but incomplete healing is observed: scaling instruction tuning and clean data pre-training improve the declined cognition yet cannot restore baseline capability, suggesting persistent representational drift rather than format mismatch. Finally, we discover that the popularity, a non-semantic metric, of a tweet is a better indicator of the Brain Rot effect than the length in M1. Together, the results provide significant, multi-perspective evidence that data quality is a causal driver of LLM capability decay, reframing curation for continual pretraining as a training-time safety problem and motivating routine "cognitive health checks" for deployed LLMs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11170</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13928</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 09:04:28 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 13:28:49 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>What Generative Search Engines Like and How to Optimize Web Content Cooperatively</title>
|
<title>On Pretraining for Project-Level Code Completion</title>
|
||||||
<link>https://arxiv.org/abs/2510.11438</link>
|
<link>https://arxiv.org/abs/2510.13697</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11438.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujiang Wu, Shanshan Zhong, Yubin Kim, Chenyan Xiong</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> By employing large language models (LLMs) to retrieve documents and generate natural language responses, Generative Engines, such as Google AI overview and ChatGPT, provide significantly enhanced user experiences and have rapidly become the new form of search. Their rapid adoption also drives the needs of Generative Engine Optimization (GEO), as content providers are eager to gain more traction from them. In this paper, we introduce AutoGEO, a framework to automatically learn generative engine preferences when using retrieved contents for response generation, and rewrite web contents for more such traction. AutoGEO first prompts frontier LLMs to explain generative engine preferences and extract meaningful preference rules from these explanations. Then it uses preference rules as context engineering for AutoGEO_API, a prompt-based GEO system, and as rule-based rewards to train AutoGEO_Mini, a cost-effective GEO model. Experiments on the standard GEO-Bench and two newly constructed benchmarks using real user queries demonstrate the effectiveness of AutoGEO in enhancing content traction while preserving search utility. Analyses confirm the learned rules' robustness and abilities to capture unique preferences in variant domains, and AutoGEO systems' ability to embed them in content optimization. The code is released at https://github.com/cxcscmu/AutoGEO.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13697.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maksim Sapronov, Evgeniy Glukhov</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work, we investigate how different repository-processing strategies affect in-context learning in OpenCoder, a 1.5B-parameter model. We extend its context window from 4,096 to 16,384 tokens by training on additional 1B tokens of curated repository-level data. Despite relying on a smaller dataset than competing models (which often use hundreds of billions of tokens), our model achieves comparable performance on the Long Code Arena benchmark. We find that various repository-processing techniques yield similarly strong results, with the primary gain coming from adapting to a new rotary positional embedding (RoPE) scaling parameter. Finally, we show that a simpler file-level training approach at the original sequence length remains highly effective, opening up repository-level code completion research to settings with more constrained data and compute resources.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11438</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13697</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 14:10:26 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 15:55:19 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model</title>
|
<title>The German Commons - 154 Billion Tokens of Openly Licensed Text for German Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2510.11653</link>
|
<link>https://arxiv.org/abs/2510.13996</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prasanna Mayilvahanan, Ricardo Dominguez-Olmedo, Thaddäus Wiedemer, Wieland Brendel</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the open-source ecosystem reveals a critical limitation: with sufficiently many draws (e.g., pass@1024), many existing base models already solve nearly all questions on widely used math benchmarks such as MATH-500 and AIME 2024. This suggests that the RL fine-tuning methods prevalent in the LLM reasoning literature largely sharpen existing solution modes rather than discovering entirely new ones. Such sharpening stands in contrast to the broader promise of RL: to foster exploration and to acquire new skills. To move beyond this plateau, we introduce MATH-Beyond (MATH-B), a benchmark deliberately constructed to defeat common open-source models of up to 8B parameters even under large sampling budgets. Improving performance on our benchmark via RL requires methods that learn to reason in ways that go beyond base model capabilities in repeated sampling. Since the problems are drawn from subsets of DAPO-Math-17K and DeepScaleR datasets, they remain topically equivalent to standard high-school math. Validating our premise, RL fine-tuned models such as Nemotron-Research-Reasoning-Qwen-1.5B and DeepScaleR-1.5B-Preview perform poorly on MATH-B at pass@1024, showing how existing approaches fall short on tackling harder instances. We hope MATH-B will catalyze exploration-driven RL approaches that elicit deeper reasoning capabilities. We release MATH-B at https://huggingface.co/datasets/brendel-group/MATH-Beyond.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lukas Gienapp, Christopher Schröder, Stefan Schweter, Christopher Akiki, Ferdinand Schlatt, Arden Zimmermann, Phillipe Genêt, Martin Potthast</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language model development relies on large-scale training corpora, yet most contain data of unclear licensing status, limiting the development of truly open models. This problem is exacerbated for non-English languages, where openly licensed text remains critically scarce. We introduce the German Commons, the largest collection of openly licensed German text to date. It compiles data from 41 sources across seven domains, encompassing legal, scientific, cultural, political, news, economic, and web text. Through systematic sourcing from established data providers with verifiable licensing, it yields 154.56 billion tokens of high-quality text for language model training. Our processing pipeline implements comprehensive quality filtering, deduplication, and text formatting fixes, ensuring consistent quality across heterogeneous text sources. All domain subsets feature licenses of at least CC-BY-SA 4.0 or equivalent, ensuring legal compliance for model training and redistribution. The German Commons therefore addresses the critical gap in openly licensed German pretraining data, and enables the development of truly open German language models. We also release code for corpus construction and data filtering tailored to German language text, rendering the German Commons fully reproducible and extensible.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11653</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13996</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 17:30:54 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 18:24:26 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Point Prompting: Counterfactual Tracking with Video Diffusion Models</title>
|
<title>BitNet Distillation</title>
|
||||||
<link>https://arxiv.org/abs/2510.11715</link>
|
<link>https://arxiv.org/abs/2510.13998</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11715.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ayush Shrivastava, Sanyam Mehta, Daniel Geng, Andrew Owens</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Trackers and video generators solve closely related problems: the former analyze motion, while the latter synthesize it. We show that this connection enables pretrained video diffusion models to perform zero-shot point tracking by simply prompting them to visually mark points as they move over time. We place a distinctively colored marker at the query point, then regenerate the rest of the video from an intermediate noise level. This propagates the marker across frames, tracing the point's trajectory. To ensure that the marker remains visible in this counterfactual generation, despite such markers being unlikely in natural videos, we use the unedited initial frame as a negative prompt. Through experiments with multiple image-conditioned video diffusion models, we find that these "emergent" tracks outperform those of prior zero-shot methods and persist through occlusions, often obtaining performance that is competitive with specialized self-supervised models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13998.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xun Wu, Shaohan Huang, Wenhui Wang, Ting Song, Li Dong, Yan Xia, Furu Wei</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> In this paper, we present BitNet Distillation (BitDistill), a lightweight pipeline that fine-tunes off-the-shelf full-precision LLMs (e.g., Qwen) into 1.58-bit precision (i.e., ternary weights {-1, 0, 1}) for specific downstream tasks, achieving strong task-specific performance with minimal computational cost. Specifically, BitDistill incorporates three key techniques: the SubLN module, as introduced in BitNet; multi-head attention distillation, based on MiniLM; and continual pre-training, which serves as a crucial warm-up step to mitigate the scalability issue of the performance gap between finetuned full-precision and 1.58-bit LLMs on specific tasks. Experimental results show that BitDistill achieves performance comparable to the full-precision counterpart models across model size, while enabling up to 10x memory savings and 2.65x faster inference on CPUs. Code is available at https://github.com/microsoft/BitNet.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11715</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.13998</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 17:59:46 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 18:28:12 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Direct Multi-Token Decoding</title>
|
<title>Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2510.11958</link>
|
<link>https://arxiv.org/abs/2510.14095</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11958.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuan Luo, Weizhi Wang, Xifeng Yan</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs, early, middle, and late layers may serve distinct roles: Early layers focus on understanding the input context, middle layers handle task-specific processing, and late layers convert abstract representations into output tokens. We hypothesize that once representations have been processed by the early and middle layers, the resulting hidden states may encapsulate sufficient information to support the generation of multiple tokens using only the late layers, eliminating the need to repeatedly traverse the early and middle layers. We refer to this inference paradigm as Direct Multi-Token Decoding (DMTD). Unlike speculative decoding, our method introduces no additional parameters, auxiliary routines, or post-generation verification. Despite being trained on a limited dataset, a fine-tuned DMTD Qwen3-4B model has already demonstrated promising results, achieving up to a 2x speedup with only minor performance loss. Moreover, as shown in our scaling analysis, its performance is expected to further improve with larger training datasets.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14095.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Awni Altabaa, Siyu Chen, John Lafferty, Zhuoran Yang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Systematic, compositional generalization beyond the training distribution remains a core challenge in machine learning -- and a critical bottleneck for the emergent reasoning abilities of modern language models. This work investigates out-of-distribution (OOD) generalization in Transformer networks using a GSM8K-style modular arithmetic on computational graphs task as a testbed. We introduce and explore a set of four architectural mechanisms aimed at enhancing OOD generalization: (i) input-adaptive recurrence; (ii) algorithmic supervision; (iii) anchored latent representations via a discrete bottleneck; and (iv) an explicit error-correction mechanism. Collectively, these mechanisms yield an architectural approach for native and scalable latent space reasoning in Transformer networks with robust algorithmic generalization capabilities. We complement these empirical results with a detailed mechanistic interpretability analysis that reveals how these mechanisms give rise to robust OOD generalization abilities.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11958</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14095</guid>
|
||||||
<pubDate>Mon, 13 Oct 2025 21:42:37 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 21:03:59 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving</title>
|
<title>LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2510.12560</link>
|
<link>https://arxiv.org/abs/2510.14211</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12560.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoji Zheng, Ziyuan Yang, Yanhao Chen, Yuhang Peng, Yuanrong Tang, Gengyuan Liu, Bokui Chen, Jiangtao Gong</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> End-to-end autonomous driving models trained solely with imitation learning (IL) often suffer from poor generalization. In contrast, reinforcement learning (RL) promotes exploration through reward maximization but faces challenges such as sample inefficiency and unstable convergence. A natural solution is to combine IL and RL. Moving beyond the conventional two-stage paradigm (IL pretraining followed by RL fine-tuning), we propose CoIRL-AD, a competitive dual-policy framework that enables IL and RL agents to interact during training. CoIRL-AD introduces a competition-based mechanism that facilitates knowledge exchange while preventing gradient conflicts. Experiments on the nuScenes dataset show an 18% reduction in collision rate compared to baselines, along with stronger generalization and improved performance on long-tail scenarios. Code is available at: https://github.com/SEU-zxj/CoIRL-AD.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14211.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Beomseok Kang, Jiwon Song, Jae-Joon Kim</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Multi-stage reasoning has emerged as an effective strategy for enhancing the reasoning capability of small language models by decomposing complex problems into sequential sub-stages. However, this comes at the cost of increased latency. We observe that existing adaptive acceleration techniques, such as layer skipping, struggle to balance efficiency and accuracy in this setting due to two key challenges: (1) stage-wise variation in skip sensitivity, and (2) the generation of redundant output tokens. To address these, we propose LiteStage, a latency-aware layer skipping framework for multi-stage reasoning. LiteStage combines a stage-wise offline search that allocates optimal layer budgets with an online confidence-based generation early exit to suppress unnecessary decoding. Experiments on three benchmarks, e.g., OBQA, CSQA, and StrategyQA, show that LiteStage achieves up to 1.70x speedup with less than 4.0% accuracy loss, outperforming prior training-free layer skipping methods.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.12560</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14211</guid>
|
||||||
<pubDate>Tue, 14 Oct 2025 14:21:52 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 01:37:39 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Learning to Grasp Anything by Playing with Random Toys</title>
|
<title>LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild</title>
|
||||||
<link>https://arxiv.org/abs/2510.12866</link>
|
<link>https://arxiv.org/abs/2510.14240</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12866.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dantong Niu, Yuvan Sharma, Baifeng Shi, Rachel Ding, Matteo Gioia, Haoru Xue, Henry Tsai, Konstantinos Kallidromitis, Anirudh Pai, Shankar Shastry, Trevor Darrell, Jitendra Malik, Roei Herzig</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Robotic manipulation policies often struggle to generalize to novel objects, limiting their real-world utility. In contrast, cognitive science suggests that children develop generalizable dexterous manipulation skills by mastering a small set of simple toys and then applying that knowledge to more complex items. Inspired by this, we study if similar generalization capabilities can also be achieved by robots. Our results indicate robots can learn generalizable grasping using randomly assembled objects that are composed from just four shape primitives: spheres, cuboids, cylinders, and rings. We show that training on these "toys" enables robust generalization to real-world objects, yielding strong zero-shot performance. Crucially, we find the key to this generalization is an object-centric visual representation induced by our proposed detection pooling mechanism. Evaluated in both simulation and on physical robots, our model achieves a 67% real-world grasping success rate on the YCB dataset, outperforming state-of-the-art approaches that rely on substantially more in-domain data. We further study how zero-shot generalization performance scales by varying the number and diversity of training toys and the demonstrations per toy. We believe this work offers a promising path to scalable and generalizable learning in robotic manipulation. Demonstration videos, code, checkpoints and our dataset are available on our project page: https://lego-grasp.github.io/ .</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen, Austin Xu, Zixuan Ke, Frederic Sala, Aws Albarghouthi, Caiming Xiong, Shafiq Joty</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Deep research -- producing comprehensive, citation-grounded reports by searching and synthesizing information from hundreds of live web sources -- marks an important frontier for agentic systems. To rigorously evaluate this ability, four principles are essential: tasks should be (1) user-centric, reflecting realistic information needs, (2) dynamic, requiring up-to-date information beyond parametric knowledge, (3) unambiguous, ensuring consistent interpretation across users, and (4) multi-faceted and search-intensive, requiring search over numerous web sources and in-depth analysis. Existing benchmarks fall short of these principles, often focusing on narrow domains or posing ambiguous questions that hinder fair comparison. Guided by these principles, we introduce LiveResearchBench, a benchmark of 100 expert-curated tasks spanning daily life, enterprise, and academia, each requiring extensive, dynamic, real-time web search and synthesis. Built with over 1,500 hours of human labor, LiveResearchBench provides a rigorous basis for systematic evaluation. To evaluate citation-grounded long-form reports, we introduce DeepEval, a comprehensive suite covering both content- and report-level quality, including coverage, presentation, citation accuracy and association, consistency and depth of analysis. DeepEval integrates four complementary evaluation protocols, each designed to ensure stable assessment and high agreement with human judgments. Using LiveResearchBench and DeepEval, we conduct a comprehensive evaluation of 17 frontier deep research systems, including single-agent web search, single-agent deep research, and multi-agent systems. Our analysis reveals current strengths, recurring failure modes, and key system components needed to advance reliable, insightful deep research.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.12866</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14240</guid>
|
||||||
<pubDate>Tue, 14 Oct 2025 17:56:10 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 02:49:16 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain</title>
|
<title>MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems</title>
|
||||||
<link>https://arxiv.org/abs/2510.13255</link>
|
<link>https://arxiv.org/abs/2510.14252</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13255.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingmin An, Yilong Song, Ruolin Yang, Nai Ding, Lingxi Lu, Yuxuan Wang, Wei Wang, Chu Zhuang, Qian Wang, Fang Fang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) demonstrate human-level or even superior language abilities, effectively modeling syntactic structures, yet the specific computational modules responsible remain unclear. A key question is whether LLM behavioral capabilities stem from mechanisms akin to those in the human brain. To address these questions, we introduce the Hierarchical Frequency Tagging Probe (HFTP), a tool that utilizes frequency-domain analysis to identify neuron-wise components of LLMs (e.g., individual Multilayer Perceptron (MLP) neurons) and cortical regions (via intracranial recordings) encoding syntactic structures. Our results show that models such as GPT-2, Gemma, Gemma 2, Llama 2, Llama 3.1, and GLM-4 process syntax in analogous layers, while the human brain relies on distinct cortical regions for different syntactic levels. Representational similarity analysis reveals a stronger alignment between LLM representations and the left hemisphere of the brain (dominant in language processing). Notably, upgraded models exhibit divergent trends: Gemma 2 shows greater brain similarity than Gemma, while Llama 3.1 shows less alignment with the brain compared to Llama 2. These findings offer new insights into the interpretability of LLM behavioral improvements, raising questions about whether these advancements are driven by human-like or non-human-like mechanisms, and establish HFTP as a valuable tool bridging computational linguistics and cognitive neuroscience. This project is available at https://github.com/LilTiger/HFTP.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14252.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jihao Zhao, Zhiyuan Ji, Simin Niu, Hanyu Wang, Feiyu Xiong, Zhiyu Li</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge internalization and reasoning capabilities. To address this limitation, our research transforms the text processing in RAG from passive chunking to proactive understanding, defining this process as document memory extraction with the objective of simulating human cognitive processes during reading. Building upon this, we propose the Mixtures of scenario-aware document Memories (MoM) framework, engineered to efficiently handle documents from multiple domains and train small language models (SLMs) to acquire the ability to proactively explore and construct document memories. The MoM initially instructs large language models (LLMs) to simulate domain experts in generating document logical outlines, thereby directing structured chunking and core content extraction. It employs a multi-path sampling and multi-perspective evaluation mechanism, specifically designing comprehensive metrics that represent chunk clarity and extraction completeness to select the optimal document memories. Additionally, to infuse deeper human-like reading abilities during the training of SLMs, we incorporate a reverse reasoning strategy, which deduces refined expert thinking paths from high-quality outcomes. Finally, leveraging diverse forms of content generated by MoM, we develop a three-layer document memory retrieval mechanism, which is grounded in our theoretical proof from the perspective of probabilistic modeling. Extensive experimental results across three distinct domains demonstrate that the MoM framework not only resolves text chunking challenges in existing RAG systems, providing LLMs with semantically complete document memories, but also paves the way for SLMs to achieve human-centric intelligent text processing.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13255</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14252</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 08:04:49 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 03:09:51 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Universal Image Restoration Pre-training via Masked Degradation Classification</title>
|
<title>Qwen3Guard Technical Report</title>
|
||||||
<link>https://arxiv.org/abs/2510.13282</link>
|
<link>https://arxiv.org/abs/2510.14276</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13282.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> JiaKui Hu, Zhengjian Yao, Lujia Jin, Yinghao Chen, Yanye Lu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> This study introduces a Masked Degradation Classification Pre-Training method (MaskDCPT), designed to facilitate the classification of degradation types in input images, leading to comprehensive image restoration pre-training. Unlike conventional pre-training methods, MaskDCPT uses the degradation type of the image as an extremely weak supervision, while simultaneously leveraging the image reconstruction to enhance performance and robustness. MaskDCPT includes an encoder and two decoders: the encoder extracts features from the masked low-quality input image. The classification decoder uses these features to identify the degradation type, whereas the reconstruction decoder aims to reconstruct a corresponding high-quality image. This design allows the pre-training to benefit from both masked image modeling and contrastive learning, resulting in a generalized representation suited for restoration tasks. Benefit from the straightforward yet potent MaskDCPT, the pre-trained encoder can be used to address universal image restoration and achieve outstanding performance. Implementing MaskDCPT significantly improves performance for both convolution neural networks (CNNs) and Transformers, with a minimum increase in PSNR of 3.77 dB in the 5D all-in-one restoration task and a 34.8% reduction in PIQE compared to baseline in real-world degradation scenarios. It also emergences strong generalization to previously unseen degradation types and levels. In addition, we curate and release the UIR-2.5M dataset, which includes 2.5 million paired restoration samples across 19 degradation types and over 200 degradation levels, incorporating both synthetic and real-world data. The dataset, source code, and models are available at https://github.com/MILab-PKU/MaskDCPT.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiquan Zhao, Chenhan Yuan, Fei Huang, Xiaomeng Hu, Yichang Zhang, An Yang, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin, Baosong Yang, Chen Cheng, Jialong Tang, Jiandong Jiang, Jianwei Zhang, Jijie Xu, Ming Yan, Minmin Sun, Pei Zhang, Pengjun Xie, Qiaoyu Tang, Qin Zhu, Rong Zhang, Shibin Wu, Shuo Zhang, Tao He, Tianyi Tang, Tingyu Xia, Wei Liao, Weizhou Shen, Wenbiao Yin, Wenmeng Zhou, Wenyuan Yu, Xiaobin Wang, Xiaodong Deng, Xiaodong Xu, Xinyu Zhang, Yang Liu, Yeqiu Li, Yi Zhang, Yong Jiang, Yu Wan, Yuxin Zhou</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in static evaluation settings, face two major limitations in real-world applications: (1) they typically output only binary "safe/unsafe" labels, which can be interpreted inconsistently across diverse safety policies, rendering them incapable of accommodating varying safety tolerances across domains; and (2) they require complete model outputs before performing safety checks, making them fundamentally incompatible with streaming LLM inference, thereby preventing timely intervention during generation and increasing exposure to harmful partial outputs. To address these challenges, we present Qwen3Guard, a series of multilingual safety guardrail models with two specialized variants: Generative Qwen3Guard, which casts safety classification as an instruction-following task to enable fine-grained tri-class judgments (safe, controversial, unsafe); and Stream Qwen3Guard, which introduces a token-level classification head for real-time safety monitoring during incremental text generation. Both variants are available in three sizes (0.6B, 4B, and 8B parameters) and support up to 119 languages and dialects, providing comprehensive, scalable, and low-latency safety moderation for global LLM deployments. Evaluated across English, Chinese, and multilingual benchmarks, Qwen3Guard achieves state-of-the-art performance in both prompt and response safety classification. All models are released under the Apache 2.0 license for public use.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13282</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14276</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 08:30:15 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 04:00:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE</title>
|
<title>Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learning</title>
|
||||||
<link>https://arxiv.org/abs/2510.13344</link>
|
<link>https://arxiv.org/abs/2510.14300</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenyu Liu, Yunxin Li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Jinchao Li, Qi Wang, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with music and speech often developed in isolation, hindering progress towards universal audio synthesis. This separation stems from inherent task conflicts and severe data imbalances, which impede the development of a truly unified audio generation model. To address this challenge, we propose UniMoE-Audio, a unified speech and music generation model within a novel Dynamic-Capacity Mixture-of-Experts (MoE) framework. Architecturally, UniMoE-Audio introduces a Top-P routing strategy for dynamic expert number allocation, and a hybrid expert design comprising routed experts for domain-specific knowledge, shared experts for domain-agnostic features, and null experts for adaptive computation skipping. To tackle data imbalance, we introduce a three-stage training curriculum: 1) Independent Specialist Training leverages original datasets to instill domain-specific knowledge into each "proto-expert" without interference; 2) MoE Integration and Warmup incorporates these specialists into the UniMoE-Audio architecture, warming up the gate module and shared expert using a subset of balanced dataset; and 3) Synergistic Joint Training trains the entire model end-to-end on the fully balanced dataset, fostering enhanced cross-domain synergy. Extensive experiments show that UniMoE-Audio not only achieves state-of-the-art performance on major speech and music generation benchmarks, but also demonstrates superior synergistic learning, mitigating the performance degradation typically seen in naive joint training. Our findings highlight the substantial potential of specialized MoE architecture and curated training strategies in advancing the field of universal audio generation. Homepage: https://mukioxun.github.io/Uni-MoE-site/home.html</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Shen, Yitian Liu, Yuhao Wu, Zhixuan Liang, Sijia Gu, Dehui Wang, Tian Nian, Lei Xu, Yusen Qin, Jiangmiao Pang, Xinping Guan, Xiaokang Yang, Yao Mu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Vision-Language-Action (VLA) models are experiencing rapid development and demonstrating promising capabilities in robotic manipulation tasks. However, scaling up VLA models presents several critical challenges: (1) Training new VLA models from scratch demands substantial computational resources and extensive datasets. Given the current scarcity of robot data, it becomes particularly valuable to fully leverage well-pretrained VLA model weights during the scaling process. (2) Real-time control requires carefully balancing model capacity with computational efficiency. To address these challenges, We propose AdaMoE, a Mixture-of-Experts (MoE) architecture that inherits pretrained weights from dense VLA models, and scales up the action expert by substituting the feedforward layers into sparsely activated MoE layers. AdaMoE employs a decoupling technique that decouples expert selection from expert weighting through an independent scale adapter working alongside the traditional router. This enables experts to be selected based on task relevance while contributing with independently controlled weights, allowing collaborative expert utilization rather than winner-takes-all dynamics. Our approach demonstrates that expertise need not monopolize. Instead, through collaborative expert utilization, we can achieve superior performance while maintaining computational efficiency. AdaMoE consistently outperforms the baseline model across key benchmarks, delivering performance gains of 1.8% on LIBERO and 9.3% on RoboTwin. Most importantly, a substantial 21.5% improvement in real-world experiments validates its practical effectiveness for robotic manipulation tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13344</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14300</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 09:30:25 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 04:52:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning</title>
|
<title>Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts</title>
|
||||||
<link>https://arxiv.org/abs/2510.13515</link>
|
<link>https://arxiv.org/abs/2510.14351</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13515.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tiancheng Gu, Kaicheng Yang, Kaichen Zhang, Xiang An, Ziyong Feng, Yueyi Zhang, Weidong Cai, Jiankang Deng, Lidong Bing</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often struggle to capture subtle semantic differences among candidates and lack diversity in negative samples. Moreover, the embeddings exhibit limited discriminative ability in distinguishing false and hard negatives. In this paper, we leverage the advanced understanding capabilities of MLLMs to enhance representation learning and present a novel Universal Multimodal Embedding (UniME-V2) model. Our approach first constructs a potential hard negative set through global retrieval. We then introduce the MLLM-as-a-Judge mechanism, which utilizes MLLMs to assess the semantic alignment of query-candidate pairs and generate soft semantic matching scores. These scores serve as a foundation for hard negative mining, mitigating the impact of false negatives and enabling the identification of diverse, high-quality hard negatives. Furthermore, the semantic matching scores are used as soft labels to mitigate the rigid one-to-one mapping constraint. By aligning the similarity matrix with the soft semantic matching score matrix, the model learns semantic distinctions among candidates, significantly enhancing its discriminative capacity. To further improve performance, we propose UniME-V2-Reranker, a reranking model trained on our mined hard negatives through a joint pairwise and listwise optimization approach. We conduct comprehensive experiments on the MMEB benchmark and multiple retrieval tasks, demonstrating that our method achieves state-of-the-art performance on average across all tasks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14351.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Perapard Ngokpol, Kun Kerdthaisong, Pasin Buakhaw, Pitikorn Khlaisamniang, Supasate Vorathammathorn, Piyalitt Ittichaiwong, Nutchanon Yongsatianchot</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models (LLMs) are increasingly used as role-playing agents, yet their capacity to faithfully and consistently portray version-specific characters -- for example, superheroes across comic and cinematic universes -- remains underexplored. Superhero canons such as Marvel and DC provide a rich testbed: decades of storytelling yield multiple incarnations of the same character with distinct histories, values, and moral codes. To study this problem, we introduce Beyond One World, a benchmark for character-grounded roleplay spanning 30 iconic heroes and 90 canon-specific versions. The benchmark comprises two tasks: (i) Canon Events, which probes factual recall of pivotal life stages, and (ii) Moral Dilemmas, which confronts models with ethically charged scenarios. We score responses for canonical accuracy and reasoning fidelity under a framework that separates internal deliberation ("thinking") from outward decisions ("acting"). We further propose Think-Act Matching, a metric that quantifies alignment between reasons and actions and serves as a proxy for model trustworthiness. Experiments across reasoning- and non-reasoning-oriented models yield three findings: (1) chain-of-thought prompting improves narrative coherence in weaker models but can reduce canonical accuracy in stronger ones; (2) cross-version generalization within a character remains a major obstacle; and (3) models often excel at either thinking or acting, but rarely both. Beyond One World exposes critical gaps in multiversal consistency and reasoning alignment, offering a challenging evaluation for role-playing LLMs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13515</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14351</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 13:07:00 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 06:39:27 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization</title>
|
<title>AI for Service: Proactive Assistance with AI Glasses</title>
|
||||||
<link>https://arxiv.org/abs/2510.13554</link>
|
<link>https://arxiv.org/abs/2510.14359</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang, Shaopan Xiong, Yijia Luo, Jiashun Liu, Han Lu, Jiamang Wang, Wenbo Su, Bo Zheng, Junchi Yan</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work positions attention as a privileged substrate that renders the internal logic of LLMs legible, not merely as a byproduct of computation, but as a mechanistic blueprint of reasoning itself. We first distinguish attention heads between locally and globally focused information processing and reveal that locally focused heads produce a sawtooth pattern near the diagonal indicating phrasal chunks, while globally focused heads expose tokens that exert broad downstream influence over future tokens. We formalize these with two metrics: 1) Windowed Average Attention Distance, which measures the extent of backward attention within a clipped window; 2) Future Attention Influence, which quantifies a token's global importance as the average attention it receives from subsequent tokens. Taken together, these signals reveal a recurring preplan-and-anchor mechanism, where the model first performs a long-range contextual reference to generate an introductory token, which is immediately followed by or coincides with a semantic anchor token that organizes subsequent reasoning. Leveraging these insights, we introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes (preplan tokens, anchor tokens, and their temporal coupling) and show consistent performance gains across various reasoning tasks. By aligning optimization with the model's intrinsic reasoning rhythm, we aim to transform opaque optimization into an actionable structure-aware process, hoping to offer a potential step toward more transparent and effective optimization of LLM reasoning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14359.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichen Wen, Yiyu Wang, Chenfei Liao, Boxue Yang, Junxian Li, Weifeng Liu, Haocong He, Bolong Feng, Xuyang Liu, Yuanhuiyi Lyu, Xu Zheng, Xuming Hu, Linfeng Zhang</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-time assistance in daily life. Existing AI services remain largely reactive, responding only to explicit user commands. We argue that a truly intelligent and helpful assistant should be capable of anticipating user needs and taking actions proactively when appropriate. To realize this vision, we propose Alpha-Service, a unified framework that addresses two fundamental challenges: Know When to intervene by detecting service opportunities from egocentric video streams, and Know How to provide both generalized and personalized services. Inspired by the von Neumann computer architecture and based on AI glasses, Alpha-Service consists of five key components: an Input Unit for perception, a Central Processing Unit for task scheduling, an Arithmetic Logic Unit for tool utilization, a Memory Unit for long-term personalization, and an Output Unit for natural human interaction. As an initial exploration, we implement Alpha-Service through a multi-agent system deployed on AI glasses. Case studies, including a real-time Blackjack advisor, a museum tour guide, and a shopping fit assistant, demonstrate its ability to seamlessly perceive the environment, infer user intent, and provide timely and useful assistance without explicit prompts.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13554</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14359</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 13:49:51 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 06:55:28 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs</title>
|
<title>PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model</title>
|
||||||
<link>https://arxiv.org/abs/2510.13586</link>
|
<link>https://arxiv.org/abs/2510.14528</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13586.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pasin Buakhaw, Kun Kerdthaisong, Phuree Phenhiran, Pitikorn Khlaisamniang, Supasate Vorathammathorn, Piyalitt Ittichaiwong, Nutchanon Yongsatianchot</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The emergence of large language models (LLMs) has opened new opportunities for cre- ating dynamic non-player characters (NPCs) in gaming environments, enabling both func- tional task execution and persona-consistent dialogue generation. In this paper, we (Tu_Character_lab) report our participation in the Commonsense Persona-Grounded Dialogue Challenge (CPDC) 2025 Round 2, which eval- uates agents across three tracks: task-oriented dialogue, context-aware dialogue, and their integration. Our approach combines two complementary strategies: (i) lightweight prompting techniques in the API track, including a Deflanderization prompting method to suppress excessive role-play and improve task fidelity, and (ii) fine-tuned large models in the GPU track, leveraging Qwen3-14B with supervisedfinetuning (SFT) and Low-Rank Adaptation(LoRA). Our best submissions ranked 2nd on Task 1, 2nd on Task 3 (API track), and 4th on Task 3 (GPU track).</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Cui, Ting Sun, Suyin Liang, Tingquan Gao, Zelun Zhang, Jiaxuan Liu, Xueqing Wang, Changda Zhou, Hongen Liu, Manhui Lin, Yue Zhang, Yubo Zhang, Handong Zheng, Jing Zhang, Jun Zhang, Yi Liu, Dianhai Yu, Yanjun Ma</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> In this report, we propose PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13586</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14528</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 14:17:23 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 10:18:48 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>NOSA: Native and Offloadable Sparse Attention</title>
|
<title>Agentic Entropy-Balanced Policy Optimization</title>
|
||||||
<link>https://arxiv.org/abs/2510.13602</link>
|
<link>https://arxiv.org/abs/2510.14545</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13602.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Huang, Chaojun Xiao, Xu Han, Zhiyuan Liu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Trainable sparse attention has emerged as a promising solution to address the decoding efficiency bottleneck of LLMs in long-context processing, significantly saving memory accesses while minimally impacting task performance. However, existing sparse attention methods leave a crucial limitation unresolved: the size of the key-value (KV) cache remains unreduced, which constrains on-GPU batch sizes and throttles decoding throughput, especially in large-scale batched inference. In this paper, we show that trainable sparse attention naturally exhibits strong locality in token selection across adjacent decoding steps, thereby enabling KV cache offloading without altering the underlying attention computation. However, the inherent locality remains insufficient to achieve efficient offloading, as the transfer of selected KV pairs between the CPU and GPU continues to dominate the overall decoding cost. Building on this insight, we present NOSA, a trainable sparse attention framework designed to natively support KV cache offloading. NOSA introduces explicit locality constraints by decomposing token selection into query-aware and query-agnostic components, thereby reducing KV transfers while preserving the same attention computation as used during training. We pretrain a 1B-parameter model with NOSA and conduct extensive benchmarks, showing that it preserves near-lossless performance while achieving up to a 2.3x improvement in decoding throughput compared with the vanilla trainable sparse attention baseline (InfLLM-V2).</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14545.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao, Xiaoxi Li, Jiajie Jin, Jinghan Yang, Hangyu Mao, Fuzheng Zhang, Kun Gai, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Recently, Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents. While mainstream agentic RL algorithms autonomously explore high-uncertainty tool-call steps under the guidance of entropy, excessive reliance on entropy signals can impose further constraints, leading to the training collapse. In this paper, we delve into the challenges caused by entropy and propose the Agentic Entropy-Balanced Policy Optimization (AEPO), an agentic RL algorithm designed to balance entropy in both the rollout and policy update phases. AEPO comprises two core components: (1) a dynamic entropy-balanced rollout mechanism that adaptively allocate global and branch sampling budget through entropy pre-monitoring, while imposing a branch penalty on consecutive high-entropy tool-call steps to prevent over-branching issues; and (2) Entropy-Balanced Policy Optimization that inserts a stop-gradient operation into the high-entropy clipping term to preserve and properly rescale gradients on high-entropy tokens, while incorporating entropy-aware advantage estimation to prioritize learning on high-uncertainty tokens. Results across 14 challenging datasets show that AEPO consistently outperforms 7 mainstream RL algorithms. With just 1K RL samples, Qwen3-14B with AEPO achieves impressive results: 47.6% on GAIA, 11.2% on Humanity's Last Exam, and 43.0% on WebWalker for Pass@1; 65.0% on GAIA, 26.0% on Humanity's Last Exam, and 70.0% on WebWalker for Pass@5. Further analysis reveals that AEPO improves rollout sampling diversity while maintaining stable policy entropy, facilitating scalable web agent training.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13602</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14545</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 14:33:16 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 10:40:52 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The Role of Computing Resources in Publishing Foundation Model Research</title>
|
<title>Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures</title>
|
||||||
<link>https://arxiv.org/abs/2510.13621</link>
|
<link>https://arxiv.org/abs/2510.14616</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13621.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuexing Hao, Yue Huang, Haoran Zhang, Chenyang Zhao, Zhenwen Liang, Paul Pu Liang, Yue Zhao, Lichao Sun, Saleh Kalantari, Xiangliang Zhang, Marzyeh Ghassemi</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Cutting-edge research in Artificial Intelligence (AI) requires considerable resources, including Graphics Processing Units (GPUs), data, and human resources. In this paper, we evaluate of the relationship between these resources and the scientific advancement of foundation models (FM). We reviewed 6517 FM papers published between 2022 to 2024, and surveyed 229 first-authors to the impact of computing resources on scientific output. We find that increased computing is correlated with national funding allocations and citations, but our findings don't observe the strong correlations with research environment (academic or industrial), domain, or study methodology. We advise that individuals and institutions focus on creating shared and affordable computing opportunities to lower the entry barrier for under-resourced researchers. These steps can help expand participation in FM research, foster diversity of ideas and contributors, and sustain innovation and progress in AI. The data will be available at: https://mit-calc.csail.mit.edu/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14616.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuangshuang Ying, Yunwen Li, Xingwei Qu, Xin Li, Sheng Jin, Minghao Liu, Zhoufutu Wen, Xeron Du, Tianyu Zheng, Yichi Zhang, Letian Ni, Yuyang Cheng, Qiguang Chen, Jingzhe Ding, Shengda Long, Wangchunshu Zhou, Jiazhan Feng, Wanjun Zhong, Libo Qin, Ge Zhang, Wenhao Huang, Wanxiang Che, Chenghua Lin</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Current preference learning methods achieve high accuracy on standard benchmarks but exhibit significant performance degradation when objective quality signals are removed. We introduce WritingPreferenceBench, a dataset of 1,800 human-annotated preference pairs (1,200 English, 600 Chinese) across 8 creative writing genres, where responses are matched for objective correctness, factual accuracy, and length. On this benchmark, sequence-based reward models--the standard architecture for RLHF--achieve only 52.7% mean accuracy, while zero-shot language model judges perform at 53.9%. In contrast, generative reward models that produce explicit reasoning chains achieve 81.8% accuracy. We observe high within-model variance across genres: individual models range from 18.2% to 81.8% accuracy across different writing categories, with standard deviations averaging 10.1%. This variance persists regardless of model scale, with 27B parameter models showing no consistent improvement over 8B variants. Our results suggest that current RLHF methods primarily learn to detect objective errors rather than capture subjective quality preferences (e.g., creativity, stylistic flair, and emotional resonance), and that successful preference modeling may require intermediate reasoning representations rather than direct classification.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13621</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14616</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 14:50:45 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 12:23:13 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models</title>
|
<title>COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes</title>
|
||||||
<link>https://arxiv.org/abs/2510.13626</link>
|
<link>https://arxiv.org/abs/2510.14763</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13626.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Senyu Fei, Siyin Wang, Junhao Shi, Zihao Dai, Jikun Cai, Pengfang Qian, Li Ji, Xinzhe He, Shiduo Zhang, Zhaoye Fei, Jinlan Fu, Jingjing Gong, Xipeng Qiu</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform a systematic vulnerability analysis by introducing controlled perturbations across seven dimensions: objects layout, camera viewpoints, robot initial states, language instructions, light conditions, background textures and sensor noise. We comprehensively analyzed multiple state-of-the-art models and revealed consistent brittleness beneath apparent competence. Our analysis exposes critical weaknesses: models exhibit extreme sensitivity to perturbation factors, including camera viewpoints and robot initial states, with performance dropping from 95% to below 30% under modest perturbations. Surprisingly, models are largely insensitive to language variations, with further experiments revealing that models tend to ignore language instructions completely. Our findings challenge the assumption that high benchmark scores equate to true competency and highlight the need for evaluation practices that assess reliability under realistic variation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunwen Li, Shuangshuang Ying, Xingwei Qu, Xin Li, Sheng Jin, Minghao Liu, Zhoufutu Wen, Tianyu Zheng, Xeron Du, Qiguang Chen, Jiajun Shi, Wangchunshu Zhou, Jiazhan Feng, Wanjun Zhong, Libo Qin, Stephen Huang, Wanxiang Che, Chenghua Lin, Eli Zhang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large language models exhibit systematic deficiencies in creative writing, particularly in non-English contexts where training data is scarce and lacks process-level supervision. We present COIG-Writer, a novel Chinese creative writing dataset that captures both diverse outputs and their underlying thought processes through systematic reverse-engineering of high-quality texts. Unlike existing datasets that provide only input-output pairs, COIG-Writer comprises 1,665 meticulously curated triplets spanning 51 genres, each containing: (1) a reverse-engineered prompt, (2) detailed creative reasoning documenting decision-making processes, and (3) the final text. Through comprehensive experiments, we identify a two-component model of creative writing: narrative logic (provided by process supervision) and linguistic expression (maintained by general-purpose data). Our findings reveal three critical insights: (1) Process supervision is highly effective but requires stabilization with general data. A ratio of at least one creative sample to twelve general samples is needed to achieve optimal performance; below this threshold, the win rate progressively degrades (from 62.75% down to 35.78%)., (2) creative capabilities are culturally-bound with no cross-lingual transfer (89.26pp gap between Chinese and English performance), and (3) lexical diversity inversely correlates with creative quality (TTR paradox), suggesting high diversity signals compensatory behavior for logical deficiencies. These findings establish that creative excellence emerges from the interaction between logical scaffolding and linguistic grounding, analogous to how mathematical reasoning enhances but cannot replace linguistic competence in foundation models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13626</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14763</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 14:51:36 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 15:01:19 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FlashWorld: High-quality 3D Scene Generation within Seconds</title>
|
<title>SimKO: Simple Pass@K Policy Optimization</title>
|
||||||
<link>https://arxiv.org/abs/2510.13678</link>
|
<link>https://arxiv.org/abs/2510.14807</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyang Li, Tengfei Wang, Zixiao Gu, Shengchuan Zhang, Chunchao Guo, Liujuan Cao</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> We propose FlashWorld, a generative model that produces 3D scenes from a single image or text prompt in seconds, 10~100times faster than previous works while possessing superior rendering quality. Our approach shifts from the conventional multi-view-oriented (MV-oriented) paradigm, which generates multi-view images for subsequent 3D reconstruction, to a 3D-oriented approach where the model directly produces 3D Gaussian representations during multi-view generation. While ensuring 3D consistency, 3D-oriented method typically suffers poor visual quality. FlashWorld includes a dual-mode pre-training phase followed by a cross-mode post-training phase, effectively integrating the strengths of both paradigms. Specifically, leveraging the prior from a video diffusion model, we first pre-train a dual-mode multi-view diffusion model, which jointly supports MV-oriented and 3D-oriented generation modes. To bridge the quality gap in 3D-oriented generation, we further propose a cross-mode post-training distillation by matching distribution from consistent 3D-oriented mode to high-quality MV-oriented mode. This not only enhances visual quality while maintaining 3D consistency, but also reduces the required denoising steps for inference. Also, we propose a strategy to leverage massive single-view images and text prompts during this process to enhance the model's generalization to out-of-distribution inputs. Extensive experiments demonstrate the superiority and efficiency of our method.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14807.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruotian Peng, Yi Ren, Zhouliang Yu, Weiyang Liu, Yandong Wen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models (LLMs). However, prevailing RLVR methods exhibit a systematic bias toward exploitation over exploration, as evidenced by improved pass@1 but reduced pass@K (K>1) performance. To understand this issue, we analyze training dynamics of RLVR methods by tracking the token-level probability distributions over vocabulary candidates. Our analysis reveals a consistent probability concentration effect where the top-1 candidate increasingly accumulates probability mass and suppresses that of other candidates. More importantly, stronger over-concentration correlates with worse pass@K performance. Inspired by this finding, we propose Simple Pass@K Optimization (SimKO), a method designed to mitigate the over-concentration issue, thereby encouraging exploration. SimKO operates in an asymmetrical manner. For verified-correct responses, it boosts the probabilities of the top-K candidates. For verified-incorrect responses, it applies stronger penalties to the top-1 candidate. We observe that this asymmetric design is particularly effective at mitigating over-concentration when applied at tokens with high entropy. Across various math and logical-reasoning benchmarks, SimKO consistently yields higher pass@K for a wide range of K, providing a simple way to improve RLVR's exploration.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13678</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14807</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 15:35:48 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 15:40:49 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Dedelayed: Deleting remote inference delay via on-device correction</title>
|
<title>ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints</title>
|
||||||
<link>https://arxiv.org/abs/2510.13714</link>
|
<link>https://arxiv.org/abs/2510.14847</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dan Jacobellis, Mateen Ulhaq, Fabien Racapé, Hyomin Choi, Neeraja J. Yadwadkar</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Remote inference allows lightweight devices to leverage powerful cloud models. However, communication network latency makes predictions stale and unsuitable for real-time tasks. To address this, we introduce Dedelayed, a delay-corrective method that mitigates arbitrary remote inference delays, allowing the local device to produce low-latency outputs in real time. Our method employs a lightweight local model that processes the current frame and fuses in features that a heavyweight remote model computes from past frames. On video from the BDD100K driving dataset, Dedelayed improves semantic segmentation accuracy over the stronger of the local-only and remote-only baselines across all realistic communication network delays beyond 33 ms. Without incurring additional delay, it improves accuracy by 6.4 mIoU compared to fully local inference and 9.8 mIoU compared to remote inference, for a round-trip delay of 100 ms. The advantage grows under longer delays and higher-motion scenes, as delay-mitigated split inference sustains accuracy more effectively, providing clear advantages for real-time tasks that must remain aligned with the current world state.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14847.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meiqi Wu, Jiashu Zhu, Xiaokun Feng, Chubin Chen, Chen Zhu, Bingze Song, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Kaiqi Huang</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Video generation models have achieved remarkable progress, particularly excelling in realistic scenarios; however, their performance degrades notably in imaginative scenarios. These prompts often involve rarely co-occurring concepts with long-distance semantic relationships, falling outside training distributions. Existing methods typically apply test-time scaling for improving video quality, but their fixed search spaces and static reward designs limit adaptability to imaginative scenarios. To fill this gap, we propose ImagerySearch, a prompt-guided adaptive test-time search strategy that dynamically adjusts both the inference search space and reward function according to semantic relationships in the prompt. This enables more coherent and visually plausible videos in challenging imaginative settings. To evaluate progress in this direction, we introduce LDT-Bench, the first dedicated benchmark for long-distance semantic prompts, consisting of 2,839 diverse concept pairs and an automated protocol for assessing creative generation capabilities. Extensive experiments show that ImagerySearch consistently outperforms strong video generation baselines and existing test-time scaling approaches on LDT-Bench, and achieves competitive improvements on VBench, demonstrating its effectiveness across diverse prompt types. We will release LDT-Bench and code to facilitate future research on imaginative video generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13714</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14847</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 16:13:44 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 16:19:13 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math</title>
|
<title>Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report</title>
|
||||||
<link>https://arxiv.org/abs/2510.13744</link>
|
<link>https://arxiv.org/abs/2510.14880</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13744.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shrey Pandit, Austin Xu, Xuan-Phi Nguyen, Yifei Ming, Caiming Xiong, Shafiq Joty</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive full credit, each step must be not only correct but also sufficiently supported. To train LLM-based reasoners in such challenging, open-ended settings, strong verifiers capable of catching step-level mistakes are necessary prerequisites. We introduce Hard2Verify, a human-annotated, step-level verification benchmark produced with over 500 hours of human labor. Hard2Verify is designed to rigorously assess step-level verifiers at the frontier: Verifiers must provide step-level annotations or identify the first error in responses generated by frontier LLMs for very recent, challenging, and open-ended math questions. We evaluate 29 generative critics and process reward models, demonstrating that, beyond a few standouts, open-source verifiers lag closed source models. We subsequently analyze what drives poor performance in step-level verification, the impacts of scaling verifier compute, as well as fundamental questions such as self-verification and verification-generation dynamics.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rikiya Takehi, Benjamin Clavié, Sean Lee, Aamir Shakir</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> In this work, we introduce mxbai-edge-colbert-v0 models, at two different parameter counts: 17M and 32M. As part of our research, we conduct numerous experiments to improve retrieval and late-interaction models, which we intend to distill into smaller models as proof-of-concepts. Our ultimate aim is to support retrieval at all scales, from large-scale retrieval which lives in the cloud to models that can run locally, on any device. mxbai-edge-colbert-v0 is a model that we hope will serve as a solid foundation backbone for all future experiments, representing the first version of a long series of small proof-of-concepts. As part of the development of mxbai-edge-colbert-v0, we conducted multiple ablation studies, of which we report the results. In terms of downstream performance, mxbai-edge-colbert-v0 is a particularly capable small model, outperforming ColBERTv2 on common short-text benchmarks (BEIR) and representing a large step forward in long-context tasks, with unprecedented efficiency.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13744</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14880</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 16:50:54 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:00:35 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue</title>
|
<title>VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation</title>
|
||||||
<link>https://arxiv.org/abs/2510.13747</link>
|
<link>https://arxiv.org/abs/2510.14902</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenwen Tong, Hewei Guo, Dongchuan Ran, Jiangnan Chen, Jiefan Lu, Kaibin Wang, Keqiang Li, Xiaoxu Zhu, Jiakui Li, Kehan Li, Xueheng Li, Lumin Li, Chenxu Guo, Jiasheng Zhou, Jiandong Chen, Xianye Wu, Jiahao Wang, Silei Wu, Lei Chen, Hanming Deng, Yuxuan Song, Dinghao Zhou, Guiping Zhong, Ken Zheng, Shiyin Kang, Lewei Lu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> We introduce InteractiveOmni, a unified and open-source omni-modal large language model for audio-visual multi-turn interaction, ranging from 4B to 8B parameters, designed to lead the field of lightweight models by offering comprehensive omni-modal understanding and speech generation capabilities. To achieve this, we integrate the vision encoder, audio encoder, large language model, and speech decoder into a unified model for understanding and generation tasks. We design a multi-stage training strategy to ensure robust cross-modal capabilities, including pre-training for omni-modal understanding, followed by post-training with speech conversation and audio-visual interaction. To enable human-like long-term conversational ability, we meticulously curate a multi-turn training dataset that enhances the model's ability to handle complex and multi-turn interactions. To effectively evaluate the multi-turn memory and speech interaction capabilities, we construct the multi-modal multi-turn memory benchmark and the multi-turn speech interaction benchmark. Experiments demonstrate that InteractiveOmni significantly outperforms leading open-source models and provides a more intelligent multi-turn audio-visual experience, particularly in its long-term memory capabilities. Notably, InteractiveOmni-4B is comparable to the much larger model like Qwen2.5-Omni-7B on general benchmarks, and it can retain 97% of the performance of the InteractiveOmni-8B while utilizing only 50% of the model size. Achieving state-of-the-art results against similarly sized models across image, audio, video understanding, and speech generation tasks, InteractiveOmni is an accessible, open-source foundation for next-generation intelligent interactive systems.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14902.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Zhao, Jiaxuan Zhang, Wenxuan Song, Pengxiang Ding, Donglin Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Current vision-language-action (VLA) models, pre-trained on large-scale robotic data, exhibit strong multi-task capabilities and generalize well to variations in visual and language instructions for manipulation. However, their success rate drops significantly when faced with object concepts outside the training data, such as unseen object descriptions and textures in the dataset. To address this, we propose a novel agentic framework, VLA^2, which leverages OpenVLA as the execution backbone and effectively leverages external modules such as web retrieval and object detection to provide visual and textual knowledge about target objects to the VLA. This approach mitigates generalization failure when handling out-of-distribution objects. Based on the LIBERO simulation environment, we introduced novel objects and object descriptions to construct a new evaluation benchmark with three difficulty levels to test the effectiveness of our method. Our framework successfully outperformed the current state-of-the-art models on our designed hard-level generalization benchmark. Compared to the standalone OpenVLA baseline, VLA^2 achieves a 44.2% improvement in the success rate in the hard-level benchmark and an average improvement of 20.2% in all customized environments without any performance degradation on in-domain tasks. Project website: https://vla-2.github.io.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13747</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14902</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 16:52:48 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:18:34 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark</title>
|
<title>Budget-aware Test-time Scaling via Discriminative Verification</title>
|
||||||
<link>https://arxiv.org/abs/2510.13759</link>
|
<link>https://arxiv.org/abs/2510.14913</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13759.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Zou, Ziqi Huang, Yuhao Dong, Shulin Tian, Dian Zheng, Hongbo Liu, Jingwen He, Bin Liu, Yu Qiao, Ziwei Liu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that inherently couple them. To address this gap, we present Uni-MMMU, a comprehensive and discipline-aware benchmark that systematically unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains, including science, coding, mathematics, and puzzles. Each task is bidirectionally coupled, demanding models to (i) leverage conceptual understanding to guide precise visual synthesis, or (ii) utilize generation as a cognitive scaffold for analytical reasoning. Uni-MMMU incorporates verifiable intermediate reasoning steps, unique ground truths, and a reproducible scoring protocol for both textual and visual outputs. Through extensive evaluation of state-of-the-art unified, generation-only, and understanding-only models, we reveal substantial performance disparities and cross-modal dependencies, offering new insights into when and how these abilities reinforce one another, and establishing a reliable foundation for advancing unified models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kyle Montgomery, Sijun Tan, Yuqi Chen, Siyuan Zhuang, Tianjun Zhang, Raluca Ada Popa, Chenguang Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Test-time scaling is a powerful strategy for boosting the performance of large language models on complex reasoning tasks. While state-of-the-art approaches often employ generative verifiers to select the best solution from a pool of candidates, this method incurs prohibitive computational costs, limiting its practicality. In this work, we shift the focus to a more budget-aware paradigm: discriminative verification. We conduct a thorough empirical analysis and demonstrate that while discriminative verifiers may underperform in isolation, combining them with self-consistency in a hybrid approach creates a powerful and efficient test-time scaling mechanism. Notably, under a fixed compute budget, this hybrid approach surpasses state-of-the-art generative verification by a significant margin: achieving up to 15.3\% higher accuracy on AIME2025. Our findings establish that for practical, real-world applications, budget-aware scaling with discriminative verifiers is not only a "free" upgrade over self-consistency, but also a more effective and efficient alternative to costly generative techniques. Code is available at https://github.com/wang-research-lab/verification.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13759</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14913</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:10:35 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:30:02 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy</title>
|
<title>Predicting Task Performance with Context-aware Scaling Laws</title>
|
||||||
<link>https://arxiv.org/abs/2510.13778</link>
|
<link>https://arxiv.org/abs/2510.14919</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13778.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyi Chen, Yilun Chen, Yanwei Fu, Ning Gao, Jiaya Jia, Weiyang Jin, Hao Li, Yao Mu, Jiangmiao Pang, Yu Qiao, Yang Tian, Bin Wang, Bolun Wang, Fangjing Wang, Hanqing Wang, Tai Wang, Ziqin Wang, Xueyuan Wei, Chao Wu, Shuai Yang, Jinhui Ye, Junqiu Yu, Jia Zeng, Jingjing Zhang, Jinyu Zhang, Shi Zhang, Feng Zheng, Bowen Zhou, Yangkun Zhu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14919.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kyle Montgomery, David Park, Jianhong Tu, Michael Bendersky, Beliz Gunel, Dawn Song, Chenguang Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Scaling laws have transformed our understanding of large language models by linking upstream metrics like cross-entropy loss to design factors such as model size, training data, and compute. However, these conventional laws fail to capture downstream task performance, where context plays a critical role. In this work, we propose a straightforward, interpretable framework that jointly models downstream performance as a function of the training compute and the provided context. We empirically validate our framework by fitting it on the observed downstream performance of extended-context variants of Llama-2-7B and Llama-2-13B across 65,500 unique instances spanning three tasks: arithmetic reasoning, common sense reasoning, and machine translation. Our results demonstrate that our framework accurately models in-distribution downstream performance, generalizes across three orders of magnitude in training compute, and reliably extrapolates performance as the amount of context increases. These findings offer valuable insights into the interplay between training compute and context utilization, providing guidance for designing more efficient long-context LLMs for diverse downstream tasks. Our code is available at https://github.com/wang-research-lab/context-scaling.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13778</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14919</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:30:05 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:35:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The Art of Scaling Reinforcement Learning Compute for LLMs</title>
|
<title>GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2510.13786</link>
|
<link>https://arxiv.org/abs/2510.14942</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Devvrit Khatri, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, Sai Surya Duvvuri, Manzil Zaheer, Inderjit S. Dhillon, David Brandfonbrener, Rishabh Agarwal</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Reinforcement learning (RL) has become central to training large language models (LLMs), yet the field lacks predictive scaling methodologies comparable to those established for pre-training. Despite rapidly rising compute budgets, there is no principled understanding of how to evaluate algorithmic improvements for scaling RL compute. We present the first large-scale systematic study, amounting to more than 400,000 GPU-hours, that defines a principled framework for analyzing and predicting RL scaling in LLMs. We fit sigmoidal compute-performance curves for RL training and ablate a wide range of common design choices to analyze their effects on asymptotic performance and compute efficiency. We observe: (1) Not all recipes yield similar asymptotic performance, (2) Details such as loss aggregation, normalization, curriculum, and off-policy algorithm primarily modulate compute efficiency without materially shifting the asymptote, and (3) Stable, scalable recipes follow predictable scaling trajectories, enabling extrapolation from smaller-scale runs. Combining these insights, we propose a best-practice recipe, ScaleRL, and demonstrate its effectiveness by successfully scaling and predicting validation performance on a single RL run scaled up to 100,000 GPU-hours. Our work provides both a scientific framework for analyzing scaling in RL and a practical recipe that brings RL training closer to the predictability long achieved in pre-training.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14942.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yao Zhang, Yu Wu, Haowei Zhang, Weiguo Li, Haokun Chen, Jingpei Wu, Guohao Li, Zhen Han, Volker Tresp</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Process Reward Models (PRMs) aim to improve multi-step reasoning in Large Language Models (LLMs) by supervising intermediate steps and identifying errors. However, building effective PRMs remains challenging due to the lack of scalable, high-quality annotations. Existing approaches rely on costly human labeling, LLM-based self-evaluation that is prone to hallucination, or Monte Carlo (MC) estimation, which infers step quality solely from rollout outcomes and often introduces noisy, misaligned supervision due to credit misattribution. These issues result in three core limitations: noisy rewards, low factual fidelity, and misalignment with step-level reasoning objectives. To address these challenges, we introduce GroundedPRM, a tree-guided and fidelity-aware framework for automatic process supervision. To reduce reward noise and enable fine-grained credit assignment, we construct structured reasoning paths via Monte Carlo Tree Search (MCTS). To eliminate hallucinated supervision, we validate each intermediate step using an external tool, providing execution-grounded correctness signals. To combine both step-level validation and global outcome assessment, we design a hybrid reward aggregation mechanism that fuses tool-based verification with MCTS-derived feedback. Finally, we format the reward signal into a rationale-enhanced, generative structure to promote interpretability and compatibility with instruction-tuned LLMs. GroundedPRM is trained on only 40K automatically labeled samples, amounting to just 10% of the data used by the best-performing PRM trained with auto-labeled supervision. Nevertheless, it achieves up to a 26% relative improvement in average performance on ProcessBench. When used for reward-guided greedy search, GroundedPRM outperforms even PRMs trained with human-labeled supervision, offering a scalable and verifiable path toward high-quality process-level reasoning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13786</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14942</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:43:03 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:54:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs</title>
|
<title>LaSeR: Reinforcement Learning with Last-Token Self-Rewarding</title>
|
||||||
<link>https://arxiv.org/abs/2510.13795</link>
|
<link>https://arxiv.org/abs/2510.14943</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13795.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Zhang, Bolin Ni, Xin-Sheng Chen, Heng-Rui Zhang, Yongming Rao, Houwen Peng, Qinglin Lu, Han Hu, Meng-Hao Guo, Shi-Min Hu</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SFT). Existing open-source datasets are often plagued by widespread noise and a critical deficit in complex reasoning data, such as Chain-of-Thought (CoT), which hinders the development of advanced model capabilities. Addressing these challenges, our work makes three primary contributions. First, we introduce Honey-Data-15M, a new SFT dataset comprising approximately 15 million QA pairs, processed through multiple cleaning techniques and enhanced with a novel dual-level (short and long) CoT enrichment strategy. Second, we introduce HoneyPipe, the data curation pipeline, and its underlying framework DataStudio, providing the community with a transparent and adaptable methodology for data curation that moves beyond static dataset releases. Finally, to validate our dataset and pipeline, we train Bee-8B, an 8B model on Honey-Data-15M. Experiments show that Bee-8B establishes a new state-of-the-art (SOTA) for fully open MLLMs, achieving performance that is competitive with, and in some cases surpasses, recent semi-open models such as InternVL3.5-8B. Our work delivers to the community a suite of foundational resources, including: the Honey-Data-15M corpus; the full-stack suite comprising HoneyPipe and DataStudio; training recipes; an evaluation harness; and the model weights. This effort demonstrates that a principled focus on data quality is a key pathway to developing fully open MLLMs that are highly competitive with their semi-open counterparts.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenkai Yang, Weijie Liu, Ruobing Xie, Yiju Guo, Lulu Wu, Saiyong Yang, Yankai Lin</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). To address the lack of verification signals at test time, prior studies incorporate the training of model's self-verification capability into the standard RLVR process, thereby unifying reasoning and verification capabilities within a single LLM. However, previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency. In this work, we theoretically reveal that the closed-form solution to the RL objective of self-verification can be reduced to a remarkably simple form: the true reasoning reward of a solution is equal to its last-token self-rewarding score, which is computed as the difference between the policy model's next-token log-probability assigned to any pre-specified token at the solution's last token and a pre-calculated constant, scaled by the KL coefficient. Based on this insight, we propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss that aligns the last-token self-rewarding scores with verifier-based reasoning rewards, jointly optimizing the reasoning and self-rewarding capabilities of LLMs. The optimized self-rewarding scores can be utilized in both training and testing to enhance model performance. Notably, our algorithm derives these scores from the predicted next-token probability distribution of the last token immediately after generation, incurring only the minimal extra cost of one additional token inference. Experiments show that our method not only improves the model's reasoning performance but also equips it with remarkable self-rewarding capability, thereby boosting its inference-time scaling performance.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13795</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14943</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:52:59 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:55:11 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Reasoning in Space via Grounding in the World</title>
|
<title>DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation</title>
|
||||||
<link>https://arxiv.org/abs/2510.13800</link>
|
<link>https://arxiv.org/abs/2510.14949</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Chen, Zekun Qi, Wenyao Zhang, Xin Jin, Li Zhang, Peidong Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> In this paper, we claim that 3D visual grounding is the cornerstone of spatial reasoning and introduce the Grounded-Spatial Reasoner (GS-Reasoner) to explore the effective spatial representations that bridge the gap between them. Existing 3D LLMs suffer from the absence of a unified 3D representation capable of jointly capturing semantic and geometric information. This deficiency is manifested either in poor performance on grounding or in an excessive reliance on external modules, ultimately hindering the seamless integration of grounding and spatial reasoning. To address this, we propose a simple yet effective dual-path pooling mechanism that tightly aligns geometric features with both semantic and positional cues, constructing a unified image patch-based 3D representation that encapsulates all essential information without increasing the number of input tokens. Leveraging this holistic representation, GS-Reasoner is the first 3D LLM that achieves autoregressive grounding entirely without external modules while delivering performance comparable to state-of-the-art models, establishing a unified and self-contained framework for 3D spatial reasoning. To further bridge grounding and spatial reasoning, we introduce the Grounded Chain-of-Thought (GCoT) dataset. This dataset is meticulously curated to include both 3D bounding box annotations for objects referenced in reasoning questions and step-by-step reasoning paths that integrate grounding as a core component of the problem-solving process. Extensive experiments demonstrate that GS-Reasoner achieves impressive results on 3D visual grounding, which in turn significantly enhances its spatial reasoning capabilities, leading to state-of-the-art performance.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14949.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zhou, Sohyun An, Haikang Deng, Da Yin, Clark Peng, Cho-Jui Hsieh, Kai-Wei Chang, Nanyun Peng</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Contact languages like English exhibit rich regional variations in the form of dialects, which are often used by dialect speakers interacting with generative models. However, can multimodal generative models effectively produce content given dialectal textual input? In this work, we study this question by constructing a new large-scale benchmark spanning six common English dialects. We work with dialect speakers to collect and verify over 4200 unique prompts and evaluate on 17 image and video generative models. Our automatic and human evaluation results show that current state-of-the-art multimodal generative models exhibit 32.26% to 48.17% performance degradation when a single dialect word is used in the prompt. Common mitigation methods such as fine-tuning and prompt rewriting can only improve dialect performance by small margins (< 7%), while potentially incurring significant performance degradation in Standard American English (SAE). To this end, we design a general encoder-based mitigation strategy for multimodal generative models. Our method teaches the model to recognize new dialect features while preserving SAE performance. Experiments on models such as Stable Diffusion 1.5 show that our method is able to simultaneously raise performance on five dialects to be on par with SAE (+34.4%), while incurring near zero cost to SAE performance.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13800</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14949</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:58:08 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:56:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Trace Anything: Representing Any Video in 4D via Trajectory Fields</title>
|
<title>RealDPO: Real or Not Real, that is the Preference</title>
|
||||||
<link>https://arxiv.org/abs/2510.13802</link>
|
<link>https://arxiv.org/abs/2510.14955</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13802.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinhang Liu, Yuxi Xiao, Donny Y. Chen, Jiashi Feng, Yu-Wing Tai, Chi-Keung Tang, Bingyi Kang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Effective spatio-temporal representation is fundamental to modeling, understanding, and predicting dynamics in videos. The atomic unit of a video, the pixel, traces a continuous 3D trajectory over time, serving as the primitive element of dynamics. Based on this principle, we propose representing any video as a Trajectory Field: a dense mapping that assigns a continuous 3D trajectory function of time to each pixel in every frame. With this representation, we introduce Trace Anything, a neural network that predicts the entire trajectory field in a single feed-forward pass. Specifically, for each pixel in each frame, our model predicts a set of control points that parameterizes a trajectory (i.e., a B-spline), yielding its 3D position at arbitrary query time instants. We trained the Trace Anything model on large-scale 4D data, including data from our new platform, and our experiments demonstrate that: (i) Trace Anything achieves state-of-the-art performance on our new benchmark for trajectory field estimation and performs competitively on established point-tracking benchmarks; (ii) it offers significant efficiency gains thanks to its one-pass paradigm, without requiring iterative optimization or auxiliary estimators; and (iii) it exhibits emergent abilities, including goal-conditioned manipulation, motion forecasting, and spatio-temporal fusion. Project page: https://trace-anything.github.io/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guo Cheng, Danni Yang, Ziqi Huang, Jianlou Si, Chenyang Si, Ziwei Liu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Video generative models have recently achieved notable advancements in synthesis quality. However, generating complex motions remains a critical challenge, as existing models often struggle to produce natural, smooth, and contextually consistent movements. This gap between generated and real-world motions limits their practical applicability. To address this issue, we introduce RealDPO, a novel alignment paradigm that leverages real-world data as positive samples for preference learning, enabling more accurate motion synthesis. Unlike traditional supervised fine-tuning (SFT), which offers limited corrective feedback, RealDPO employs Direct Preference Optimization (DPO) with a tailored loss function to enhance motion realism. By contrasting real-world videos with erroneous model outputs, RealDPO enables iterative self-correction, progressively refining motion quality. To support post-training in complex motion synthesis, we propose RealAction-5K, a curated dataset of high-quality videos capturing human daily activities with rich and precise motion details. Extensive experiments demonstrate that RealDPO significantly improves video quality, text alignment, and motion realism compared to state-of-the-art models and existing preference optimization techniques.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13802</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14955</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:59:04 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:58:25 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Generative Universal Verifier as Multimodal Meta-Reasoner</title>
|
<title>MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2510.13804</link>
|
<link>https://arxiv.org/abs/2510.14958</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13804.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinchen Zhang, Xiaoying Zhang, Youbin Wu, Yanbin Cao, Renrui Zhang, Ruihang Chu, Ling Yang, Yujiu Yang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> We introduce Generative Universal Verifier, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and refinement on visual outcomes during the reasoning and generation process. This work makes three main contributions: (1) We build ViVerBench, a comprehensive benchmark spanning 16 categories of critical tasks for evaluating visual outcomes in multimodal reasoning. Results show that existing VLMs consistently underperform across these tasks, underscoring a substantial gap from human-level capability in reliable visual verification. (2) We design two automated pipelines to construct large-scale visual verification data and train OmniVerifier-7B, the first omni-capable generative verifier trained for universal visual verification and achieves notable gains on ViVerBench(+8.3). Through training, we identify three atomic capabilities in visual verification and demonstrate how they generalize and interact synergistically. (3) We propose OmniVerifier-TTS, a sequential test-time scaling paradigm that leverages the universal verifier to bridge image generation and editing within unified models, enhancing the upper bound of generative ability through iterative fine-grained optimization. Beyond generation, we extend universal verifier to broader world-modeling interleaved reasoning scenarios. Empirically, OmniVerifier-TTS achieves improvements on T2I-ReasonBench(+3.7), and GenEval++(+4.3), outperforming existing parallel test-time scaling methods, such as Best-of-N. By endowing multimodal reasoning with reliable visual verification, OmniVerifier advances both reliable reflection during generation and scalable test-time refinement, marking a step toward more trustworthy and controllable next-generation reasoning systems.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14958.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weikang Shi, Aldrich Yu, Rongyao Fang, Houxing Ren, Ke Wang, Aojun Zhou, Changyao Tian, Xinyu Fu, Yuxuan Hu, Zimu Lu, Linjiang Huang, Si Liu, Rui Liu, Hongsheng Li</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> While Large Language Models (LLMs) have excelled in textual reasoning, they struggle with mathematical domains like geometry that intrinsically rely on visual aids. Existing approaches to Visual Chain-of-Thought (VCoT) are often limited by rigid external tools or fail to generate the high-fidelity, strategically-timed diagrams necessary for complex problem-solving. To bridge this gap, we introduce MathCanvas, a comprehensive framework designed to endow unified Large Multimodal Models (LMMs) with intrinsic VCoT capabilities for mathematics. Our approach consists of two phases. First, a Visual Manipulation stage pre-trains the model on a novel 15.2M-pair corpus, comprising 10M caption-to-diagram pairs (MathCanvas-Imagen) and 5.2M step-by-step editing trajectories (MathCanvas-Edit), to master diagram generation and editing. Second, a Strategic Visual-Aided Reasoning stage fine-tunes the model on MathCanvas-Instruct, a new 219K-example dataset of interleaved visual-textual reasoning paths, teaching it when and how to leverage visual aids. To facilitate rigorous evaluation, we introduce MathCanvas-Bench, a challenging benchmark with 3K problems that require models to produce interleaved visual-textual solutions. Our model, BAGEL-Canvas, trained under this framework, achieves an 86% relative improvement over strong LMM baselines on MathCanvas-Bench, demonstrating excellent generalization to other public math benchmarks. Our work provides a complete toolkit-framework, datasets, and benchmark-to unlock complex, human-like visual-aided reasoning in LMMs. Project Page: https://mathcanvas.github.io/</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13804</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14958</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:59:24 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:58:58 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning</title>
|
<title>Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2510.13809</link>
|
<link>https://arxiv.org/abs/2510.14961</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.13809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sihui Ji, Xi Chen, Xin Tao, Pengfei Wan, Hengshuang Zhao</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plausible videos and serve as ''world models''. To address this issue, we propose PhysMaster, which captures physical knowledge as a representation for guiding video generation models to enhance their physics-awareness. Specifically, PhysMaster is based on the image-to-video task where the model is expected to predict physically plausible dynamics from the input image. Since the input image provides physical priors like relative positions and potential interactions of objects in the scenario, we devise PhysEncoder to encode physical information from it as an extra condition to inject physical knowledge into the video generation process. The lack of proper supervision on the model's physical performance beyond mere appearance motivates PhysEncoder to apply reinforcement learning with human feedback to physical representation learning, which leverages feedback from generation models to optimize physical representations with Direct Preference Optimization (DPO) in an end-to-end manner. PhysMaster provides a feasible solution for improving physics-awareness of PhysEncoder and thus of video generation, proving its ability on a simple proxy task and generalizability to wide-ranging physical scenarios. This implies that our PhysMaster, which unifies solutions for various physical processes via representation learning in the reinforcement learning paradigm, can act as a generic and plug-in solution for physics-aware video generation and broader applications.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14961.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jonas Geiping, Xinyu Yang, Guinan Su</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have demonstrated that these architectures can scale to modern language modeling tasks while exhibiting advantages in reasoning tasks. In this work, we examine the relationship between recurrent-depth models and diffusion language models. Building on their similarities, we develop a new diffusion forcing sampler for these models to accelerate generation. The sampler advances by decoding new tokens at every forward pass of the model, while the latent states of these tokens can be further refined in parallel through recurrence. Theoretically, generation with our sampler is strictly more expressive than the baseline autoregressive generation using the same time budget on modern hardware. Moreover, this sampler, based on principles from diffusion literature, can be directly applied to existing 3.5B recurrent-depth transformers without any tuning, leading to up to a 5x speedup. Consequently, our findings not only provide an efficient mechanism for parallelizing the extra computation in recurrent-depth models at inference, but also suggest that such models can be naturally viewed as strong continuous, though causal, diffusion language models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.13809</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14961</guid>
|
||||||
<pubDate>Wed, 15 Oct 2025 17:59:59 +0000</pubDate>
|
<pubDate>Thu, 16 Oct 2025 17:59:07 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14967</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14967.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guoqing Wang, Sunhao Dai, Guangze Ye, Zeyu Gan, Wei Yao, Yong Deng, Xiaofeng Wu, Zhenzhe Ying</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require multi-turn reasoning and knowledge acquisition. However, existing approaches typically rely on outcome-based rewards that are only provided at the final answer. This reward sparsity becomes particularly problematic in multi-turn settings, where long trajectories exacerbate two critical issues: (i) advantage collapse, where all rollouts receive identical rewards and provide no useful learning signals, and (ii) lack of fine-grained credit assignment, where dependencies between turns are obscured, especially in long-horizon tasks. In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training. IGPO models each interaction turn as an incremental process of acquiring information about the ground truth, and defines turn-level rewards as the marginal increase in the policy's probability of producing the correct answer. Unlike prior process-level reward approaches that depend on external reward models or costly Monte Carlo estimation, IGPO derives intrinsic rewards directly from the model's own belief updates. These intrinsic turn-level rewards are combined with outcome-level supervision to form dense reward trajectories. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that IGPO consistently outperforms strong baselines in multi-turn scenarios, achieving higher accuracy and improved sample efficiency.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14967</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:32 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14969</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14969.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Wang, Da Yin, Yuedong Cui, Ruichen Zheng, Zhiqian Li, Zongyu Lin, Di Wu, Xueqing Wu, Chenchen Ye, Yu Zhou, Kai-Wei Chang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering perspectives. To this end, we introduce UI-Simulator, a scalable paradigm that generates structured UI states and transitions to synthesize training trajectories at scale. Our paradigm integrates a digital world simulator for diverse UI states, a guided rollout process for coherent exploration, and a trajectory wrapper that produces high-quality and diverse trajectories for agent training. We further propose UI-Simulator-Grow, a targeted scaling strategy that enables more rapid and data-efficient scaling by prioritizing high-impact tasks and synthesizes informative trajectory variants. Experiments on WebArena and AndroidWorld show that UI-Simulator rivals or surpasses open-source agents trained on real UIs with significantly better robustness, despite using weaker teacher models. Moreover, UI-Simulator-Grow matches the performance of Llama-3-70B-Instruct using only Llama-3-8B-Instruct as the base model, highlighting the potential of targeted synthesis scaling paradigm to continuously and efficiently enhance the digital agents.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14969</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:38 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14972</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14972.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinxi Li, Yuntian Deng, Pengyu Nie</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming language code but driven by statistics rather than grammar. As a result, semantically identical code snippets can be tokenized differently depending on superficial factors such as whitespace or identifier naming. To measure the impact of this misalignment, we introduce TokDrift, a framework that applies semantic-preserving rewrite rules to create code variants differing only in tokenization. Across nine code LLMs, including large ones with over 30B parameters, even minor formatting changes can cause substantial shifts in model behavior. Layer-wise analysis shows that the issue originates in early embeddings, where subword segmentation fails to capture grammar token boundaries. Our findings identify misaligned tokenization as a hidden obstacle to reliable code understanding and generation, highlighting the need for grammar-aware tokenization for future code LLMs.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14972</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:45 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Attention Is All You Need for KV Cache in Diffusion LLMs</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14973</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14973.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every denoising step and layer, despite KV states changing little across most steps, especially in shallow layers, leading to substantial redundancy. We make three observations: (1) distant {bf MASK} tokens primarily act as a length-bias and can be cached block-wise beyond the active prediction window; (2) KV dynamics increase with depth, suggesting that selective refresh starting from deeper layers is sufficient; and (3) the most-attended token exhibits the smallest KV drift, providing a conservative lower bound on cache change for other tokens. Building on these, we propose {bf Elastic-Cache}, a training-free, architecture-agnostic strategy that jointly decides {when} to refresh (via an attention-aware drift test on the most-attended token) and {where} to refresh (via a depth-aware schedule that recomputes from a chosen layer onward while reusing shallow-layer caches and off-window MASK caches). Unlike fixed-period schemes, Elastic-Cache performs adaptive, layer-aware cache updates for diffusion LLMs, reducing redundant computation and accelerating decoding with negligible loss in generation quality. Experiments on LLaDA-Instruct, LLaDA-1.5, and LLaDA-V across mathematical reasoning and code generation tasks demonstrate consistent speedups: 8.7times on GSM8K (256 tokens), 45.1times on longer sequences, and 4.8times on HumanEval, while consistently maintaining higher accuracy than the baseline. Our method achieves significantly higher throughput (6.8times on GSM8K) than existing confidence-based approaches while preserving generation quality, enabling practical deployment of diffusion LLMs.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14973</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:48 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14974</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14974.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hansheng Chen, Kai Zhang, Hao Tan, Leonidas Guibas, Gordon Wetzstein, Sai Bi</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often suffer from a quality-diversity trade-off. To address this, we propose policy-based flow models (pi-Flow). pi-Flow modifies the output layer of a student flow model to predict a network-free policy at one timestep. The policy then produces dynamic flow velocities at future substeps with negligible overhead, enabling fast and accurate ODE integration on these substeps without extra network evaluations. To match the policy's ODE trajectory to the teacher's, we introduce a novel imitation distillation approach, which matches the policy's velocity to the teacher's along the policy's trajectory using a standard ell_2 flow matching loss. By simply mimicking the teacher's behavior, pi-Flow enables stable and scalable training and avoids the quality-diversity trade-off. On ImageNet 256^2, it attains a 1-NFE FID of 2.85, outperforming MeanFlow of the same DiT architecture. On FLUX.1-12B and Qwen-Image-20B at 4 NFEs, pi-Flow achieves substantially better diversity than state-of-the-art few-step methods, while maintaining teacher-level quality.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14974</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:51 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>WithAnyone: Towards Controllable and ID Consistent Image Generation</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14975</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengyuan Xu, Wei Cheng, Peng Xing, Yixiao Fang, Shuhan Wu, Rui Wang, Xianfang Zeng, Daxin Jiang, Gang Yu, Xingjun Ma, Yu-Gang Jiang</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets containing multiple images of the same individual forces most approaches to adopt reconstruction-based training. This reliance often leads to a failure mode we term copy-paste, where the model directly replicates the reference face rather than preserving identity across natural variations in pose, expression, or lighting. Such over-similarity undermines controllability and limits the expressive power of generation. To address these limitations, we (1) construct a large-scale paired dataset MultiID-2M, tailored for multi-person scenarios, providing diverse references for each identity; (2) introduce a benchmark that quantifies both copy-paste artifacts and the trade-off between identity fidelity and variation; and (3) propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity. These contributions culminate in WithAnyone, a diffusion-based model that effectively mitigates copy-paste while preserving high identity similarity. Extensive qualitative and quantitative experiments demonstrate that WithAnyone significantly reduces copy-paste artifacts, improves controllability over pose and expression, and maintains strong perceptual quality. User studies further validate that our method achieves high identity fidelity while enabling expressive controllable generation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14975</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:54 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14976</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14976.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaowei Liu, Chuan Guo, Bing Zhou, Jian Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Close-proximity human-human interactive poses convey rich contextual information about interaction dynamics. Given such poses, humans can intuitively infer the context and anticipate possible past and future dynamics, drawing on strong priors of human behavior. Inspired by this observation, we propose Ponimator, a simple framework anchored on proximal interactive poses for versatile interaction animation. Our training data consists of close-contact two-person poses and their surrounding temporal context from motion-capture interaction datasets. Leveraging interactive pose priors, Ponimator employs two conditional diffusion models: (1) a pose animator that uses the temporal prior to generate dynamic motion sequences from interactive poses, and (2) a pose generator that applies the spatial prior to synthesize interactive poses from a single pose, text, or both when interactive poses are unavailable. Collectively, Ponimator supports diverse tasks, including image-based interaction animation, reaction animation, and text-to-interaction synthesis, facilitating the transfer of interaction knowledge from high-quality mocap data to open-world scenarios. Empirical experiments across diverse datasets and applications demonstrate the universality of the pose prior and the effectiveness and robustness of our framework.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14976</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:56 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Learning an Image Editing Model without Image Editing Pairs</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14978</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14978.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nupur Kumari, Sheng-Yu Wang, Nanxuan Zhao, Yotam Nitzan, Yuheng Li, Krishna Kumar Singh, Richard Zhang, Eli Shechtman, Jun-Yan Zhu, Xun Huang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of input-target pairs. This is a critical bottleneck, as such naturally occurring pairs are hard to curate at scale. Current workarounds use synthetic training pairs that leverage the zero-shot capabilities of existing models. However, this can propagate and magnify the artifacts of the pretrained model into the final trained model. In this work, we present a new training paradigm that eliminates the need for paired data entirely. Our approach directly optimizes a few-step diffusion model by unrolling it during training and leveraging feedback from vision-language models (VLMs). For each input and editing instruction, the VLM evaluates if an edit follows the instruction and preserves unchanged content, providing direct gradients for end-to-end optimization. To ensure visual fidelity, we incorporate distribution matching loss (DMD), which constrains generated images to remain within the image manifold learned by pretrained models. We evaluate our method on standard benchmarks and include an extensive ablation study. Without any paired data, our method performs on par with various image editing diffusion models trained on extensive supervised paired data, under the few-step setting. Given the same VLM as the reward model, we also outperform RL-based techniques like Flow-GRPO.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14978</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:57 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Agentic Design of Compositional Machines</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14980</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqian Zhang, Weiyang Liu, Zhen Liu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The design of complex machines stands as both a marker of human intelligence and a foundation of engineering practice. Given recent advances in large language models (LLMs), we ask whether they, too, can learn to create. We approach this question through the lens of compositional machine design: a task in which machines are assembled from standardized components to meet functional demands like locomotion or manipulation in a simulated physical environment. To support this investigation, we introduce BesiegeField, a testbed built on the machine-building game Besiege, which enables part-based construction, physical simulation and reward-driven evaluation. Using BesiegeField, we benchmark state-of-the-art LLMs with agentic workflows and identify key capabilities required for success, including spatial reasoning, strategic assembly, and instruction-following. As current open-source models fall short, we explore reinforcement learning (RL) as a path to improvement: we curate a cold-start dataset, conduct RL finetuning experiments, and highlight open challenges at the intersection of language, machine design, and physical reasoning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14980</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:58 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>From Pixels to Words -- Towards Native Vision-Language Primitives at Scale</title>
|
||||||
|
<link>https://arxiv.org/abs/2510.14979</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiwen Diao, Mingxuan Li, Silei Wu, Linjun Dai, Xiaohua Wang, Hanming Deng, Lewei Lu, Dahua Lin, Ziwei Liu</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> The edifice of native Vision-Language Models (VLMs) has emerged as a rising contender to typical modular VLMs, shaped by evolving model architectures and training paradigms. Yet, two lingering clouds cast shadows over its widespread exploration and promotion: (-) What fundamental constraints set native VLMs apart from modular ones, and to what extent can these barriers be overcome? (-) How to make research in native VLMs more accessible and democratized, thereby accelerating progress in the field. In this paper, we clarify these challenges and outline guiding principles for constructing native VLMs. Specifically, one native VLM primitive should: (i) effectively align pixel and word representations within a shared semantic space; (ii) seamlessly integrate the strengths of formerly separate vision and language modules; (iii) inherently embody various cross-modal properties that support unified vision-language encoding, aligning, and reasoning. Hence, we launch NEO, a novel family of native VLMs built from first principles, capable of rivaling top-tier modular counterparts across diverse real-world scenarios. With only 390M image-text examples, NEO efficiently develops visual perception from scratch while mitigating vision-language conflicts inside a dense and monolithic model crafted from our elaborate primitives. We position NEO as a cornerstone for scalable and powerful native VLMs, paired with a rich set of reusable components that foster a cost-effective and extensible ecosystem. Our code and models are publicly available at: https://github.com/EvolvingLMMs-Lab/NEO.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.14979</guid>
|
||||||
|
<pubDate>Thu, 16 Oct 2025 17:59:58 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user