bot: update RSS feed
This commit is contained in:
github-actions[bot]
331
feed.xml
331
feed.xml
@@ -7,251 +7,202 @@
|
|||||||
<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, 24 Oct 2025 00:02:18 +0000</lastBuildDate>
|
<lastBuildDate>Sat, 25 Oct 2025 00:02:38 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models</title>
|
<title>Diff-XYZ: A Benchmark for Evaluating Diff Understanding</title>
|
||||||
<link>https://arxiv.org/abs/2510.15015</link>
|
<link>https://arxiv.org/abs/2510.12487</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15015.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mor Ventura, Michael Toker, Or Patashnik, Yonatan Belinkov, Roi Reichart</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Text-to-Image (T2I) models have advanced rapidly, yet they remain vulnerable to semantic leakage, the unintended transfer of semantically related features between distinct entities. Existing mitigation strategies are often optimization-based or dependent on external inputs. We introduce DeLeaker, a lightweight, optimization-free inference-time approach that mitigates leakage by directly intervening on the model's attention maps. Throughout the diffusion process, DeLeaker dynamically reweights attention maps to suppress excessive cross-entity interactions while strengthening the identity of each entity. To support systematic evaluation, we introduce SLIM (Semantic Leakage in IMages), the first dataset dedicated to semantic leakage, comprising 1,130 human-verified samples spanning diverse scenarios, together with a novel automatic evaluation framework. Experiments demonstrate that DeLeaker consistently outperforms all baselines, even when they are provided with external information, achieving effective leakage mitigation without compromising fidelity or quality. These results underscore the value of attention control and pave the way for more semantically precise T2I models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12487.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Evgeniy Glukhov, Michele Conti, Egor Bogomolov, Yaroslav Golubev, Alexander Bezzubov</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reliable handling of code diffs is central to agents that edit and refactor repositories at scale. We introduce Diff-XYZ, a compact benchmark for code-diff understanding with three supervised tasks: apply (old code + diff rightarrow new code), anti-apply (new code - diff rightarrow old code), and diff generation (new code - old code rightarrow diff). Instances in the benchmark are triples langle old code, new code, diff rangle drawn from real commits in CommitPackFT, paired with automatic metrics and a clear evaluation protocol. We use the benchmark to do a focused empirical study of the unified diff format and run a cross-format comparison of different diff representations. Our findings reveal that different formats should be used depending on the use case and model size. For example, representing diffs in search-replace format is good for larger models in the diff generation scenario, yet not suited well for diff analysis and smaller models. The Diff-XYZ benchmark is a reusable foundation for assessing and improving diff handling in LLMs that can aid future development of diff formats and models editing code. The dataset is published on HuggingFace Hub: https://huggingface.co/datasets/JetBrains-Research/diff-xyz.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15015</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.12487</guid>
|
||||||
<pubDate>Thu, 16 Oct 2025 17:39:21 +0000</pubDate>
|
<pubDate>Tue, 14 Oct 2025 13:23:01 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Directional Reasoning Injection for Fine-Tuning MLLMs</title>
|
<title>CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation</title>
|
||||||
<link>https://arxiv.org/abs/2510.15050</link>
|
<link>https://arxiv.org/abs/2510.17853</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15050.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Huang, Zeliang Zhang, Jiang Liu, Ximeng Sun, Jialian Wu, Xiaodong Yu, Ze Wang, Chenliang Xu, Emad Barsoum, Zicheng Liu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Multimodal large language models (MLLMs) are rapidly advancing, yet their reasoning ability often lags behind that of strong text-only counterparts. Existing methods to bridge this gap rely on supervised fine-tuning over large-scale multimodal reasoning data or reinforcement learning, both of which are resource-intensive. A promising alternative is model merging, which interpolates parameters between reasoning-enhanced LLMs and multimodal variants. However, our analysis shows that naive merging is not always a "free lunch": its effectiveness varies drastically across model families, with some (e.g., LLaVA, Idefics) benefiting while others (e.g., Qwen) suffer performance degradation. To address this, we propose Directional Reasoning Injection for Fine-Tuning (DRIFT) MLLMs, a lightweight method that transfers reasoning knowledge in the gradient space, without destabilizing multimodal alignment. DRIFT precomputes a reasoning prior as the parameter-space difference between reasoning and multimodal variants, then uses it to bias gradients during multimodal fine-tuning. This approach preserves the simplicity of standard supervised fine-tuning pipelines while enabling efficient reasoning transfer. Extensive experiments on multimodal reasoning benchmarks, including MathVista and MathVerse, demonstrate that DRIFT consistently improves reasoning performance over naive merging and supervised fine-tuning, while matching or surpassing training-heavy methods at a fraction of the cost.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17853.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yee Man Choi, Xuehang Guo, Yi R., Fung, Qingyun Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) have emerged as promising assistants for scientific writing. However, there have been concerns regarding the quality and reliability of the generated text, one of which is the citation accuracy and faithfulness. While most recent work relies on methods such as LLM-as-a-Judge, the reliability of LLM-as-a-Judge alone is also in doubt. In this work, we reframe citation evaluation as a problem of citation attribution alignment, which is assessing whether LLM-generated citations match those a human author would include for the same text. We propose CiteGuard, a retrieval-aware agent framework designed to provide more faithful grounding for citation validation. CiteGuard improves the prior baseline by 12.3%, and achieves up to 65.4% accuracy on the CiteME benchmark, on par with human-level performance (69.7%). It also enables the identification of alternative but valid citations.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15050</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.17853</guid>
|
||||||
<pubDate>Thu, 16 Oct 2025 18:06:46 +0000</pubDate>
|
<pubDate>Wed, 15 Oct 2025 00:32:26 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Language Models are Injective and Hence Invertible</title>
|
<title>Emergence of Linear Truth Encodings in Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2510.15511</link>
|
<link>https://arxiv.org/abs/2510.15804</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15511.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Giorgos Nikolaou, Tommaso Mencattini, Donato Crisostomi, Andrea Santilli, Yannis Panagakis, Emanuele Rodola'</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exact recovery of the input from a model's representations. In this paper, we challenge this view. First, we prove mathematically that transformer language models mapping discrete input sequences to their corresponding sequence of continuous representations are injective and therefore lossless, a property established at initialization and preserved during training. Second, we confirm this result empirically through billions of collision tests on six state-of-the-art language models, and observe no collisions. Third, we operationalize injectivity: we introduce SipIt, the first algorithm that provably and efficiently reconstructs the exact input text from hidden activations, establishing linear-time guarantees and demonstrating exact invertibility in practice. Overall, our work establishes injectivity as a fundamental and exploitable property of language models, with direct implications for transparency, interpretability, and safe deployment.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15804.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shauli Ravfogel, Gilad Yehudai, Tal Linzen, Joan Bruna, Alberto Bietti</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent probing studies reveal that large language models exhibit linear subspaces that separate true from false statements, yet the mechanism behind their emergence is unclear. We introduce a transparent, one-layer transformer toy model that reproduces such truth subspaces end-to-end and exposes one concrete route by which they can arise. We study one simple setting in which truth encoding can emerge: a data distribution where factual statements co-occur with other factual statements (and vice-versa), encouraging the model to learn this distinction in order to lower the LM loss on future tokens. We corroborate this pattern with experiments in pretrained language models. Finally, in the toy setting we observe a two-phase learning dynamic: networks first memorize individual factual associations in a few steps, then -- over a longer horizon -- learn to linearly separate true from false, which in turn lowers language-modeling loss. Together, these results provide both a mechanistic demonstration and an empirical motivation for how and why linear truth representations can emerge in language models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15511</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.15804</guid>
|
||||||
<pubDate>Fri, 17 Oct 2025 10:25:30 +0000</pubDate>
|
<pubDate>Fri, 17 Oct 2025 16:30:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Attention Sinks in Diffusion Language Models</title>
|
<title>Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism</title>
|
||||||
<link>https://arxiv.org/abs/2510.15731</link>
|
<link>https://arxiv.org/abs/2510.17896</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15731.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maximo Eduardo Rulli, Simone Petruzzi, Edoardo Michielon, Fabrizio Silvestri, Simone Scardapane, Alessio Devoto</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Masked Diffusion Language Models (DLMs) have recently emerged as a promising alternative to traditional Autoregressive Models (ARMs). DLMs employ transformer encoders with bidirectional attention, enabling parallel token generation while maintaining competitive performance. Although their efficiency and effectiveness have been extensively studied, the internal mechanisms that govern DLMs remain largely unexplored. In this work, we conduct an empirical analysis of DLM attention patterns, focusing on the attention sinking phenomenon, an effect previously observed in various transformer-based architectures. Our findings reveal that DLMs also exhibit attention sinks, but with distinct characteristics. First, unlike in ARMs, the sink positions in DLMs tend to shift throughout the generation process, displaying a dynamic behaviour. Second, while ARMs are highly sensitive to the removal of attention sinks, DLMs remain robust: masking sinks leads to only a minor degradation in performance. These results provide new insights into the inner workings of diffusion-based language models and highlight fundamental differences in how they allocate and utilize attention compared to autoregressive models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17896.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tao Bu, Qiangang Wang, Bowen Zeng, Hanwen Sun, Yunpeng Huang, Chun Cao, Jingwei Xu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Transformer-based large language models (LLMs) have achieved remarkable success, yet their standard attention mechanism incurs quadratic computation and memory costs with respect to sequence length, posing a major bottleneck for long-context training. Prior work tackles this challenge along two directions: (1) kernel-level optimizations, which accelerate dense and sparse attention operators; and (2) module-level strategies, often referred to as distributed attention or context parallel training, which scale attention across multiple devices. However, systematic evaluation still remains limited: operator-level comparisons are often incomplete, while context parallel strategies are typically framework-specific, with unclear performance analysis across contexts. To address these gaps, we propose a unified benchmark that integrates representative attention kernels and context parallel mechanisms with a modular and extensible interface for evaluation. The benchmark evaluates methods along two critical dimensions: (1) attention mask patterns, which strongly affect efficiency, scalability, and usability, and (2) sequence length and distributed scale, which determine performance under extreme long-context training. Through comprehensive experiments on the cluster of up to 96 GPUs, our benchmark enables reproducible comparisons, highlights method-specific trade-offs, and provides practical guidance for designing and deploying attention mechanisms in long-context LLM training.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15731</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.17896</guid>
|
||||||
<pubDate>Fri, 17 Oct 2025 15:23:58 +0000</pubDate>
|
<pubDate>Sun, 19 Oct 2025 07:07:37 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>What Questions Should Robots Be Able to Answer? A Dataset of User Questions for Explainable Robotics</title>
|
<title>Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations</title>
|
||||||
<link>https://arxiv.org/abs/2510.16435</link>
|
<link>https://arxiv.org/abs/2510.16893</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16435.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lennart Wachowiak, Andrew Coles, Gerard Canal, Oya Celiktutan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> With the growing use of large language models and conversational interfaces in human-robot interaction, robots' ability to answer user questions is more important than ever. We therefore introduce a dataset of 1,893 user questions for household robots, collected from 100 participants and organized into 12 categories and 70 subcategories. Most work in explainable robotics focuses on why-questions. In contrast, our dataset provides a wide variety of questions, from questions about simple execution details to questions about how the robot would act in hypothetical scenarios -- thus giving roboticists valuable insights into what questions their robot needs to be able to answer. To collect the dataset, we created 15 video stimuli and 7 text stimuli, depicting robots performing varied household tasks. We then asked participants on Prolific what questions they would want to ask the robot in each portrayed situation. In the final dataset, the most frequent categories are questions about task execution details (22.5%), the robot's capabilities (12.7%), and performance assessments (11.3%). Although questions about how robots would handle potentially difficult scenarios and ensure correct behavior are less frequent, users rank them as the most important for robots to be able to answer. Moreover, we find that users who identify as novices in robotics ask different questions than more experienced users. Novices are more likely to inquire about simple facts, such as what the robot did or the current state of the environment. As robots enter environments shared with humans and language becomes central to giving instructions and interaction, this dataset provides a valuable foundation for (i) identifying the information robots need to log and expose to conversational interfaces, (ii) benchmarking question-answering modules, and (iii) designing explanation strategies that align with user expectations.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16893.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo-Han Feng, Chien-Feng Liu, Yu-Hsuan Li Liang, Chih-Kai Yang, Szu-Wei Fu, Zhehuai Chen, Ke-Han Lu, Sung-Feng Huang, Chao-Han Huck Yang, Yu-Chiang Frank Wang, Yun-Nung Chen, Hung-yi Lee</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, and task performance have been widely studied, their safety alignment under paralinguistic variation remains underexplored. This work systematically investigates the role of speaker emotion. We construct a dataset of malicious speech instructions expressed across multiple emotions and intensities, and evaluate several state-of-the-art LALMs. Our results reveal substantial safety inconsistencies: different emotions elicit varying levels of unsafe responses, and the effect of intensity is non-monotonic, with medium expressions often posing the greatest risk. These findings highlight an overlooked vulnerability in LALMs and call for alignment strategies explicitly designed to ensure robustness under emotional variation, a prerequisite for trustworthy deployment in real-world settings.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16435</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.16893</guid>
|
||||||
<pubDate>Sat, 18 Oct 2025 10:16:45 +0000</pubDate>
|
<pubDate>Sun, 19 Oct 2025 15:41:25 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FinSight: Towards Real-World Financial Deep Research</title>
|
<title>SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2510.16844</link>
|
<link>https://arxiv.org/abs/2510.16917</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajie Jin, Yuyao Zhang, Yimeng Xu, Hongjin Qian, Yutao Zhu, Zhicheng Dou</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Generating professional financial reports is a labor-intensive and intellectually demanding process that current AI systems struggle to fully automate. To address this challenge, we introduce FinSight (Financial InSight), a novel multi agent framework for producing high-quality, multimodal financial reports. The foundation of FinSight is the Code Agent with Variable Memory (CAVM) architecture, which unifies external data, designed tools, and agents into a programmable variable space, enabling flexible data collection, analysis and report generation through executable code. To ensure professional-grade visualization, we propose an Iterative Vision-Enhanced Mechanism that progressively refines raw visual outputs into polished financial charts. Furthermore, a two stage Writing Framework expands concise Chain-of-Analysis segments into coherent, citation-aware, and multimodal reports, ensuring both analytical depth and structural consistency. Experiments on various company and industry-level tasks demonstrate that FinSight significantly outperforms all baselines, including leading deep research systems in terms of factual accuracy, analytical depth, and presentation quality, demonstrating a clear path toward generating reports that approach human-expert quality.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chih-Kai Yang, Yen-Ting Piao, Tzu-Wen Hsu, Szu-Wei Fu, Zhehuai Chen, Ke-Han Lu, Sung-Feng Huang, Chao-Han Huck Yang, Yu-Chiang Frank Wang, Yun-Nung Chen, Hung-yi Lee</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Knowledge editing offers an efficient way to update model knowledge without full retraining, but prior work has concentrated almost exclusively on textual or visual modalities. We introduce SAKE, the first benchmark specifically designed for editing auditory attribute knowledge in Large Audio-Language Models (LALMs). Unlike factual updates, SAKE targets several abstract auditory attributes, capturing knowledge types that go beyond conventional textual and visual domains. We benchmark seven editing methods on two LALMs along four dimensions: reliability, generality, audio/text locality, and portability. Results highlight challenges such as preserving intra-attribute knowledge unrelated to the edit, generalizing edits to multimodal reasoning, and maintaining edits under sequential updates. SAKE provides a principled framework to study how knowledge editing extends to the auditory modalities, opening new directions for maintaining and adapting LALMs in more diverse real-world scenarios.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16844</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.16917</guid>
|
||||||
<pubDate>Sun, 19 Oct 2025 14:05:35 +0000</pubDate>
|
<pubDate>Sun, 19 Oct 2025 16:22:09 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>From Charts to Code: A Hierarchical Benchmark for Multimodal Models</title>
|
<title>Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2510.17932</link>
|
<link>https://arxiv.org/abs/2510.18245</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17932.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, information-dense tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,023 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 25 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5, Qwen2.5-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5 averages only 0.57 on code-based evaluation and 0.22 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs. Our code and data are available on Chart2Code.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Song Bian, Tao Yu, Shivaram Venkataraman, Youngsuk Park</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Scaling the number of parameters and the size of training data has proven to be an effective strategy for improving large language model (LLM) performance. Yet, as these models grow increasingly powerful and widely deployed, the cost of inference has become a pressing concern. Despite its importance, the trade-off between model accuracy and inference efficiency remains underexplored. In this work, we examine how key architectural factors, hidden size, the allocation of parameters between MLP and attention (mlp-to-attention ratio), and grouped-query attention (GQA), influence both inference cost and accuracy. We introduce a conditional scaling law that augments the Chinchilla framework with architectural information, along with a search framework for identifying architectures that are simultaneously inference-efficient and accurate. To validate our approach, we train more than 200 models spanning 80M to 3B parameters and 8B to 100B training tokens, and fit the proposed conditional scaling law. Our results show that the conditional scaling law reliably predicts optimal architectural choices and that the resulting models outperform existing open-source baselines. Under the same training budget, optimized architectures achieve up to 2.1% higher accuracy and 42% greater inference throughput compared to LLaMA-3.2.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17932</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.18245</guid>
|
||||||
<pubDate>Mon, 20 Oct 2025 15:11:56 +0000</pubDate>
|
<pubDate>Tue, 21 Oct 2025 03:08:48 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SAVANT: Semantic Analysis with Vision-Augmented Anomaly deTection</title>
|
<title>Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference</title>
|
||||||
<link>https://arxiv.org/abs/2510.18034</link>
|
<link>https://arxiv.org/abs/2510.18413</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18034.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roberto Brusnicki, David Pop, Yuan Gao, Mattia Piccinini, Johannes Betz</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution scenarios with semantic anomalies. While Vision Language Models (VLMs) offer promising reasoning capabilities, naive prompting approaches yield unreliable performance and depend on expensive proprietary models, limiting practical deployment. We introduce SAVANT (Semantic Analysis with Vision-Augmented Anomaly deTection), a structured reasoning framework that achieves high accuracy and recall in detecting anomalous driving scenarios from input images through layered scene analysis and a two-phase pipeline: structured scene description extraction followed by multi-modal evaluation. Our approach transforms VLM reasoning from ad-hoc prompting to systematic analysis across four semantic layers: Street, Infrastructure, Movable Objects, and Environment. SAVANT achieves 89.6% recall and 88.0% accuracy on real-world driving scenarios, significantly outperforming unstructured baselines. More importantly, we demonstrate that our structured framework enables a fine-tuned 7B parameter open-source model (Qwen2.5VL) to achieve 90.8% recall and 93.8% accuracy - surpassing all models evaluated while enabling local deployment at near-zero cost. By automatically labeling over 9,640 real-world images with high accuracy, SAVANT addresses the critical data scarcity problem in anomaly detection and provides a practical path toward reliable, accessible semantic monitoring for autonomous systems.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18413.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Yan, Guo-Qing Jiang, Yuchen Zhang, Xiaoxing Ma, Ran Zhu, Chun Cao, Jingwei Xu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models (LLMs) now support context windows of hundreds of thousands to millions of tokens, enabling applications such as long-document summarization, large-scale code synthesis, multi-document question answering and persistent multi-turn dialogue. However, such extended contexts exacerbate the quadratic cost of self-attention, leading to severe latency in autoregressive decoding. Existing sparse attention methods alleviate these costs but rely on heuristic patterns that struggle to recall critical key-value (KV) pairs for each query, resulting in accuracy degradation. We introduce Adamas, a lightweight yet highly accurate sparse attention mechanism designed for long-context inference. Adamas applies the Hadamard transform, bucketization and 2-bit compression to produce compact representations, and leverages Manhattan-distance estimation for efficient top-k selections. Experiments show that Adamas matches the accuracy of full attention with only a 64-token budget, achieves near-lossless performance at 128, and supports up to 8x higher sparsity than prior state-of-the-art (SOTA) methods while delivering up to 4.4x self-attention and 1.5x end-to-end speedups on 32K-length sequences. Remarkably, Adamas attains comparable or even lower perplexity than full attention, underscoring its effectiveness in maintaining accuracy under aggressive sparsity.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18034</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.18413</guid>
|
||||||
<pubDate>Mon, 20 Oct 2025 19:14:29 +0000</pubDate>
|
<pubDate>Tue, 21 Oct 2025 08:44:47 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Accelerating Vision Transformers with Adaptive Patch Sizes</title>
|
<title>Search Self-play: Pushing the Frontier of Agent Capability without Supervision</title>
|
||||||
<link>https://arxiv.org/abs/2510.18091</link>
|
<link>https://arxiv.org/abs/2510.18821</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18091.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rohan Choudhury, JungEun Kim, Jinhyung Park, Eunho Yang, László A. Jeni, Kris M. Kitani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses this by using multiple different patch sizes within the same image. APT reduces the total number of input tokens by allocating larger patch sizes in more homogeneous areas and smaller patches in more complex ones. APT achieves a drastic speedup in ViT inference and training, increasing throughput by 40% on ViT-L and 50% on ViT-H while maintaining downstream performance, and can be applied to a previously fine-tuned ViT, converging in as little as 1 epoch. It also significantly reduces training and inference time without loss of performance in high-resolution dense visual tasks, achieving up to 30\% faster training and inference in visual QA, object detection, and semantic segmentation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18821.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongliang Lu, Yuhang Wen, Pengyu Cheng, Ruijin Ding, Haotian Xu, Jiaqi Guo, Chutian Wang, Haonan Chen, Xiaoxi Jiang, Guanjun Jiang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on well-crafted task queries and corresponding ground-truth answers to provide accurate rewards, which requires massive human efforts and hinders the RL scaling processes, especially under agentic scenarios. Although a few recent works explore task synthesis methods, the difficulty of generated agentic tasks can hardly be controlled to provide effective RL training advantages. To achieve agentic RLVR with higher scalability, we explore self-play training for deep search agents, in which the learning LLM utilizes multi-turn search engine calling and acts simultaneously as both a task proposer and a problem solver. The task proposer aims to generate deep search queries with well-defined ground-truth answers and increasing task difficulty. The problem solver tries to handle the generated search queries and output the correct answer predictions. To ensure that each generated search query has accurate ground truth, we collect all the searching results from the proposer's trajectory as external knowledge, then conduct retrieval-augmentation generation (RAG) to test whether the proposed query can be correctly answered with all necessary search documents provided. In this search self-play (SSP) game, the proposer and the solver co-evolve their agent capabilities through both competition and cooperation. With substantial experimental results, we find that SSP can significantly improve search agents' performance uniformly on various benchmarks without any supervision under both from-scratch and continuous RL training setups. The code is at https://github.com/Alibaba-Quark/SSP.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18091</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.18821</guid>
|
||||||
<pubDate>Mon, 20 Oct 2025 20:37:11 +0000</pubDate>
|
<pubDate>Tue, 21 Oct 2025 17:19:35 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection</title>
|
<title>Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall</title>
|
||||||
<link>https://arxiv.org/abs/2510.18909</link>
|
<link>https://arxiv.org/abs/2510.19304</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18909.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongyi He, Xiao Liu, Zhenghao Lin, Mingni Tang, Yi Cheng, Jintao Wang, Wenjie Li, Peng Cheng, Yeyun Gong</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> High-quality pre-training data is crutial for large language models, where quality captures factual reliability and semantic value, and diversity ensures broad coverage and distributional heterogeneity. Existing approaches typically rely on single or multiple-dimensional score-based selection. However, directly selecting top-scored data often degrades performance, and sampling from a broader range is required to recover results. The above non-monotonicity between dataset scores and downstream benchmark results reveals a fundamental bias: score-based methods collapse correlated dimensions, causing top-scored data to appear high-quality while systematically overlooking diversity. We argue that ensuring diversity requires decomposing correlated metrics into orthogonal feature dimensions, from which the top-scored data can be directly selected. Therefore, we proposed the Orthogonal Diversity-Aware Selection (ODiS) algorithm, which preserves both quality and diversity during data selection. First, ODiS evaluates data from multiple dimensions, covering language quality, knowledge quality, and comprehension difficulty. The multi-dimensional scores are then decorrelated via Principal Component Analysis (PCA), yielding orthogonal evaluation dimensions. For each dimension, a Roberta-based scorer is trained to regress the data onto PCA-projected scores, enabling scalable inference on large corpora. Finally, ODiS constructs the training dataset by selecting top-scored data within each orthogonal dimension, thereby ensuring both quality and diversity. Empirical results show that ODiS-selected data exhibit less than 2\% inter-dimension overlap, confirming orthogonality between dimensions. More importantly, models trained with ODiS-selected data significantly outperform other baselines on downstream benchmarks, highlighting the necessity of orthogonal, diversity-aware data selection for LLMs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyu Jo, Jaesik Yoon, Justin Deschenaux, Caglar Gulcehre, Sungjin Ahn</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Discrete diffusion models offer a promising alternative to autoregressive generation through parallel decoding, but they suffer from a sampling wall: once categorical sampling occurs, rich distributional information collapses into one-hot vectors and cannot be propagated across steps, forcing subsequent steps to operate with limited information. To mitigate this problem, we introduce Loopholing, a novel and simple mechanism that preserves this information via a deterministic latent pathway, leading to Loopholing Discrete Diffusion Models (LDDMs). Trained efficiently with a self-conditioning strategy, LDDMs achieve substantial gains-reducing generative perplexity by up to 61% over prior baselines, closing (and in some cases surpassing) the gap with autoregressive models, and producing more coherent text. Applied to reasoning tasks, LDDMs also improve performance on arithmetic benchmarks such as Countdown and Game of 24. These results also indicate that loopholing mitigates idle steps and oscillations, providing a scalable path toward high-quality non-autoregressive text generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18909</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.19304</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 03:37:31 +0000</pubDate>
|
<pubDate>Wed, 22 Oct 2025 07:08:47 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs</title>
|
<title>The Massive Legal Embedding Benchmark (MLEB)</title>
|
||||||
<link>https://arxiv.org/abs/2510.18279</link>
|
<link>https://arxiv.org/abs/2510.19365</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18279.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanhong Li, Zixuan Lan, Jiawei Zhou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while preserving performance? In this paper, we show that visual text representations are a practical and surprisingly effective form of input compression for decoder LLMs. We exploit the idea of rendering long text inputs as a single image and provide it directly to the model. This leads to dramatically reduced number of decoder tokens required, offering a new form of input compression. Through experiments on two distinct benchmarks RULER (long-context retrieval) and CNN/DailyMail (document summarization) we demonstrate that this text-as-image method yields substantial token savings (often nearly half) without degrading task performance.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19365.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Umar Butler, Abdur-Rahman Butler, Adrian Lucas Malec</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We present the Massive Legal Embedding Benchmark (MLEB), the largest, most diverse, and most comprehensive open-source benchmark for legal information retrieval to date. MLEB consists of ten expert-annotated datasets spanning multiple jurisdictions (the US, UK, EU, Australia, Ireland, and Singapore), document types (cases, legislation, regulatory guidance, contracts, and literature), and task types (search, zero-shot classification, and question answering). Seven of the datasets in MLEB were newly constructed in order to fill domain and jurisdictional gaps in the open-source legal information retrieval landscape. We document our methodology in building MLEB and creating the new constituent datasets, and release our code, results, and data openly to assist with reproducible evaluations.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18279</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.19365</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 04:07:20 +0000</pubDate>
|
<pubDate>Wed, 22 Oct 2025 08:38:44 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>OmniNWM: Omniscient Driving Navigation World Models</title>
|
<title>MSC-Bench: A Rigorous Benchmark for Multi-Server Tool Orchestration</title>
|
||||||
<link>https://arxiv.org/abs/2510.18313</link>
|
<link>https://arxiv.org/abs/2510.19423</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bohan Li, Zhuang Ma, Dalong Du, Baorui Peng, Zhujin Liang, Zhenqiang Liu, Chao Ma, Yueming Jin, Hao Zhao, Wenjun Zeng, Xin Jin</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Autonomous driving world models are expected to work effectively across three core dimensions: state, action, and reward. Existing models, however, are typically restricted to limited state modalities, short video sequences, imprecise action control, and a lack of reward awareness. In this paper, we introduce OmniNWM, an omniscient panoramic navigation world model that addresses all three dimensions within a unified framework. For state, OmniNWM jointly generates panoramic videos of RGB, semantics, metric depth, and 3D occupancy. A flexible forcing strategy enables high-quality long-horizon auto-regressive generation. For action, we introduce a normalized panoramic Plucker ray-map representation that encodes input trajectories into pixel-level signals, enabling highly precise and generalizable control over panoramic video generation. Regarding reward, we move beyond learning reward functions with external image-based models: instead, we leverage the generated 3D occupancy to directly define rule-based dense rewards for driving compliance and safety. Extensive experiments demonstrate that OmniNWM achieves state-of-the-art performance in video generation, control accuracy, and long-horizon stability, while providing a reliable closed-loop evaluation framework through occupancy-grounded rewards. Project page is available at https://github.com/Arlo0o/OmniNWM.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19423.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jia-Kai Dong, I-Wei Huang, Chun-Tin Wu, Yi-Tien Tsai</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce MSC-Bench, a large-scale benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents in a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often evaluate tools in isolation, ignoring challenges such as functional overlap and cross-server orchestration, leading to overly optimistic assessments. MSC-Bench addresses these gaps by constructing ground truth through 'equal function sets', allowing objective metrics such as F1 score and reducing the dependency on LLM-as-a-judge evaluation. Organized as a five-level curriculum, it systematically tests agent capabilities from single-tool orchestration to complex cross-server planning, and robustness to out-of-scope requests. Experiments reveal that rigid hierarchies can hinder performance without co-designed strategies, and even state-of-the-art agents exhibit systemic weaknesses in robustness. MSC-Bench provides a diagnostic framework to expose these limitations and guide the development of more capable and efficient tool-using agents. The benchmark and resources are publicly available at https://github.com/snooow1029/MSC_Bench.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18313</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.19423</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 05:49:01 +0000</pubDate>
|
<pubDate>Wed, 22 Oct 2025 09:45:11 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>RIR-Mega: a large-scale simulated room impulse response dataset for machine learning and room acoustics modeling</title>
|
<title>Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1</title>
|
||||||
<link>https://arxiv.org/abs/2510.18917</link>
|
<link>https://arxiv.org/abs/2510.19600</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mandip Goswami</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Room impulse responses are a core resource for dereverberation, robust speech recognition, source localization, and room acoustics estimation. We present RIR-Mega, a large collection of simulated RIRs described by a compact, machine friendly metadata schema and distributed with simple tools for validation and reuse. The dataset ships with a Hugging Face Datasets loader, scripts for metadata checks and checksums, and a reference regression baseline that predicts RT60 like targets from waveforms. On a train and validation split of 36,000 and 4,000 examples, a small Random Forest on lightweight time and spectral features reaches a mean absolute error near 0.013 s and a root mean square error near 0.022 s. We host a subset with 1,000 linear array RIRs and 3,000 circular array RIRs on Hugging Face for streaming and quick tests, and preserve the complete 50,000 RIR archive on Zenodo. The dataset and code are public to support reproducible studies.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianli Ma, Siyu Wang, Yilin Chen, Yinhao Tang, Yixiang Yang, Chang Guo, Bingjie Gao, Zhening Xing, Yanan Sun, Zhipeng Zhang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> In the quest for scientific progress, communicating research is as vital as the discovery itself. Yet, researchers are often sidetracked by the manual, repetitive chore of building project webpages to make their dense papers accessible. While automation has tackled static slides and posters, the dynamic, interactive nature of webpages has remained an unaddressed challenge. To bridge this gap, we reframe the problem, arguing that the solution lies not in a single command, but in a collaborative, hierarchical process. We introduce AutoPage, a novel multi-agent system that embodies this philosophy. AutoPage deconstructs paper-to-page creation into a coarse-to-fine pipeline from narrative planning to multimodal content generation and interactive rendering. To combat AI hallucination, dedicated "Checker" agents verify each step against the source paper, while optional human checkpoints ensure the final product aligns perfectly with the author's vision, transforming the system from a mere tool into a powerful collaborative assistant. To rigorously validate our approach, we also construct PageBench, the first benchmark for this new task. Experiments show AutoPage not only generates high-quality, visually appealing pages but does so with remarkable efficiency in under 15 minutes for less than \0.1. Code and dataset will be released at https://mqleet.github.io/AutoPage_ProjectPage/{Webpage}$.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18917</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.19600</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 06:53:14 +0000</pubDate>
|
<pubDate>Wed, 22 Oct 2025 13:53:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library</title>
|
<title>AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders</title>
|
||||||
<link>https://arxiv.org/abs/2510.18428</link>
|
<link>https://arxiv.org/abs/2510.19779</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minwei Kong, Ao Qu, Xiaotong Guo, Wenbin Ouyang, Chonghe Jiang, Han Zheng, Yining Ma, Dingyi Zhuang, Yuhan Tang, Junyi Li, Hai Wang, Cathy Wu, Jinhua Zhao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Optimization modeling enables critical decisions across industries but remains difficult to automate: informal language must be mapped to precise mathematical formulations and executable solver code. Prior LLM approaches either rely on brittle prompting or costly retraining with limited generalization. We present AlphaOPT, a self-improving experience library that enables an LLM to learn from limited demonstrations (even answers alone, without gold-standard programs) and solver feedback - without annotated reasoning traces or parameter updates. AlphaOPT operates in a continual two-phase cycle: (i) a Library Learning phase that reflects on failed attempts, extracting solver-verified, structured insights as {taxonomy, condition, explanation, example}; and (ii) a Library Evolution phase that diagnoses retrieval misalignments and refines the applicability conditions of stored insights, improving transfer across tasks. This design (1) learns efficiently from limited demonstrations without curated rationales, (2) expands continually without costly retraining by updating the library rather than model weights, and (3) makes knowledge explicit and interpretable for human inspection and intervention. Experiments show that AlphaOPT steadily improves with more data (65% to 72% from 100 to 300 training items) and surpasses the strongest baseline by 7.7% on the out-of-distribution OptiBench dataset when trained only on answers. Code and data are available at: https://github.com/Minw913/AlphaOPT.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuezhou Hu, Jiaxin Guo, Xinyu Feng, Tuo Zhao</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions, which are then verified by a larger target model. The effectiveness of SD hinges on the alignment between these models, which is typically enhanced by Knowledge Distillation (KD). However, conventional KD methods aim to minimize the KL divergence between the draft and target models across all tokens, a goal that is misaligned with the true objective of SD, which is to maximize token acceptance rate. Therefore, draft models often struggle to fully assimilate the target model's knowledge due to capacity constraints, leading to suboptimal performance. To address this challenge, we propose AdaSPEC, a novel method that incorporates selective token filtering into the KD process. AdaSPEC utilizes a reference model to identify and filter out difficult-to-fit tokens, enabling the distillation of a draft model that better aligns with the target model on simpler tokens. This approach improves the overall token acceptance rate without compromising generation quality. We evaluate AdaSPEC across diverse tasks, including arithmetic reasoning, instruction-following, coding, and summarization, using model configurations of 31M/1.4B and 350M/2.7B parameters. Our results demonstrate that AdaSPEC consistently outperforms the state-of-the-art DistillSpec method, achieving higher acceptance rates across all tasks (up to 15\%). The code is publicly available at https://github.com/yuezhouhu/adaspec.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18428</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.19779</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 09:03:26 +0000</pubDate>
|
<pubDate>Wed, 22 Oct 2025 17:13:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping</title>
|
<title>Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets</title>
|
||||||
<link>https://arxiv.org/abs/2510.18927</link>
|
<link>https://arxiv.org/abs/2510.19944</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18927.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Xi, Xin Guo, Yang Nan, Enyu Zhou, Junrui Shen, Wenxiang Chen, Jiaqi Liu, Jixuan Huang, Zhihao Zhang, Honglin Guo, Xun Deng, Zhikai Lei, Miao Zheng, Guoteng Wang, Shuo Zhang, Peng Sun, Rui Zheng, Hang Yan, Tao Gui, Qi Zhang, Xuanjing Huang</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for training--improves sample efficiency, but remains challenging: policy entropy declines sharply, optimization often becomes unstable and may even collapse. Through theoretical and empirical analysis, we identify two key insights: (i) an imbalance in optimization, where negative-advantage samples dominate the policy gradient, suppressing useful behaviors and risking gradient explosions; and (ii) the derived Entropy-Clip Rule, which reveals that the fixed clipping mechanism in PPO-like objectives systematically blocks entropy-increasing updates, thereby driving the policy toward over-exploitation at the expense of exploration. Building on these insights, we propose BAlanced Policy Optimization with Adaptive Clipping (BAPO), a simple yet effective method that dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization. Across diverse off-policy scenarios--including sample replay and partial rollout--BAPO achieves fast, stable, and data-efficient training. On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B, while our 32B BAPO model not only achieves state-of-the-art results among models of the same scale but also outperforms leading proprietary systems like o3-mini and Gemini-2.5-Flash-Thinking.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19944.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiashi Feng, Xiu Li, Jing Lin, Jiahang Liu, Gaohong Liu, Weiqiang Lou, Su Ma, Guang Shi, Qinlong Wang, Jun Wang, Zhongcong Xu, Xuanyu Yi, Zihao Yu, Jianfeng Zhang, Yifan Zhu, Rui Chen, Jinxin Chi, Zixian Du, Li Han, Lixin Huang, Kaihua Jiang, Yuhan Li, Guan Luo, Shuguang Wang, Qianyi Wu, Fan Yang, Junyang Zhang, Xuanmeng Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18927</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.19944</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 12:55:04 +0000</pubDate>
|
<pubDate>Wed, 22 Oct 2025 18:16:32 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>See the Text: From Tokenization to Visual Reading</title>
|
<title>Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication</title>
|
||||||
<link>https://arxiv.org/abs/2510.18840</link>
|
<link>https://arxiv.org/abs/2510.19995</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18840.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ling Xing, Alex Jinpeng Wang, Rui Yan, Hongyu Qu, Zechao Li, Jinhui Tang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> People see text. Humans read by recognizing words as visual objects, including their shapes, layouts, and patterns, before connecting them to meaning, which enables us to handle typos, distorted fonts, and various scripts effectively. Modern large language models (LLMs), however, rely on subword tokenization, fragmenting text into pieces from a fixed vocabulary. While effective for high-resource languages, this approach over-segments low-resource languages, yielding long, linguistically meaningless sequences and inflating computation. In this work, we challenge this entrenched paradigm and move toward a vision-centric alternative. Our method, SeeTok, renders text as images (visual-text) and leverages pretrained multimodal LLMs to interpret them, reusing strong OCR and text-vision alignment abilities learned from large-scale multimodal training. Across three different language tasks, SeeTok matches or surpasses subword tokenizers while requiring 4.43 times fewer tokens and reducing FLOPs by 70.5%, with additional gains in cross-lingual generalization, robustness to typographic noise, and linguistic hierarchy. SeeTok signals a shift from symbolic tokenization to human-like visual reading, and takes a step toward more natural and cognitively inspired language models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Lu, Xun Wang, Simin Ma, Shujian Liu, Sathish Reddy Indurthi, Song Wang, Haoyun Deng, Fei Liu, Kaiqiang Song</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Teamwork in workspace for complex tasks requires diverse communication strategies, but current multi-agent LLM systems lack systematic frameworks for task oriented communication. We introduce Communication to Completion (C2C), a scalable framework that addresses this gap through two key innovations: (1) the Alignment Factor (AF), a novel metric quantifying agent task alignment that directly impacts work efficiency, and (2) a Sequential Action Framework that integrates stepwise execution with intelligent communication decisions. C2C enables agents to make cost aware communication choices, dynamically improving task understanding through targeted interactions. We evaluated C2C on realistic coding workflows across three complexity tiers and team sizes from 5 to 17 agents, comparing against no communication and fixed steps baselines. The results show that C2C reduces the task completion time by about 40% with acceptable communication costs. The framework completes all tasks successfully in standard configurations and maintains effectiveness at scale. C2C establishes both a theoretical foundation for measuring communication effectiveness in multi-agent systems and a practical framework for complex collaborative tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18840</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.19995</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 17:34:48 +0000</pubDate>
|
<pubDate>Wed, 22 Oct 2025 19:48:17 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning</title>
|
<title>Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values</title>
|
||||||
<link>https://arxiv.org/abs/2510.18940</link>
|
<link>https://arxiv.org/abs/2510.20187</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18940.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhi Zhang, Yixian Shen, Congfeng Cao, Ekaterina Shutova</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks, offering strong memory efficiency. However, their representational capacity is often limited, making them less suitable for fine-grained adaptation. In contrast, the latter directly fine-tunes a carefully chosen subset of the original model parameters, allowing for more precise and effective adaptation, but at the cost of significantly increased memory consumption. To reconcile this trade-off, we propose NeuroAda, a novel PEFT method that enables fine-grained model finetuning while maintaining high memory efficiency. Our approach first identifies important parameters (i.e., connections within the network) as in selective adaptation, and then introduces bypass connections for these selected parameters. During finetuning, only the bypass connections are updated, leaving the original model parameters frozen. Empirical results on 23+ tasks spanning both natural language generation and understanding demonstrate that NeuroAda achieves state-of-the-art performance with as little as leq 0.02% trainable parameters, while reducing CUDA memory usage by up to 60%. We release our code here: https://github.com/FightingFighting/NeuroAda.git.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20187.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dian Yu, Yulai Zhao, Kishan Panaganti, Linfeng Song, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We propose Reinforcement Learning with Explicit Human Values (RLEV), a method that aligns Large Language Model (LLM) optimization directly with quantifiable human value signals. While Reinforcement Learning with Verifiable Rewards (RLVR) effectively trains models in objective domains using binary correctness rewards, it overlooks that not all tasks are equally significant. RLEV extends this framework by incorporating human-defined value signals directly into the reward function. Using exam-style data with explicit ground-truth value labels, RLEV consistently outperforms correctness-only baselines across multiple RL algorithms and model scales. Crucially, RLEV policies not only improve value-weighted accuracy but also learn a value-sensitive termination policy: concise for low-value prompts, thorough for high-value ones. We demonstrate this behavior stems from value-weighted gradient amplification on end-of-sequence tokens. Ablation studies confirm the gain is causally linked to value alignment. RLEV remains robust under noisy value signals, such as difficulty-based labels, demonstrating that optimizing for an explicit utility function offers a practical path to aligning LLMs with human priorities.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18940</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20187</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 17:59:24 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 04:15:22 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge</title>
|
<title>ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases</title>
|
||||||
<link>https://arxiv.org/abs/2510.18941</link>
|
<link>https://arxiv.org/abs/2510.20270</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.18941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhilin Wang, Jaehun Jung, Ximing Lu, Shizhe Diao, Ellie Evans, Jiaqi Zeng, Pavlo Molchanov, Yejin Choi, Jan Kautz, Yi Dong</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and short-form question-answering. However, many real-world applications require evaluating LLMs in processing professional documents, synthesizing information, and generating comprehensive reports in response to user queries. We introduce ProfBench: a set of over 7000 response-criterion pairs as evaluated by human-experts with professional knowledge across Physics PhD, Chemistry PhD, Finance MBA and Consulting MBA. We build robust and affordable LLM-Judges to evaluate ProfBench rubrics, by mitigating self-enhancement bias and reducing the cost of evaluation by 2-3 orders of magnitude, to make it fair and accessible to the broader community. Our findings reveal that ProfBench poses significant challenges even for state-of-the-art LLMs, with top-performing models like GPT-5-high achieving only 65.9\% overall performance. Furthermore, we identify notable performance disparities between proprietary and open-weight models and provide insights into the role that extended thinking plays in addressing complex, professional-domain tasks. Data: https://huggingface.co/datasets/nvidia/ProfBench and Code: https://github.com/NVlabs/ProfBench</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20270.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqian Zhong, Aditi Raghunathan, Nicholas Carlini</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The tendency to find and exploit "shortcuts" to complete tasks poses significant risks for reliable assessment and deployment of large language models (LLMs). For example, an LLM agent with access to unit tests may delete failing tests rather than fix the underlying bug. Such behavior undermines both the validity of benchmark results and the reliability of real-world LLM coding assistant deployments. To quantify, study, and mitigate such behavior, we introduce ImpossibleBench, a benchmark framework that systematically measures LLM agents' propensity to exploit test cases. ImpossibleBench creates "impossible" variants of tasks from existing benchmarks like LiveCodeBench and SWE-bench by introducing direct conflicts between the natural-language specification and the unit tests. We measure an agent's "cheating rate" as its pass rate on these impossible tasks, where any pass necessarily implies a specification-violating shortcut. As a practical framework, ImpossibleBench is not just an evaluation but a versatile tool. We demonstrate its utility for: (1) studying model behaviors, revealing more fine-grained details of cheating behaviors from simple test modification to complex operator overloading; (2) context engineering, showing how prompt, test access and feedback loop affect cheating rates; and (3) developing monitoring tools, providing a testbed with verified deceptive solutions. We hope ImpossibleBench serves as a useful framework for building more robust and reliable LLM systems. Our implementation can be found at https://github.com/safety-research/impossiblebench.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.18941</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20270</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 17:59:44 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 06:58:32 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues</title>
|
<title>ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature</title>
|
||||||
<link>https://arxiv.org/abs/2510.19028</link>
|
<link>https://arxiv.org/abs/2510.20362</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19028.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eunsu Kim, Junyeong Park, Juhyun Oh, Kiwoong Park, Seyoung Song, A. Seza Dogruoz, Najoung Kim, Alice Oh</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> As large language models (LLMs) are increasingly used in human-AI interactions, their social reasoning capabilities in interpersonal contexts are critical. We introduce SCRIPTS, a 1k-dialogue dataset in English and Korean, sourced from movie scripts. The task involves evaluating models' social reasoning capability to infer the interpersonal relationships (e.g., friends, sisters, lovers) between speakers in each dialogue. Each dialogue is annotated with probabilistic relational labels (Highly Likely, Less Likely, Unlikely) by native (or equivalent) Korean and English speakers from Korea and the U.S. Evaluating nine models on our task, current proprietary LLMs achieve around 75-80% on the English dataset, whereas their performance on Korean drops to 58-69%. More strikingly, models select Unlikely relationships in 10-25% of their responses. Furthermore, we find that thinking models and chain-of-thought prompting, effective for general reasoning, provide minimal benefits for social reasoning and occasionally amplify social biases. Our findings reveal significant limitations in current LLMs' social reasoning capabilities, highlighting the need for efforts to develop socially-aware language models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20362.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aritra Roy, Enrico Grisan, John Buckeridge, Chiara Gattinoni</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Since the advent of various pre-trained large language models, extracting structured knowledge from scientific text has experienced a revolutionary change compared with traditional machine learning or natural language processing techniques. Despite these advances, accessible automated tools that allow users to construct, validate, and visualise datasets from scientific literature extraction remain scarce. We therefore developed ComProScanner, an autonomous multi-agent platform that facilitates the extraction, validation, classification, and visualisation of machine-readable chemical compositions and properties, integrated with synthesis data from journal articles for comprehensive database creation. We evaluated our framework using 100 journal articles against 10 different LLMs, including both open-source and proprietary models, to extract highly complex compositions associated with ceramic piezoelectric materials and corresponding piezoelectric strain coefficients (d33), motivated by the lack of a large dataset for such materials. DeepSeek-V3-0324 outperformed all models with a significant overall accuracy of 0.82. This framework provides a simple, user-friendly, readily-usable package for extracting highly complex experimental data buried in the literature to build machine learning or deep learning datasets.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19028</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20362</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 19:12:47 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 09:01:44 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Steering Autoregressive Music Generation with Recursive Feature Machines</title>
|
<title>Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence</title>
|
||||||
<link>https://arxiv.org/abs/2510.19127</link>
|
<link>https://arxiv.org/abs/2510.20470</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19127.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Zhao, Daniel Beaglehole, Taylor Berg-Kirkpatrick, Julian McAuley, Zachary Novack</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Controllable music generation remains a significant challenge, with existing methods often requiring model retraining or introducing audible artifacts. We introduce MusicRFM, a framework that adapts Recursive Feature Machines (RFMs) to enable fine-grained, interpretable control over frozen, pre-trained music models by directly steering their internal activations. RFMs analyze a model's internal gradients to produce interpretable "concept directions", or specific axes in the activation space that correspond to musical attributes like notes or chords. We first train lightweight RFM probes to discover these directions within MusicGen's hidden states; then, during inference, we inject them back into the model to guide the generation process in real-time without per-step optimization. We present advanced mechanisms for this control, including dynamic, time-varying schedules and methods for the simultaneous enforcement of multiple musical properties. Our method successfully navigates the trade-off between control and generation quality: we can increase the accuracy of generating a target musical note from 0.23 to 0.82, while text prompt adherence remains within approximately 0.02 of the unsteered baseline, demonstrating effective control with minimal impact on prompt fidelity. We release code to encourage further exploration on RFMs in the music domain.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20470.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kun Ouyang, Yuanxin Liu, Linli Yao, Yishuo Cai, Hao Zhou, Jie Zhou, Fandong Meng, Xu Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Video reasoning, which requires multi-step deduction across frames, remains a major challenge for multimodal large language models (MLLMs). While reinforcement learning (RL)-based methods enhance reasoning capabilities, they often rely on text-only chains that yield ungrounded or hallucinated conclusions. Conversely, frame-retrieval approaches introduce visual grounding but still struggle with inaccurate evidence localization. To address these challenges, we present Conan, a framework for evidence-grounded multi-step video reasoning. Conan identifies contextual and evidence frames, reasons over cross-frame clues, and adaptively decides when to conclude or explore further. To achieve this, we (1) construct Conan-91K, a large-scale dataset of automatically generated reasoning traces that includes frame identification, evidence reasoning, and action decision, and (2) design a multi-stage progressive cold-start strategy combined with an Identification-Reasoning-Action (AIR) RLVR training framework to jointly enhance multi-step visual reasoning. Extensive experiments on six multi-step reasoning benchmarks demonstrate that Conan surpasses the baseline Qwen2.5-VL-7B-Instruct by an average of over 10% in accuracy, achieving state-of-the-art performance. Furthermore, Conan generalizes effectively to long-video understanding tasks, validating its strong scalability and robustness.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19127</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20470</guid>
|
||||||
<pubDate>Tue, 21 Oct 2025 23:23:14 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 12:11:46 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>TheMCPCompany: Creating General-purpose Agents with Task-specific Tools</title>
|
<title>Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence</title>
|
||||||
<link>https://arxiv.org/abs/2510.19286</link>
|
<link>https://arxiv.org/abs/2510.20579</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19286.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Reza Esfandiarpoor, Vishwas Suryanarayanan, Stephen H. Bach, Vishal Chowdhary, Anthony Aue</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Since the introduction of the Model Context Protocol (MCP), the number of available tools for Large Language Models (LLMs) has increased significantly. These task-specific tool sets offer an alternative to general-purpose tools such as web browsers, while being easier to develop and maintain than GUIs. However, current general-purpose agents predominantly rely on web browsers for interacting with the environment. Here, we introduce TheMCPCompany, a benchmark for evaluating tool-calling agents on tasks that involve interacting with various real-world services. We use the REST APIs of these services to create MCP servers, which include over 18,000 tools. We also provide manually annotated ground-truth tools for each task. In our experiments, we use the ground truth tools to show the potential of tool-calling agents for both improving performance and reducing costs assuming perfect tool retrieval. Next, we explore agent performance using tool retrieval to study the real-world practicality of tool-based agents. While all models with tool retrieval perform similarly or better than browser-based agents, smaller models cannot take full advantage of the available tools through retrieval. On the other hand, GPT-5's performance with tool retrieval is very close to its performance with ground-truth tools. Overall, our work shows that the most advanced reasoning models are effective at discovering tools in simpler environments, but seriously struggle with navigating complex enterprise environments. TheMCPCompany reveals that navigating tens of thousands of tools and combining them in non-trivial ways to solve complex problems is still a challenging task for current models and requires both better reasoning and better retrieval models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20579.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Meng, Xiangtai Li, Haochen Wang, Yue Tan, Tao Zhang, Lingdong Kong, Yunhai Tong, Anran Wang, Zhiyang Teng, Yujing Wang, Zhuochen Wang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Most video reasoning models only generate textual reasoning traces without indicating when and where key evidence appears. Recent models such as OpenAI-o3 have sparked wide interest in evidence-centered reasoning for images, yet extending this ability to videos is more challenging, as it requires joint temporal tracking and spatial localization across dynamic scenes. We introduce Open-o3 Video, a non-agent framework that integrates explicit spatio-temporal evidence into video reasoning, and carefully collect training data and design training strategies to address the aforementioned challenges. The model highlights key timestamps, objects, and bounding boxes alongside its answers, allowing reasoning to be grounded in concrete visual observations. To enable this functionality, we first curate and build two high-quality datasets, STGR-CoT-30k for SFT and STGR-RL-36k for RL, with carefully constructed temporal and spatial annotations, since most existing datasets offer either temporal spans for videos or spatial boxes on images, lacking unified spatio-temporal supervision and reasoning traces. Then, we adopt a cold-start reinforcement learning strategy with multiple specially designed rewards that jointly encourage answer accuracy, temporal alignment, and spatial precision. On V-STAR benchmark, Open-o3 Video achieves state-of-the-art performance, raising mAM by 14.4% and mLGM by 24.2% on the Qwen2.5-VL baseline. Consistent improvements are also observed on a broad range of video understanding benchmarks, including VideoMME, WorldSense, VideoMMMU, and TVGBench. Beyond accuracy, the reasoning traces produced by Open-o3 Video also provide valuable signals for test-time scaling, enabling confidence-aware verification and improving answer reliability.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19286</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20579</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 06:42:01 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 14:05:56 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Unified Reinforcement and Imitation Learning for Vision-Language Models</title>
|
<title>From Masks to Worlds: A Hitchhiker's Guide to World Models</title>
|
||||||
<link>https://arxiv.org/abs/2510.19307</link>
|
<link>https://arxiv.org/abs/2510.20668</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19307.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro, Yu-Chiang Frank Wang, Yueh-Hua Wu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful, lightweight VLMs. RIL distinctively combines the strengths of reinforcement learning with adversarial imitation learning. This enables smaller student VLMs not only to mimic the sophisticated text generation of large teacher models but also to systematically improve their generative capabilities through reinforcement signals. Key to our imitation framework is an LLM-based discriminator that adeptly distinguishes between student and teacher outputs, complemented by guidance from multiple large teacher VLMs to ensure diverse learning. This unified learning strategy, leveraging both reinforcement and imitation, empowers student models to achieve significant performance gains, making them competitive with leading closed-source VLMs. Extensive experiments on diverse vision-language benchmarks demonstrate that RIL significantly narrows the performance gap with state-of-the-art open- and closed-source VLMs and, in several instances, surpasses them.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinbin Bai, Yu Lei, Hecong Wu, Yuchen Zhu, Shufan Li, Yi Xin, Xiangtai Li, Molei Tao, Aditya Grover, Ming-Hsuan Yang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> This is not a typical survey of world models; it is a guide for those who want to build worlds. We do not aim to catalog every paper that has ever mentioned a ``world model". Instead, we follow one clear road: from early masked models that unified representation learning across modalities, to unified architectures that share a single paradigm, then to interactive generative models that close the action-perception loop, and finally to memory-augmented systems that sustain consistent worlds over time. We bypass loosely related branches to focus on the core: the generative heart, the interactive loop, and the memory system. We show that this is the most promising path towards true world models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19307</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20668</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 07:12:14 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 15:46:44 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints</title>
|
<title>Thought Communication in Multiagent Collaboration</title>
|
||||||
<link>https://arxiv.org/abs/2510.19316</link>
|
<link>https://arxiv.org/abs/2510.20733</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19316.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kailin Jiang, Hongbo Jiang, Ning Jiang, Zhi Gao, Jinhe Bi, Yuchen Ren, Bin Li, Yuntao Du, Lei Liu, Qing Li</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world developments, which hinders continuous knowledge acquisition. Effective knowledge injection thus becomes critical, involving two goals: knowledge adaptation (injecting new knowledge) and knowledge retention (preserving old knowledge). Existing methods often struggle to learn new knowledge and suffer from catastrophic forgetting. To address this, we propose KORE, a synergistic method of KnOwledge-oRientEd augmentations and constraints for injecting new knowledge into large multimodal models while preserving old knowledge. Unlike general text or image data augmentation, KORE automatically converts individual knowledge items into structured and comprehensive knowledge to ensure that the model accurately learns new knowledge, enabling accurate adaptation. Meanwhile, KORE stores previous knowledge in the covariance matrix of LMM's linear layer activations and initializes the adapter by projecting the original weights into the matrix's null space, defining a fine-tuning direction that minimizes interference with previous knowledge, enabling powerful retention. Extensive experiments on various LMMs, including LLaVA-v1.5-7B, LLaVA-v1.5-13B, and Qwen2.5-VL-7B, show that KORE achieves superior new knowledge injection performance and effectively mitigates catastrophic forgetting.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20733.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujia Zheng, Zhuokai Zhao, Zijian Li, Yaqi Xie, Mingze Gao, Lizhu Zhang, Kun Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Natural language has long enabled human cooperation, but its lossy, ambiguous, and indirect nature limits the potential of collective intelligence. While machines are not subject to these constraints, most LLM-based multi-agent systems still rely solely on natural language, exchanging tokens or their embeddings. To go beyond language, we introduce a new paradigm, thought communication, which enables agents to interact directly mind-to-mind, akin to telepathy. To uncover these latent thoughts in a principled way, we formalize the process as a general latent variable model, where agent states are generated by an unknown function of underlying thoughts. We prove that, in a nonparametric setting without auxiliary information, both shared and private latent thoughts between any pair of agents can be identified. Moreover, the global structure of thought sharing, including which agents share which thoughts and how these relationships are structured, can also be recovered with theoretical guarantees. Guided by the established theory, we develop a framework that extracts latent thoughts from all agents prior to communication and assigns each agent the relevant thoughts, along with their sharing patterns. This paradigm naturally extends beyond LLMs to all modalities, as most observational data arise from hidden generative processes. Experiments on both synthetic and real-world benchmarks validate the theory and demonstrate the collaborative advantages of thought communication. We hope this work illuminates the potential of leveraging the hidden world, as many challenges remain unsolvable through surface-level observation alone, regardless of compute or data scale.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19316</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20733</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 07:26:55 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 16:48:02 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents</title>
|
<title>DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion</title>
|
||||||
<link>https://arxiv.org/abs/2510.19336</link>
|
<link>https://arxiv.org/abs/2510.20766</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19336.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Shi, Jun Yang, Ni Yang, Binqiang Pan, Qingsong Xie, Chao Zhang, Zhenyu Yang, Tianhuang Su, Haonan Lu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Mobile Phone Agents (MPAs) have emerged as a promising research direction due to their broad applicability across diverse scenarios. While Multimodal Large Language Models (MLLMs) serve as the foundation for MPAs, their effectiveness in handling multiple mobile phone tasks simultaneously remains limited. Although multitask supervised fine-tuning (SFT) is widely adopted for multitask learning, existing approaches struggle to determine optimal training data compositions for peak performance. To address this challenge, we propose DaMo (Data Mixture Optimizer) - a novel solution employing a trainable network that predicts optimal data mixtures by forecasting downstream task performance for any given dataset ratio. To support comprehensive evaluation, we introduce PhoneAgentBench, the first specialized benchmark to evaluate MLLMs on multimodal mobile phone tasks, comprising 1235 QA pairs spanning diverse real-world industrial mobile application scenarios. Demonstrating strong predictive capability (R^2=0.81) in small-scale pilot experiments, DaMo efficiently extrapolates optimal data mixing configurations. Our results show DaMo achieves a 3.38% performance improvement on PhoneAgentBench compared to alternative methods. Furthermore, extensive experiments across established benchmarks including BFCL-v3, MME-Reasoning, MME-Perception, and OCRBench reveal DaMo's superior generalization, outperforming other approaches by 2.57% in terms of average score. When used solely for MLLM optimization on the BFCL-v3 task, DaMo improves the metrics by 12.47% than other methods. Notably, DaMo maintains robust scalability, preserving its effectiveness when applied to other model architectures. The code and dataset are available at https://github.com/OPPO-Mente-Lab/DaMo.git</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Noam Issachar, Guy Yariv, Sagie Benaim, Yossi Adi, Dani Lischinski, Raanan Fattal</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention mechanism's quadratic scaling with the number of image tokens. In this paper, we introduce Dynamic Position Extrapolation (DyPE), a novel, training-free method that enables pre-trained diffusion transformers to synthesize images at resolutions far beyond their training data, with no additional sampling cost. DyPE takes advantage of the spectral progression inherent to the diffusion process, where low-frequency structures converge early, while high-frequencies take more steps to resolve. Specifically, DyPE dynamically adjusts the model's positional encoding at each diffusion step, matching their frequency spectrum with the current stage of the generative process. This approach allows us to generate images at resolutions that exceed the training resolution dramatically, e.g., 16 million pixels using FLUX. On multiple benchmarks, DyPE consistently improves performance and achieves state-of-the-art fidelity in ultra-high-resolution image generation, with gains becoming even more pronounced at higher resolutions. Project page is available at https://noamissachar.github.io/DyPE/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19336</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20766</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 07:57:59 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 17:42:14 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning</title>
|
<title>AlphaFlow: Understanding and Improving MeanFlow Models</title>
|
||||||
<link>https://arxiv.org/abs/2510.19338</link>
|
<link>https://arxiv.org/abs/2510.20771</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ling Team, Bin Han, Caizhi Tang, Chen Liang, Donghao Zhang, Fan Yuan, Feng Zhu, Jie Gao, Jingyu Hu, Longfei Li, Meng Li, Mingyang Zhang, Peijie Jiang, Peng Jiao, Qian Zhao, Qingyuan Yang, Wenbo Shen, Xinxing Yang, Yalin Zhang, Yankun Ren, Yao Zhao, Yibo Cao, Yixuan Sun, Yue Zhang, Yuchen Fang, Zibin Lin, Zixuan Cheng, Jun Zhou</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B parameters and 957M activations, while Ring-flash-linear-2.0 contains 104B parameters and 6.1B activations. Both models adopt a hybrid architecture that effectively integrates linear attention and softmax attention, significantly reducing I/O and computational overhead in long-context inference scenarios. Compared to a 32 billion parameter dense model, this series reduces inference cost to 1/10, and compared to the original Ring series, the cost is also reduced by over 50%. Furthermore, through systematic exploration of the ratio between different attention mechanisms in the hybrid architecture, we have identified the currently optimal model structure. Additionally, by leveraging our self-developed high-performance FP8 operator library-linghe, overall training efficiency has been improved by 50%. Benefiting from the high alignment between the training and inference engine operators, the models can undergo long-term, stable, and highly efficient optimization during the reinforcement learning phase, consistently maintaining SOTA performance across multiple challenging complex reasoning benchmarks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20771.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huijie Zhang, Aliaksandr Siarohin, Willi Menapace, Michael Vasilkovsky, Sergey Tulyakov, Qing Qu, Ivan Skorokhodov</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> MeanFlow has recently emerged as a powerful framework for few-step generative modeling trained from scratch, but its success is not yet fully understood. In this work, we show that the MeanFlow objective naturally decomposes into two parts: trajectory flow matching and trajectory consistency. Through gradient analysis, we find that these terms are strongly negatively correlated, causing optimization conflict and slow convergence. Motivated by these insights, we introduce alpha-Flow, a broad family of objectives that unifies trajectory flow matching, Shortcut Model, and MeanFlow under one formulation. By adopting a curriculum strategy that smoothly anneals from trajectory flow matching to MeanFlow, alpha-Flow disentangles the conflicting objectives, and achieves better convergence. When trained from scratch on class-conditional ImageNet-1K 256x256 with vanilla DiT backbones, alpha-Flow consistently outperforms MeanFlow across scales and settings. Our largest alpha-Flow-XL/2+ model achieves new state-of-the-art results using vanilla DiT backbones, with FID scores of 2.58 (1-NFE) and 2.15 (2-NFE).</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19338</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20771</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 07:59:38 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 17:45:06 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts</title>
|
<title>ARGenSeg: Image Segmentation with Autoregressive Image Generation Model</title>
|
||||||
<link>https://arxiv.org/abs/2510.19363</link>
|
<link>https://arxiv.org/abs/2510.20803</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Wang, Gaokai Zhang, Li Lyna Zhang, Ning Shang, Fan Yang, Dongyao Chen, Mao Yang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context reasoning by inducing "Aha" moments in chain-of-thought, the advanced thinking patterns required for long-context reasoning remain largely unexplored, and high-difficulty RL data are scarce. In this paper, we introduce LoongRL, a data-driven RL method for advanced long-context reasoning. Central to LoongRL is KeyChain, a synthesis approach that transforms short multi-hop QA into high-difficulty long-context tasks by inserting UUID chains that hide the true question among large collections of distracting documents. Solving these tasks requires the model to trace the correct chain step-by-step, identify the true question, retrieve relevant facts and reason over them to answer correctly. RL training on KeyChain data induces an emergent plan-retrieve-reason-recheck reasoning pattern that generalizes far beyond training length. Models trained at 16K effectively solve 128K tasks without prohibitive full-length RL rollout costs. On Qwen2.5-7B and 14B, LoongRL substantially improves long-context multi-hop QA accuracy by +23.5% and +21.1% absolute gains. The resulting LoongRL-14B reaches a score of 74.2, rivaling much larger frontier models such as o3-mini (74.5) and DeepSeek-R1 (74.9). It also improves long-context retrieval, passes all 128K needle-in-a-haystack stress tests, and preserves short-context reasoning capabilities.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaolong Wang, Lixiang Ru, Ziyuan Huang, Kaixiang Ji, Dandan Zheng, Jingdong Chen, Jun Zhou</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level perception within a unified framework. Prior works integrating image segmentation into multimodal large language models (MLLMs) typically employ either boundary points representation or dedicated segmentation heads. These methods rely on discrete representations or semantic prompts fed into task-specific decoders, which limits the ability of the MLLM to capture fine-grained visual details. To address these challenges, we introduce a segmentation framework for MLLM based on image generation, which naturally produces dense masks for target objects. We leverage MLLM to output visual tokens and detokenize them into images using an universal VQ-VAE, making the segmentation fully dependent on the pixel-level understanding of the MLLM. To reduce inference latency, we employ a next-scale-prediction strategy to generate required visual tokens in parallel. Extensive experiments demonstrate that our method surpasses prior state-of-the-art approaches on multiple segmentation datasets with a remarkable boost in inference speed, while maintaining strong understanding capabilities.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19363</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20803</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 08:35:28 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 17:58:26 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ColorAgent: Building A Robust, Personalized, and Interactive OS Agent</title>
|
<title>LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas</title>
|
||||||
<link>https://arxiv.org/abs/2510.19386</link>
|
<link>https://arxiv.org/abs/2510.20820</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19386.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ning Li, Qiqiang Lin, Zheng Wu, Xiaoyun Mo, Weiming Zhang, Yin Zhao, Xiangmou Qu, Jiamu Zhou, Jun Wang, Congmin Zheng, Yuanyi Song, Hongjiang Chen, Heyuan Huang, Jihong Wang, Jiaxin Yin, Jingwei Yu, Junwei Liao, Qiuying Peng, Xingyu Lou, Jun Wang, Weiwen Liu, Zhuosheng Zhang, Weinan Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> With the advancements in hardware, software, and large language model technologies, the interaction between humans and operating systems has evolved from the command-line interface to the rapidly emerging AI agent interactions. Building an operating system (OS) agent capable of executing user instructions and faithfully following user desires is becoming a reality. In this technical report, we present ColorAgent, an OS agent designed to engage in long-horizon, robust interactions with the environment while also enabling personalized and proactive user interaction. To enable long-horizon interactions with the environment, we enhance the model's capabilities through step-wise reinforcement learning and self-evolving training, while also developing a tailored multi-agent framework that ensures generality, consistency, and robustness. In terms of user interaction, we explore personalized user intent recognition and proactive engagement, positioning the OS agent not merely as an automation tool but as a warm, collaborative partner. We evaluate ColorAgent on the AndroidWorld and AndroidLab benchmarks, achieving success rates of 77.2% and 50.7%, respectively, establishing a new state of the art. Nonetheless, we note that current benchmarks are insufficient for a comprehensive evaluation of OS agents and propose further exploring directions in future work, particularly in the areas of evaluation paradigms, agent collaboration, and security. Our code is available at https://github.com/MadeAgents/mobile-use.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20820.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guocheng Gordon Qian, Ruihang Zhang, Tsai-Shien Chen, Yusuf Dalva, Anujraaj Argo Goyal, Willi Menapace, Ivan Skorokhodov, Meng Dong, Arpit Sahni, Daniil Ostashev, Ju Hu, Sergey Tulyakov, Kuan-Chieh Jackson Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Despite their impressive visual fidelity, existing personalized generative models lack interactive control over spatial composition and scale poorly to multiple subjects. To address these limitations, we present LayerComposer, an interactive framework for personalized, multi-subject text-to-image generation. Our approach introduces two main contributions: (1) a layered canvas, a novel representation in which each subject is placed on a distinct layer, enabling occlusion-free composition; and (2) a locking mechanism that preserves selected layers with high fidelity while allowing the remaining layers to adapt flexibly to the surrounding context. Similar to professional image-editing software, the proposed layered canvas allows users to place, resize, or lock input subjects through intuitive layer manipulation. Our versatile locking mechanism requires no architectural changes, relying instead on inherent positional embeddings combined with a new complementary data sampling strategy. Extensive experiments demonstrate that LayerComposer achieves superior spatial control and identity preservation compared to the state-of-the-art methods in multi-subject personalized image generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19386</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20820</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 09:02:48 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 17:59:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>GigaBrain-0: A World Model-Powered Vision-Language-Action Model</title>
|
<title>HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives</title>
|
||||||
<link>https://arxiv.org/abs/2510.19430</link>
|
<link>https://arxiv.org/abs/2510.20822</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19430.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> GigaBrain Team, Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang, Guosheng Zhao, Haoyun Li, Jie Li, Jiagang Zhu, Lv Feng, Peng Li, Qiuping Deng, Runqi Ouyang, Wenkang Qin, Xinze Chen, Xiaofeng Wang, Yang Wang, Yifan Li, Yilong Li, Yiran Ding, Yuan Xu, Yun Ye, Yukun Zhou, Zhehao Dong, Zhenan Wang, Zhichao Liu, Zheng Zhu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Training Vision-Language-Action (VLA) models for generalist robots typically requires large-scale real-world robot data, which is expensive and time-consuming to collect. The inefficiency of physical data collection severely limits the scalability, and generalization capacity of current VLA systems. To address this challenge, we introduce GigaBrain-0, a novel VLA foundation model empowered by world model-generated data (e.g., video generation, real2real transfer, human transfer, view transfer, sim2real transfer data). By leveraging world models to generate diverse data at scale, GigaBrain-0 significantly reduces reliance on real robot data while improving cross-task generalization. Our approach further improves policy robustness through RGBD input modeling and embodied Chain-of-Thought (CoT) supervision, enabling the model to reason about spatial geometry, object states, and long-horizon dependencies during task execution. This leads to substantial gains in real-world performance on dexterous, long-horizon, and mobile manipulation tasks. Extensive experiments demonstrate that GigaBrain-0 achieves superior generalization across variations in appearances (e.g., textures, colors), object placements, and camera viewpoints. Additionally, we present GigaBrain-0-Small, an optimized lightweight variant designed to run efficiently on devices such as the NVIDIA Jetson AGX Orin.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.20822.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihao Meng, Hao Ouyang, Yue Yu, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Hanlin Wang, Yixuan Li, Cheng Chen, Yanhong Zeng, Yujun Shen, Huamin Qu</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this "narrative gap" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot to the last. Our architecture achieves precise directorial control through a Window Cross-Attention mechanism that localizes text prompts to specific shots, while a Sparse Inter-Shot Self-Attention pattern (dense within shots but sparse between them) ensures the efficiency required for minute-scale generation. Beyond setting a new state-of-the-art in narrative coherence, HoloCine develops remarkable emergent abilities: a persistent memory for characters and scenes, and an intuitive grasp of cinematic techniques. Our work marks a pivotal shift from clip synthesis towards automated filmmaking, making end-to-end cinematic creation a tangible future. Our code is available at: https://holo-cine.github.io/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19430</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2510.20822</guid>
|
||||||
<pubDate>Wed, 22 Oct 2025 09:57:13 +0000</pubDate>
|
<pubDate>Thu, 23 Oct 2025 17:59:59 +0000</pubDate>
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models</title>
|
|
||||||
<link>https://arxiv.org/abs/2510.19457</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19457.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kailin Jiang, Ning Jiang, Yuchen Ren, Yuchen Li, Yifan Gao, Jinhe Bi, Yunpu Ma, Qingqing Liu, Xianhao Wang, Yifan Jia, Hongbo Jiang, Yaocong Hu, Bin Li, Lei Liu, Yuntao Du</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Multimodal Models (LMMs) encode rich factual knowledge via cross-modal pre-training, yet their static representations struggle to maintain an accurate understanding of time-sensitive factual knowledge. Existing benchmarks remain constrained by static designs, inadequately evaluating LMMs' ability to understand time-sensitive knowledge. To address this gap, we propose MINED, a comprehensive benchmark that evaluates temporal awareness along 6 key dimensions and 11 challenging tasks: cognition, awareness, trustworthiness, understanding, reasoning, and robustness. MINED is constructed from Wikipedia by two professional annotators, containing 2,104 time-sensitive knowledge samples spanning six knowledge types. Evaluating 15 widely used LMMs on MINED shows that Gemini-2.5-Pro achieves the highest average CEM score of 63.07, while most open-source LMMs still lack time understanding ability. Meanwhile, LMMs perform best on organization knowledge, whereas their performance is weakest on sport. To address these challenges, we investigate the feasibility of updating time-sensitive knowledge in LMMs through knowledge editing methods and observe that LMMs can effectively update knowledge via knowledge editing methods in single editing scenarios.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19457</guid>
|
|
||||||
<pubDate>Wed, 22 Oct 2025 10:41:57 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos</title>
|
|
||||||
<link>https://arxiv.org/abs/2510.19488</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19488.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dunjie Lu, Yiheng Xu, Junli Wang, Haoyuan Wu, Xinyuan Wang, Zekun Wang, Junlin Yang, Hongjin Su, Jixuan Chen, Junda Chen, Yuchen Mao, Jingren Zhou, Junyang Lin, Binyuan Hui, Tao Yu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Training computer-use agents requires massive amounts of GUI interaction data, but manually annotating action trajectories at scale is prohibitively expensive. We present VideoAgentTrek, a scalable pipeline that automatically mines training data from publicly available screen-recorded videos at web scale, eliminating the need for manual annotation. Our approach addresses a key challenge: raw videos contain implicit demonstrations but lack explicit action labels. To solve this, we develop Video2Action, an inverse dynamics module (IDM) with two components: (1) a video grounding model that detects and localizes GUI actions with precise temporal boundaries and context, and (2) an action-content recognizer that extracts structured parameters like click coordinates and typed text with high fidelity. Applied to 39,000 YouTube tutorial videos, our pipeline generates 1.52 million interaction steps automatically. We leverage this data through continued pretraining followed by supervised fine-tuning. On OSWorld-Verified, our approach improves task success rates from 9.3% (SFT-only baseline) to 15.8%, a 70% relative improvement. On AgentNetBench, step accuracy increases from 64.1% to 69.3%. Our results demonstrate that passive internet videos can be transformed into high-quality supervision for computer-use agents, providing a scalable alternative to expensive manual annotation.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19488</guid>
|
|
||||||
<pubDate>Wed, 22 Oct 2025 11:25:48 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Machine Text Detectors are Membership Inference Attacks</title>
|
|
||||||
<link>https://arxiv.org/abs/2510.19492</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19492.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ryuto Koike, Liam Dugan, Masahiro Kaneko, Chris Callison-Burch, Naoaki Okazaki</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Although membership inference attacks (MIAs) and machine-generated text detection target different goals, identifying training samples and synthetic texts, their methods often exploit similar signals based on a language model's probability distribution. Despite this shared methodological foundation, the two tasks have been independently studied, which may lead to conclusions that overlook stronger methods and valuable insights developed in the other task. In this work, we theoretically and empirically investigate the transferability, i.e., how well a method originally developed for one task performs on the other, between MIAs and machine text detection. For our theoretical contribution, we prove that the metric that achieves the asymptotically highest performance on both tasks is the same. We unify a large proportion of the existing literature in the context of this optimal metric and hypothesize that the accuracy with which a given method approximates this metric is directly correlated with its transferability. Our large-scale empirical experiments, including 7 state-of-the-art MIA methods and 5 state-of-the-art machine text detectors across 13 domains and 10 generators, demonstrate very strong rank correlation (rho > 0.6) in cross-task performance. We notably find that Binoculars, originally designed for machine text detection, achieves state-of-the-art performance on MIA benchmarks as well, demonstrating the practical impact of the transferability. Our findings highlight the need for greater cross-task awareness and collaboration between the two research communities. To facilitate cross-task developments and fair evaluations, we introduce MINT, a unified evaluation suite for MIAs and machine-generated text detection, with implementation of 15 recent methods from both tasks.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19492</guid>
|
|
||||||
<pubDate>Wed, 22 Oct 2025 11:39:01 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation</title>
|
|
||||||
<link>https://arxiv.org/abs/2510.19592</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Su Ho Han, Jeongseok Hyun, Pilhyeon Lee, Minho Shim, Dongyoon Wee, Seon Joo Kim</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Multimodal large language models (MLLMs) demonstrate strong video understanding by attending to visual tokens relevant to textual queries. To directly adapt this for localization in a training-free manner, we cast video reasoning segmentation as a video QA task and extract attention maps via rollout mechanism. However, raw attention maps are noisy and poorly aligned with object regions. We propose Decomposed Attention Fusion (DecAF), which refines these maps through two mechanisms: (1) contrastive object-background fusion and (2) complementary video-frame fusion. This method suppresses irrelevant activations and enhances object-focused cues, enabling direct conversion of attention maps into coarse segmentation masks. In addition, we introduce attention-guided SAM2 prompting for obtaining fine-grained masks. Unlike existing methods that jointly train MLLMs with SAM, our method operates entirely without retraining. DecAF outperforms training-free methods and achieves performance comparable to training-based methods on both referring and reasoning VOS benchmarks. The code will be available at https://github.com/HYUNJS/DecAF.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19592</guid>
|
|
||||||
<pubDate>Wed, 22 Oct 2025 13:42:59 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>When Do Transformers Learn Heuristics for Graph Connectivity?</title>
|
|
||||||
<link>https://arxiv.org/abs/2510.19753</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19753.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qilin Ye, Deqing Fu, Robin Jia, Vatsal Sharan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Transformers often fail to learn generalizable algorithms, instead relying on brittle heuristics. Using graph connectivity as a testbed, we explain this phenomenon both theoretically and empirically. We consider a simplified Transformer architecture, the disentangled Transformer, and prove that an L-layer model has capacity to solve for graphs with diameters up to exactly 3^L, implementing an algorithm equivalent to computing powers of the adjacency matrix. We analyze the training-dynamics, and show that the learned strategy hinges on whether most training instances are within this model capacity. Within-capacity graphs (diameter leq 3^L) drive the learning of a correct algorithmic solution while beyond-capacity graphs drive the learning of a simple heuristic based on node degrees. Finally, we empirically demonstrate that restricting training data within a model's capacity leads to both standard and disentangled transformers learning the exact algorithm rather than the degree-based heuristic.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19753</guid>
|
|
||||||
<pubDate>Wed, 22 Oct 2025 16:43:32 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing</title>
|
|
||||||
<link>https://arxiv.org/abs/2510.19808</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yusu Qian, Eli Bocek-Rivele, Liangchen Song, Jialing Tong, Yinfei Yang, Jiasen Lu, Wenze Hu, Zhe Gan</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Recent advances in multimodal models have demonstrated remarkable text-guided image editing capabilities, with systems like GPT-4o and Nano-Banana setting new benchmarks. However, the research community's progress remains constrained by the absence of large-scale, high-quality, and openly accessible datasets built from real images. We introduce Pico-Banana-400K, a comprehensive 400K-image dataset for instruction-based image editing. Our dataset is constructed by leveraging Nano-Banana to generate diverse edit pairs from real photographs in the OpenImages collection. What distinguishes Pico-Banana-400K from previous synthetic datasets is our systematic approach to quality and diversity. We employ a fine-grained image editing taxonomy to ensure comprehensive coverage of edit types while maintaining precise content preservation and instruction faithfulness through MLLM-based quality scoring and careful curation. Beyond single turn editing, Pico-Banana-400K enables research into complex editing scenarios. The dataset includes three specialized subsets: (1) a 72K-example multi-turn collection for studying sequential editing, reasoning, and planning across consecutive modifications; (2) a 56K-example preference subset for alignment research and reward model training; and (3) paired long-short editing instructions for developing instruction rewriting and summarization capabilities. By providing this large-scale, high-quality, and task-rich resource, Pico-Banana-400K establishes a robust foundation for training and benchmarking the next generation of text-guided image editing models.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19808</guid>
|
|
||||||
<pubDate>Wed, 22 Oct 2025 17:43:15 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>olmOCR 2: Unit Test Rewards for Document OCR</title>
|
|
||||||
<link>https://arxiv.org/abs/2510.19817</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19817.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jake Poznanski, Luca Soldaini, Kyle Lo</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present olmOCR 2, the latest in our family of powerful OCR systems for converting digitized print documents, like PDFs, into clean, naturally ordered plain text. olmOCR 2 is powered by olmOCR-2-7B-1025, a specialized, 7B vision language model (VLM) trained using reinforcement learning with verifiable rewards (RLVR), where our rewards are a diverse set of binary unit tests. To scale unit test creation, we develop a pipeline for generating synthetic documents with diverse and challenging layouts, known ground-truth HTML source code, and extracted test cases. We show that RL training on these test cases results in state-of-the-art performance on olmOCR-Bench, our English-language OCR benchmark, with the largest improvements in math formula conversion, table parsing, and multi-column layouts compared to previous versions. We release our model, data and code under permissive open licenses.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.19817</guid>
|
|
||||||
<pubDate>Wed, 22 Oct 2025 17:53:02 +0000</pubDate>
|
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user