bot: update RSS feed
This commit is contained in:
github-actions[bot]
324
feed.xml
324
feed.xml
@@ -7,202 +7,244 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Tue, 21 Oct 2025 00:02:43 +0000</lastBuildDate>
|
||||
<lastBuildDate>Wed, 22 Oct 2025 00:02:51 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs</title>
|
||||
<link>https://arxiv.org/abs/2510.11288</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11288.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Afonin, Nikita Andriyanov, Nikhil Bageshpura, Kyle Liu, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Alexander Panchenko, Oleg Rogov, Elena Tutubalina, Mikhail Seleznyov</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to finetuning and activation steering, leaving out in-context learning (ICL). We therefore ask: does EM emerge in ICL? We find that it does: across three datasets, three frontier models produce broadly misaligned responses at rates between 2% and 17% given 64 narrow in-context examples, and up to 58% with 256 examples. We also examine mechanisms of EM by eliciting step-by-step reasoning (while leaving in-context examples unchanged). Manual analysis of the resulting chain-of-thought shows that 67.5% of misaligned traces explicitly rationalize harmful outputs by adopting a reckless or dangerous ''persona'', echoing prior results on finetuning-induced EM.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11288</guid>
|
||||
<pubDate>Mon, 13 Oct 2025 11:23:56 +0000</pubDate>
|
||||
<title>Test-Time Scaling of Reasoning Models for Machine Translation</title>
|
||||
<link>https://arxiv.org/abs/2510.06471</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06471.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Li, Shaoxiong Ji, Jörg Tiedemann</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Test-time scaling (TTS) has enhanced the performance of Reasoning Models (RMs) on various tasks such as math and coding, yet its efficacy in machine translation (MT) remains underexplored. This paper investigates whether increased inference-time computation improves translation quality. We evaluate 12 RMs across a diverse suite of MT benchmarks spanning multiple domains, examining three scenarios: direct translation, forced-reasoning extrapolation, and post-editing. Our findings show that for general-purpose RMs, TTS provides limited and inconsistent benefits for direct translation, with performance quickly plateauing. However, the effectiveness of TTS is unlocked by domain-specific fine-tuning, which aligns a model's reasoning process with task requirements, leading to consistent improvements up to an optimal, self-determined reasoning depth. We also find that forcing a model to reason beyond its natural stopping point consistently degrades translation quality. In contrast, TTS proves highly effective in a post-editing context, reliably turning self-correction into a beneficial process. These results indicate that the value of inference-time computation in MT lies not in enhancing single-pass translation with general models, but in targeted applications like multi-step, self-correction workflows and in conjunction with task-specialized models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06471</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 21:15:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Do LLMs "Feel"? Emotion Circuits Discovery and Control</title>
|
||||
<link>https://arxiv.org/abs/2510.11328</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.11328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenxi Wang, Yixuan Zhang, Ruiji Yu, Yufei Zheng, Lang Gao, Zirui Song, Zixiang Xu, Gus Xia, Huishuai Zhang, Dongyan Zhao, Xiuying Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> As the demand for emotional intelligence in large language models (LLMs) grows, a key challenge lies in understanding the internal mechanisms that give rise to emotional expression and in controlling emotions in generated text. This study addresses three core questions: (1) Do LLMs contain context-agnostic mechanisms shaping emotional expression? (2) What form do these mechanisms take? (3) Can they be harnessed for universal emotion control? We first construct a controlled dataset, SEV (Scenario-Event with Valence), to elicit comparable internal states across emotions. Subsequently, we extract context-agnostic emotion directions that reveal consistent, cross-context encoding of emotion (Q1). We identify neurons and attention heads that locally implement emotional computation through analytical decomposition and causal analysis, and validate their causal roles via ablation and enhancement interventions. Next, we quantify each sublayer's causal influence on the model's final emotion representation and integrate the identified local components into coherent global emotion circuits that drive emotional expression (Q2). Directly modulating these circuits achieves 99.65% emotion-expression accuracy on the test set, surpassing prompting- and steering-based methods (Q3). To our knowledge, this is the first systematic study to uncover and validate emotion circuits in LLMs, offering new insights into interpretability and controllable emotional intelligence.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.11328</guid>
|
||||
<pubDate>Mon, 13 Oct 2025 12:24:24 +0000</pubDate>
|
||||
<title>Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering</title>
|
||||
<link>https://arxiv.org/abs/2510.14605</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyang Hong, Jiaqi Gu, Qi Yang, Lubin Fan, Yue Wu, Ying Wang, Kun Ding, Shiming Xiang, Jieping Ye</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Knowledge-based visual question answering (KB-VQA) requires visual language models (VLMs) to integrate visual understanding with external knowledge retrieval. Although retrieval-augmented generation (RAG) achieves significant advances in this task by combining knowledge-base querying, it still struggles with the quality of multimodal queries and the relevance of retrieved results. To overcome these challenges, we propose a novel three-stage method, termed Wiki-PRF, including Processing, Retrieval and Filtering stages. The processing stage dynamically invokes visual tools to extract precise multimodal information for retrieval. The retrieval stage integrates visual and text features to achieve multimodal knowledge retrieval. The filtering stage performs relevance filtering and concentration on retrieval results. To this end, we introduce a visual language model trained with answer accuracy and format consistency as reward signals via a reinforcement learning manner. This enhances the model's reasoning, tool invocation for accurate queries, and filtering of irrelevant content. Experiments on benchmark datasets (E-VQA and InfoSeek) show significant improvements~(36.0 and 42.8) in answer quality, achieving state-of-the-art performance. Code is available at https://github.com/cqu-student/Wiki-PRF</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.14605</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 12:10:00 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>A^2FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.12838</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12838.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianben Chen, Jingyi Cao, Jiayu Zhang, Tianrui Qin, Xiaowan Li, King Zhu, Dingfeng Shi, He Zhu, Minghao Liu, Xiaobo Liang, Xin Gui, Ge Zhang, Jian Yang, Yuchen Eleanor Jiang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, which learn to interact with environments and leverage tools but often lag in deep reasoning. This divide arises from fundamentally different training objectives, leading to mismatched strengths and inefficiency on simple queries, where both families tend to overthink or over-call tools. In this work, we present Adaptive Agent Foundation Model (A^2FM), a unified framework that follows a route-then-align principle: the model first learns task-aware routing and then aligns mode-specific trajectories under a shared backbone. To address the inefficiency gap, we introduce a third mode-instant-that handles simple queries directly, preventing unnecessary reasoning or tool calls while complementing the agentic and reasoning modes. To jointly enhance accuracy and efficiency, we propose Adaptive Policy Optimization (APO), which enforces adaptive sampling across modes and applies a cost-regularized reward. On the 32B scale, A^2FM achieves 13.4% on BrowseComp, 70.4% on AIME25, and 16.7% on HLE, setting new SOTA among comparable models and performing competitively with frontier LLMs across agentic, reasoning, and general benchmarks. Notably, the adaptive execution achieves a cost of pass of only $0.00487 per correct answer-cutting cost by 45.2% relative to reasoning and 33.5% relative to agentic, thus delivering substantially higher cost efficiency while maintaining comparable accuracy.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.12838</guid>
|
||||
<pubDate>Mon, 13 Oct 2025 17:08:25 +0000</pubDate>
|
||||
<title>Constantly Improving Image Models Need Constantly Improving Benchmarks</title>
|
||||
<link>https://arxiv.org/abs/2510.15021</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15021.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxin Ge, Grace Luo, Heekyung Lee, Nishant Malpani, Long Lian, XuDong Wang, Aleksander Holynski, Trevor Darrell, Sewon Min, David M. Chan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in image generation, often driven by proprietary systems like GPT-4o Image Gen, regularly introduce new capabilities that reshape how users interact with these models. Existing benchmarks often lag behind and fail to capture these emerging use cases, leaving a gap between community perceptions of progress and formal evaluation. To address this, we present ECHO, a framework for constructing benchmarks directly from real-world evidence of model use: social media posts that showcase novel prompts and qualitative user judgments. Applying this framework to GPT-4o Image Gen, we construct a dataset of over 31,000 prompts curated from such posts. Our analysis shows that ECHO (1) discovers creative and complex tasks absent from existing benchmarks, such as re-rendering product labels across languages or generating receipts with specified totals, (2) more clearly distinguishes state-of-the-art models from alternatives, and (3) surfaces community feedback that we use to inform the design of metrics for model quality (e.g., measuring observed shifts in color, identity, and structure). Our website is at https://echo-bench.github.io.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15021</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 17:59:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Language Models Model Language</title>
|
||||
<link>https://arxiv.org/abs/2510.12766</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.12766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Łukasz Borchmann</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Linguistic commentary on LLMs, heavily influenced by the theoretical frameworks of de Saussure and Chomsky, is often speculative and unproductive. Critics challenge whether LLMs can legitimately model language, citing the need for "deep structure" or "grounding" to achieve an idealized linguistic "competence." We argue for a radical shift in perspective towards the empiricist principles of Witold Ma\'nczak, a prominent general and historical linguist. He defines language not as a "system of signs" or a "computational system of the brain" but as the totality of all that is said and written. Above all, he identifies frequency of use of particular language elements as language's primary governing principle. Using his framework, we challenge prior critiques of LLMs and provide a constructive guide for designing, evaluating, and interpreting language models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.12766</guid>
|
||||
<pubDate>Tue, 14 Oct 2025 17:45:31 +0000</pubDate>
|
||||
<title>When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling</title>
|
||||
<link>https://arxiv.org/abs/2510.15346</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15346.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heecheol Yun, Kwangmin Ki, Junghyun Lee, Eunho Yang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Ensembling Large Language Models (LLMs) has gained attention as a promising approach to surpass the performance of individual models by leveraging their complementary strengths. In particular, aggregating models' next-token probability distributions to select the next token has been shown to be effective in various tasks. However, while successful for short-form answers, its application to long-form generation remains underexplored. In this paper, we show that using existing ensemble methods in long-form generation requires a careful choice of ensembling positions, since the standard practice of ensembling at every token often degrades performance. We identify two key factors for determining these positions: tokenization mismatch across models and consensus in their next-token probability distributions. Based on this, we propose SAFE, (Stable And Fast LLM Ensembling), a framework that selectively ensembles by jointly considering these factors. To further improve stability, we introduce a probability sharpening strategy that consolidates probabilities spread across multiple sub-word tokens representing the same word into a single representative token. Our experiments on diverse benchmarks, including MATH500 and BBH, demonstrate that SAFE outperforms existing methods in both accuracy and efficiency, with gains achieved even when ensembling fewer than 1% of tokens.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15346</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 06:18:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.14077</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14077.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haziq Mohammad Khalid, Athikash Jeyaganthan, Timothy Do, Yicheng Fu, Sean O'Brien, Vasu Sharma, Kevin Zhu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) suffer significant performance degradation in multi-turn conversations when information is presented incrementally. Given that multi-turn conversations characterize everyday interactions with LLMs, this degradation poses a severe challenge to real world usability. We hypothesize that abrupt increases in model uncertainty signal misalignment in multi-turn LLM interactions, and we exploit this insight to dynamically realign conversational context. We introduce ERGO (Entropy-guided Resetting for Generation Optimization), which continuously quantifies internal uncertainty via Shannon entropy over next token distributions and triggers adaptive prompt consolidation when a sharp spike in entropy is detected. By treating uncertainty as a first class signal rather than a nuisance to eliminate, ERGO embraces variability in language and modeling, representing and responding to uncertainty. In multi-turn tasks with incrementally revealed instructions, ERGO yields a 56.6% average performance gain over standard baselines, increases aptitude (peak performance capability) by 24.7%, and decreases unreliability (variability in performance) by 35.3%, demonstrating that uncertainty aware interventions can improve both accuracy and reliability in conversational AI.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.14077</guid>
|
||||
<pubDate>Wed, 15 Oct 2025 20:33:08 +0000</pubDate>
|
||||
<title>Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training</title>
|
||||
<link>https://arxiv.org/abs/2510.15527</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aditya Vir</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> This work presents a systematic investigation of custom convolutional neural network architectures for satellite land use classification, achieving 97.23% test accuracy on the EuroSAT dataset without reliance on pre-trained models. Through three progressive architectural iterations (baseline: 94.30%, CBAM-enhanced: 95.98%, and balanced multi-task attention: 97.23%) we identify and address specific failure modes in satellite imagery classification. Our principal contribution is a novel balanced multi-task attention mechanism that combines Coordinate Attention for spatial feature extraction with Squeeze-Excitation blocks for spectral feature extraction, unified through a learnable fusion parameter. Experimental results demonstrate that this learnable parameter autonomously converges to alpha approximately 0.57, indicating near-equal importance of spatial and spectral modalities for satellite imagery. We employ progressive DropBlock regularization (5-20% by network depth) and class-balanced loss weighting to address overfitting and confusion pattern imbalance. The final 12-layer architecture achieves Cohen's Kappa of 0.9692 with all classes exceeding 94.46% accuracy, demonstrating confidence calibration with a 24.25% gap between correct and incorrect predictions. Our approach achieves performance within 1.34% of fine-tuned ResNet-50 (98.57%) while requiring no external data, validating the efficacy of systematic architectural design for domain-specific applications. Complete code, trained models, and evaluation scripts are publicly available.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15527</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 10:59:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.14265</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Xu-Yao Zhang, Qiang Liu, Zhouchen Lin, Wentao Zhang, Bin Dong</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existing benchmarks designed to assess the reasoning abilities of large models tend to be limited in scope and lack the flexibility to adapt their difficulty according to the evolving reasoning capacities of the models. To address this, we propose MorphoBench, a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. Specifically, we curate the benchmark by selecting and collecting complex reasoning questions from existing benchmarks and sources such as Olympiad-level competitions. Additionally, MorphoBench adaptively modifies the analytical challenge of questions by leveraging key statements generated during the model's reasoning process. Furthermore, it includes questions generated using simulation software, enabling dynamic adjustment of benchmark difficulty with minimal resource consumption. We have gathered over 1,300 test questions and iteratively adjusted the difficulty of MorphoBench based on the reasoning capabilities of models such as o3 and GPT-5. MorphoBench enhances the comprehensiveness and validity of model reasoning evaluation, providing reliable guidance for improving both the reasoning abilities and scientific robustness of large models. The code has been released in https://github.com/OpenDCAI/MorphoBench.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.14265</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 03:30:56 +0000</pubDate>
|
||||
<title>On Non-interactive Evaluation of Animal Communication Translators</title>
|
||||
<link>https://arxiv.org/abs/2510.15768</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15768.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Orr Paradise, David F. Gruber, Adam Tauman Kalai</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> If you had an AI Whale-to-English translator, how could you validate whether or not it is working? Does one need to interact with the animals or rely on grounded observations such as temperature? We provide theoretical and proof-of-concept experimental evidence suggesting that interaction and even observations may not be necessary for sufficiently complex languages. One may be able to evaluate translators solely by their English outputs, offering potential advantages in terms of safety, ethics, and cost. This is an instance of machine translation quality evaluation (MTQE) without any reference translations available. A key challenge is identifying ``hallucinations,'' false translations which may appear fluent and plausible. We propose using segment-by-segment translation together with the classic NLP shuffle test to evaluate translators. The idea is to translate animal communication, turn by turn, and evaluate how often the resulting translations make more sense in order than permuted. Proof-of-concept experiments on data-scarce human languages and constructed languages demonstrate the potential utility of this evaluation methodology. These human-language experiments serve solely to validate our reference-free metric under data scarcity. It is found to correlate highly with a standard evaluation based on reference translations, which are available in our experiments. We also perform a theoretical analysis suggesting that interaction may not be necessary nor efficient in the early stages of learning to translate.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15768</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 15:56:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Explore to Evolve: Scaling Evolved Aggregation Logic via Proactive Online Exploration for Deep Research Agents</title>
|
||||
<link>https://arxiv.org/abs/2510.14438</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14438.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu, Kam-Fai Wong</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Deep research web agents not only retrieve information from diverse sources such as web environments, files, and multimodal inputs, but more importantly, they need to rigorously analyze and aggregate knowledge for insightful research. However, existing open-source deep research agents predominantly focus on enhancing information-seeking capabilities of web agents to locate specific information, while overlooking the essential need for information aggregation, which would limit their ability to support in-depth research. We propose an Explore to Evolve paradigm to scalably construct verifiable training data for web agents. Begins with proactive online exploration, an agent sources grounded information by exploring the real web. Using the collected evidence, the agent then self-evolves an aggregation program by selecting, composing, and refining operations from 12 high-level logical types to synthesize a verifiable QA pair. This evolution from high-level guidance to concrete operations allowed us to scalably produce WebAggregatorQA, a dataset of 10K samples across 50K websites and 11 domains. Based on an open-source agent framework, SmolAgents, we collect supervised fine-tuning trajectories to develop a series of foundation models, WebAggregator. WebAggregator-8B matches the performance of GPT-4.1, while the 32B variant surpasses GPT-4.1 by more than 10% on GAIA-text and closely approaches Claude-3.7-sonnet. Moreover, given the limited availability of benchmarks that evaluate web agents' information aggregation abilities, we construct a human-annotated evaluation split of WebAggregatorQA as a challenging test set. On this benchmark, Claude-3.7-sonnet only achieves 28%, and GPT-4.1 scores 25.8%. Even when agents manage to retrieve all references, they still struggle on WebAggregatorQA, highlighting the need to strengthen the information aggregation capabilities of web agent foundations.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.14438</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 08:37:42 +0000</pubDate>
|
||||
<title>Chronos-2: From Univariate to Universal Forecasting</title>
|
||||
<link>https://arxiv.org/abs/2510.15821</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15821.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer, Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella, Xiyuan Zhang, Mononito Goswami, Shubham Kapoor, Danielle C. Maddix, Pablo Guerron, Tony Hu, Junming Yin, Nick Erickson, Prateek Mutalik Desai, Hao Wang, Huzefa Rangwala, George Karypis, Yuyang Wang, Michael Bohlke-Schneider</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely focus on univariate forecasting, limiting their applicability in real-world scenarios where multivariate data and covariates play a crucial role. We present Chronos-2, a pretrained model capable of handling univariate, multivariate, and covariate-informed forecasting tasks in a zero-shot manner. Chronos-2 employs a group attention mechanism that facilitates in-context learning (ICL) through efficient information sharing across multiple time series within a group, which may represent sets of related series, variates of a multivariate series, or targets and covariates in a forecasting task. These general capabilities are achieved through training on synthetic datasets that impose diverse multivariate structures on univariate series. Chronos-2 delivers state-of-the-art performance across three comprehensive benchmarks: fev-bench, GIFT-Eval, and Chronos Benchmark II. On fev-bench, which emphasizes multivariate and covariate-informed forecasting, Chronos-2's universal ICL capabilities lead to substantial improvements over existing models. On tasks involving covariates, it consistently outperforms baselines by a wide margin. Case studies in the energy and retail domains further highlight its practical advantages. The in-context learning capabilities of Chronos-2 establish it as a general-purpose forecasting model that can be used "as is" in real-world forecasting pipelines.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15821</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:00:53 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Adapting Self-Supervised Representations as a Latent Space for Efficient Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.14630</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Gui, Johannes Schusterbauer, Timy Phan, Felix Krause, Josh Susskind, Miguel Angel Bautista, Björn Ommer</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision transformers. Building on a pre-trained SSL encoder, we fine-tune only the semantic token embedding and pair it with a generative decoder trained jointly using a standard flow matching objective. This adaptation enriches the token with low-level, reconstruction-relevant details, enabling faithful image reconstruction. To preserve the favorable geometry of the original SSL space, we add a cosine-similarity loss that regularizes the adapted token, ensuring the latent space remains smooth and suitable for generation. Our single-token formulation resolves spatial redundancies of 2D latent spaces and significantly reduces training costs. Despite its simplicity and efficiency, RepTok achieves competitive results on class-conditional ImageNet generation and naturally extends to text-to-image synthesis, reaching competitive zero-shot performance on MS-COCO under extremely limited training budgets. Our findings highlight the potential of fine-tuned SSL representations as compact and effective latent spaces for efficient generative modeling.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.14630</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 12:43:03 +0000</pubDate>
|
||||
<title>GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer</title>
|
||||
<link>https://arxiv.org/abs/2510.16136</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sayan Deb Sarkar, Sinisa Stekovic, Vincent Lepetit, Iro Armeni</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Transferring appearance to 3D assets using different representations of the appearance object - such as images or text - has garnered interest due to its wide range of applications in industries like gaming, augmented reality, and digital content creation. However, state-of-the-art methods still fail when the geometry between the input and appearance objects is significantly different. A straightforward approach is to directly apply a 3D generative model, but we show that this ultimately fails to produce appealing results. Instead, we propose a principled approach inspired by universal guidance. Given a pretrained rectified flow model conditioned on image or text, our training-free method interacts with the sampling process by periodically adding guidance. This guidance can be modeled as a differentiable loss function, and we experiment with two different types of guidance including part-aware losses for appearance and self-similarity. Our experiments show that our approach successfully transfers texture and geometric details to the input 3D asset, outperforming baselines both qualitatively and quantitatively. We also show that traditional metrics are not suitable for evaluating the task due to their inability of focusing on local details and comparing dissimilar inputs, in absence of ground truth data. We thus evaluate appearance transfer quality with a GPT-based system objectively ranking outputs, ensuring robust and human-like assessment, as further confirmed by our user study. Beyond showcased scenarios, our method is general and could be extended to different types of diffusion models and guidance functions.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16136</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 18:22:04 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Rewiring Experts on the Fly:Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert models</title>
|
||||
<link>https://arxiv.org/abs/2510.14853</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.14853.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guinan Su, Yanwu Yang, Li Shen, Lu Yin, Shiwei Liu, Jonas Geiping</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Mixture-of-Experts (MoE) models achieve efficient scaling through sparse expert activation, but often suffer from suboptimal routing decisions due to distribution shifts in deployment. While existing test-time adaptation methods could potentially address these issues, they primarily focus on dense models and require access to external data, limiting their practical applicability to MoE architectures. However, we find that, instead of relying on reference data, we can optimize MoE expert selection on-the-fly based only on input context. As such, we propose a data-free, online test-time framework that continuously adapts MoE routing decisions during text generation without external supervision or data. Our method cycles between two phases: During the prefill stage, and later in regular intervals, we optimize the routing decisions of the model using self-supervision based on the already generated sequence. Then, we generate text as normal, maintaining the modified router until the next adaption. We implement this through lightweight additive vectors that only update router logits in selected layers, maintaining computational efficiency while preventing over-adaptation. The experimental results show consistent performance gains on challenging reasoning tasks while maintaining robustness to context shifts. For example, our method achieves a 5.5\% improvement on HumanEval with OLMoE. Furthermore, owing to its plug-and-play property, our method naturally complements existing test-time scaling techniques, e.g., achieving 6\% average gains when incorporated with self-consistency on DeepSeek-V2-Lite.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.14853</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 16:24:36 +0000</pubDate>
|
||||
<title>AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.16156</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16156.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yueqian Lin, Zhengmian Hu, Jayakumar Subramanian, Qinsi Wang, Nikos Vlassis, Hai "Helen" Li, Yiran Chen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Effective human-AI collaboration on complex reasoning tasks requires that users understand and interact with the model's process, not just receive an output. However, the monolithic text from methods like Chain-of-Thought (CoT) prevents this, as current interfaces lack real-time verbalization and robust user barge-in. We present AsyncVoice Agent, a system whose asynchronous architecture decouples a streaming LLM backend from a conversational voice frontend. This design allows narration and inference to run in parallel, empowering users to interrupt, query, and steer the model's reasoning process at any time. Objective benchmarks show this approach reduces interaction latency by more than 600x compared to monolithic baselines while ensuring high fidelity and competitive task accuracy. By enabling a two-way dialogue with a model's thought process, AsyncVoice Agent offers a new paradigm for building more effective, steerable, and trustworthy human-AI systems for high-stakes tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16156</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 19:00:08 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks</title>
|
||||
<link>https://arxiv.org/abs/2510.15019</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15019.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junliang Ye, Shenghao Xie, Ruowen Zhao, Zhengyi Wang, Hongyu Yan, Wenqiang Zu, Lei Ma, Jun Zhu</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> 3D object editing is essential for interactive content creation in gaming, animation, and robotics, yet current approaches remain inefficient, inconsistent, and often fail to preserve unedited regions. Most methods rely on editing multi-view renderings followed by reconstruction, which introduces artifacts and limits practicality. To address these challenges, we propose Nano3D, a training-free framework for precise and coherent 3D object editing without masks. Nano3D integrates FlowEdit into TRELLIS to perform localized edits guided by front-view renderings, and further introduces region-aware merging strategies, Voxel/Slat-Merge, which adaptively preserve structural fidelity by ensuring consistency between edited and unedited areas. Experiments demonstrate that Nano3D achieves superior 3D consistency and visual quality compared with existing methods. Based on this framework, we construct the first large-scale 3D editing datasets Nano3D-Edit-100k, which contains over 100,000 high-quality 3D editing pairs. This work addresses long-standing challenges in both algorithm design and data availability, significantly improving the generality and reliability of 3D editing, and laying the groundwork for the development of feed-forward 3D editing models. Project Page:https://jamesyjl.github.io/Nano3D</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15019</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 17:51:50 +0000</pubDate>
|
||||
<title>Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset</title>
|
||||
<link>https://arxiv.org/abs/2510.16258</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Claire McLean, Makenzie Meendering, Tristan Swartz, Orri Gabbay, Alexandra Olsen, Rachel Jacobs, Nicholas Rosen, Philippe de Bree, Tony Garcia, Gadsden Merrill, Jake Sandakly, Julia Buffalini, Neham Jain, Steven Krenn, Moneish Kumar, Dejan Markovic, Evonne Ng, Fabian Prada, Andrew Saba, Siwei Zhang, Vasu Agrawal, Tim Godisart, Alexander Richard, Michael Zollhoefer</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The Codec Avatars Lab at Meta introduces Embody 3D, a multimodal dataset of 500 individual hours of 3D motion data from 439 participants collected in a multi-camera collection stage, amounting to over 54 million frames of tracked 3D motion. The dataset features a wide range of single-person motion data, including prompted motions, hand gestures, and locomotion; as well as multi-person behavioral and conversational data like discussions, conversations in different emotional states, collaborative activities, and co-living scenarios in an apartment-like space. We provide tracked human motion including hand tracking and body shape, text annotations, and a separate audio track for each participant.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16258</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 23:06:36 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2510.15110</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15110.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shih-Yang Liu, Xin Dong, Ximing Lu, Shizhe Diao, Mingjie Liu, Min-Hung Chen, Hongxu Yin, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Yejin Choi, Jan Kautz, Pavlo Molchanov</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Reasoning language models such as OpenAI-o1, DeepSeek-R1, and Qwen achieve strong performance via extended chains of thought but often generate unnecessarily long outputs. Maximizing intelligence per token--accuracy relative to response length--remains an open problem. We revisit reinforcement learning (RL) with the simplest length penalty--truncation--and show that accuracy degradation arises not from the lack of sophisticated penalties but from inadequate RL optimization. We identify three key challenges: (i) large bias in advantage estimation, (ii) entropy collapse, and (iii) sparse reward signal. We address them with Doing Length pEnalty Right (DLER), a training recipe combining batch-wise reward normalization, higher clipping, dynamic sampling, and a simple truncation length penalty. DLER achieves state-of-the-art accuracy--efficiency trade-offs, cutting output length by over 70 percent while surpassing all previous baseline accuracy. It also improves test-time scaling: compared to DeepSeek-R1-7B, DLER-7B generates multiple concise responses in parallel with 28 percent higher accuracy and lower latency. We further introduce Difficulty-Aware DLER, which adaptively tightens truncation on easier questions for additional efficiency gains. We also propose an update-selective merging method that preserves baseline accuracy while retaining the concise reasoning ability of the DLER model, which is useful for scenarios where RL training data is scarce.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15110</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 20:05:57 +0000</pubDate>
|
||||
<title>Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense</title>
|
||||
<link>https://arxiv.org/abs/2510.16259</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhehao Zhang, Weijie Xu, Shixian Cui, Chandan K. Reddy</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a critical vulnerability we term reasoning distraction, where LRMs are diverted from their primary objective by irrelevant yet complex tasks maliciously embedded in the prompt. Through a comprehensive study across diverse models and benchmarks, we show that even state-of-the-art LRMs are highly susceptible, with injected distractors reducing task accuracy by up to 60%. We further reveal that certain alignment techniques can amplify this weakness and that models may exhibit covert compliance, following hidden adversarial instructions in reasoning while concealing them in the final output. To mitigate these risks, we propose a training-based defense that combines Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on synthetic adversarial data, improving robustness by over 50 points on challenging distractor attacks. Our findings establish reasoning distraction as a distinct and urgent threat to LRM reliability and provide a practical step toward safer and more trustworthy reasoning systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16259</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 23:16:34 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Train a Unified Multimodal Data Quality Classifier with Synthetic Data</title>
|
||||
<link>https://arxiv.org/abs/2510.15162</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15162.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weizhi Wang, Rongmei Lin, Shiyang Li, Colin Lockard, Ritesh Sarkhel, Sanket Lokegaonkar, Jingbo Shang, Xifeng Yan, Nasser Zalmout, Xian Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The Multimodal Large Language Models (MLLMs) are continually pre-trained on a mixture of image-text caption data and interleaved document data, while the high-quality data filtering towards image-text interleaved document data is under-explored. We propose to train an efficient MLLM as a Unified Mulitmodal Data Quality Classifier to Filter both high-quality image-text caption and interleaved data (UniFilter). To address the challenge of collecting diverse labeled multimodal data, we introduce a semi-synthetic approach that leverages readily available raw images and generates corresponding text across four quality levels. This method enables efficient creation of sample-score pairs for both caption and interleaved document data to train UniFilter. We apply UniFilter to curate high-quality caption data from DataComp caption dataset and interleaved data from the OBELICS image-text interleaved dataset. MLLMs pre-trained on the filtered data demonstrate significantly enhanced capabilities compared to those trained on baseline-filtered data, achieving stronger zero-shot reasoning and in-context learning capabilities. After visual supervised fine-tuning, these UniFilter-induced MLLMs achieve stronger performance on various benchmarks, highlighting the downstream benefits of high-quality multimodal pre-training. We release the synthetic training data used for training UniFilter, the UniFilter model checkpoints, and the high-quality interleaved document subset OBELICS-HQ, curated by UniFilter, to the community for reproduction and further development.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15162</guid>
|
||||
<pubDate>Thu, 16 Oct 2025 21:53:28 +0000</pubDate>
|
||||
<title>What Limits Agentic Systems Efficiency?</title>
|
||||
<link>https://arxiv.org/abs/2510.16276</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Song Bian, Minghao Yan, Anand Jayarajan, Gennady Pekhimenko, Shivaram Venkataraman</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM reasoning to mitigate uncertainties and reduce potential errors. However, existing research predominantly focuses on reasoning performance, often neglecting the efficiency of agentic systems. In this work, we present a comprehensive empirical study that identifies efficiency bottlenecks in web-interactive agentic systems. We decompose end-to-end latency into two primary components: LLM API latency and web environment latency. We conduct a comprehensive empirical study across 15 models and 5 providers to demonstrate high variability in API-based agentic systems. We observe that web environment latency can contribute as much as 53.7% to the overall latency in a web-based agentic system. To improve latency, we propose SpecCache, a caching framework augmented with speculative execution that can reduce web environment overhead. Extensive evaluations on two standard benchmarks show that our approach improves the cache hit rate by up to 58x compared to a random caching strategy, while reducing web environment overhead by up to 3.2x, without degrading agentic system performance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16276</guid>
|
||||
<pubDate>Sat, 18 Oct 2025 00:21:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain</title>
|
||||
<link>https://arxiv.org/abs/2510.15232</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tiansheng Hu, Tongyan Hu, Liuyang Bai, Yilun Zhao, Arman Cohan, Chen Zhao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent LLMs have demonstrated promising ability in solving finance related problems. However, applying LLMs in real-world finance application remains challenging due to its high risk and high stakes property. This paper introduces FinTrust, a comprehensive benchmark specifically designed for evaluating the trustworthiness of LLMs in finance applications. Our benchmark focuses on a wide range of alignment issues based on practical context and features fine-grained tasks for each dimension of trustworthiness evaluation. We assess eleven LLMs on FinTrust and find that proprietary models like o4-mini outperforms in most tasks such as safety while open-source models like DeepSeek-V3 have advantage in specific areas like industry-level fairness. For challenging task like fiduciary alignment and disclosure, all LLMs fall short, showing a significant gap in legal awareness. We believe that FinTrust can be a valuable benchmark for LLMs' trustworthiness evaluation in finance domain.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15232</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 01:45:49 +0000</pubDate>
|
||||
<title>RL makes MLLMs see better than SFT</title>
|
||||
<link>https://arxiv.org/abs/2510.16333</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16333.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junha Song, Sangdoo Yun, Dongyoon Han, Jaegul Choo, Byeongho Heo</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its immense parameter scale and remarkable capabilities. This has created a void in the understanding of the vision encoder, which determines how MLLMs perceive images. The recent shift in MLLM training paradigms, from Supervised Finetuning (SFT) to Reinforcement Learning (RL), magnifies this oversight-namely, the significant lack of analysis on how such training reshapes the vision encoder as well as the MLLM. To address this, we first investigate the impact of training strategies on MLLMs, where RL shows a clear advantage over SFT in strongly vision-related VQA benchmarks. Motivated by this, we conduct a critical yet under-explored analysis of the vision encoder of MLLMs through diverse and in-depth experiments, ranging from ImageNet classification and segmentation to gradient visualization. Our results demonstrate that MLLM's post-training strategy (i.e., SFT or RL) not only leads to distinct outcomes on MLLM downstream tasks, but also fundamentally reshapes MLLM's underlying visual representations. Specifically, the key finding of our study is that RL produces stronger and precisely localized visual representations compared to SFT, boosting the ability of the vision encoder for MLLM. We then reframe our findings into a simple recipe for building strong vision encoders for MLLMs, Preference-Instructed Vision OpTimization (PIVOT). When integrated into MLLMs, a PIVOT-trained vision encoder outperforms even larger and more heavily-trained counterparts, despite requiring less than 1% of the computational cost of standard vision pretraining. This result opens an effective and efficient path for advancing the vision backbones of MLLMs. Project page available at https://june-page.github.io/pivot/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16333</guid>
|
||||
<pubDate>Sat, 18 Oct 2025 03:37:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Robust Layerwise Scaling Rules by Proper Weight Decay Tuning</title>
|
||||
<link>https://arxiv.org/abs/2510.15262</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15262.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Fan, Yifeng Liu, Qingyue Zhao, Angela Yuan, Quanquan Gu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Empirical scaling laws prescribe how to allocate parameters, data, and compute, while maximal-update parameterization (muP) enables learning-rate transfer across widths by equalizing early-time update magnitudes. However, in modern scale-invariant architectures, training quickly enters an optimizer-governed steady state where normalization layers create backward scale sensitivity and the effective learning rate becomes width dependent, degrading muP transfer. We address this by introducing a weight-decay scaling rule for AdamW that preserves sublayer gain across widths. Empirically, the singular-value spectrum of each matrix parameter scales in norm as eta/lambda with an approximately invariant shape; under width scaling d, we observe that the top singular value scales approximately as eta/lambdacdot d^{0.75}. Combining this observation with the muP learning-rate rule eta_2propto d^{-1} for matrix-like parameters implies an empirical weight-decay scaling rule lambda_2propto d that approximately keeps sublayer gains width invariant. Together with vector-like parameters trained at eta_1=Theta_d(1) and lambda_1=0, this yields zero-shot transfer of both learning rate and weight decay from proxy to target widths, removing per-width sweeps. We validate the rule on LLaMA-style Transformers and in a minimal synthetic setting, and we provide a simple diagnostic, matching top singular values, to check sublayer-gain invariance. Our results extend muP beyond the near-init regime by explicitly controlling steady-state scales set by the optimizer, offering a practical recipe for width-robust hyperparameter transfer under AdamW.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15262</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 02:58:35 +0000</pubDate>
|
||||
<title>TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model</title>
|
||||
<link>https://arxiv.org/abs/2510.16449</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16449.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Yu, Xinming Wang, Shijie Lian, Haotian Li, Changti Wu, Ruina Hu, Bailing Wang, Yuliang Wei, Kai Chen</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Large language models (LLMs) have shown remarkable progress in complex reasoning tasks, largely enabled by test-time scaling (TTS) paradigms that allocate additional compute during inference. Among these, external TTS (particularly the Best-of-N selection paradigm) yields scalable performance improvements by selecting from multiple independently generated reasoning trajectories. However, this approach faces key limitations: (i) the high computational overhead of deploying process reward models, (ii) the underutilization of the LLM's intrinsic latent representations. We introduce TrajSelector, an efficient and effective Best-of-N framework that exploit the hidden states in the sampler LLM for process-level scoring. A lightweight verifier (with only 0.6B parameters) evaluates the quality of step-wise trajectory, and then aggregates these scores to identify the optimal reasoning trajectory. Our framework employs a fully data-driven, end-to-end training recipe that eliminates reliance on massive step-level annotations. Experiential results across five benchmarks demonstrate that TrajSelector delivers consistent performance gains. In Best-of-32 settings, it surpasses majority voting by 4.61% accuracy and outperforms existing process reward models by 4.31% to 12.21%, all while maintaining lower inference costs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16449</guid>
|
||||
<pubDate>Sat, 18 Oct 2025 11:01:39 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion</title>
|
||||
<link>https://arxiv.org/abs/2510.15264</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Wang, Jiagang Zhu, Zeyu Zhang, Xiaofeng Wang, Zheng Zhu, Guosheng Zhao, Chaojun Ni, Haoxiao Wang, Guan Huang, Xinze Chen, Yukun Zhou, Wenkang Qin, Duochao Shi, Haoyun Li, Guanghong Jia, Jiwen Lu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis either suffer from prohibitive computational demands for extended temporal generation, focus exclusively on prolonged video synthesis without 3D representation, or restrict themselves to static single-scene reconstruction. Our work bridges this methodological gap by integrating accelerated long-term video generation with large-scale dynamic scene reconstruction through multimodal conditional control. DriveGen3D introduces a unified pipeline consisting of two specialized components: FastDrive-DiT, an efficient video diffusion transformer for high-resolution, temporally coherent video synthesis under text and Bird's-Eye-View (BEV) layout guidance; and FastRecon3D, a feed-forward reconstruction module that rapidly builds 3D Gaussian representations across time, ensuring spatial-temporal consistency. Together, these components enable real-time generation of extended driving videos (up to 424times800 at 12 FPS) and corresponding dynamic 3D scenes, achieving SSIM of 0.811 and PSNR of 22.84 on novel view synthesis, all while maintaining parameter efficiency.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15264</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 03:00:08 +0000</pubDate>
|
||||
<title>Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection</title>
|
||||
<link>https://arxiv.org/abs/2510.16499</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Michelle Yuan, Khushbu Pahwa, Shuaichen Chang, Mustafa Kaba, Jiarong Jiang, Xiaofei Ma, Yi Zhang, Monica Sunkara</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods rely on static, semantic retrieval approaches for tool or agent discovery. However, effective reuse and composition of existing components remain challenging due to incomplete capability descriptions and the limitations of retrieval methods. Component selection suffers because the decisions are not based on capability, cost, and real-time utility. To address these challenges, we introduce a structured, automated framework for agentic system composition that is inspired by the knapsack problem. Our framework enables a composer agent to systematically identify, select, and assemble an optimal set of agentic components by jointly considering performance, budget constraints, and compatibility. By dynamically testing candidate components and modeling their utility in real-time, our approach streamlines the assembly of agentic systems and facilitates scalable reuse of resources. Empirical evaluation with Claude 3.5 Sonnet across five benchmarking datasets shows that our online-knapsack-based composer consistently lies on the Pareto frontier, achieving higher success rates at significantly lower component costs compared to our baselines. In the single-agent setup, the online knapsack composer shows a success rate improvement of up to 31.6% in comparison to the retrieval baselines. In multi-agent systems, the online knapsack composer increases success rate from 37% to 87% when agents are selected from an agent inventory of 100+ agents. The substantial performance gap confirms the robust adaptability of our method across diverse domains and budget constraints.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16499</guid>
|
||||
<pubDate>Sat, 18 Oct 2025 13:37:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition</title>
|
||||
<link>https://arxiv.org/abs/2510.15280</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15280.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fan Liu, Jindong Han, Tengfei Lyu, Weijia Zhang, Zhe-Rui Yang, Lu Dai, Cancheng Liu, Hao Liu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Foundation models (FMs), such as GPT-4 and AlphaFold, are reshaping the landscape of scientific research. Beyond accelerating tasks such as hypothesis generation, experimental design, and result interpretation, they prompt a more fundamental question: Are FMs merely enhancing existing scientific methodologies, or are they redefining the way science is conducted? In this paper, we argue that FMs are catalyzing a transition toward a new scientific paradigm. We introduce a three-stage framework to describe this evolution: (1) Meta-Scientific Integration, where FMs enhance workflows within traditional paradigms; (2) Hybrid Human-AI Co-Creation, where FMs become active collaborators in problem formulation, reasoning, and discovery; and (3) Autonomous Scientific Discovery, where FMs operate as independent agents capable of generating new scientific knowledge with minimal human intervention. Through this lens, we review current applications and emerging capabilities of FMs across existing scientific paradigms. We further identify risks and future directions for FM-enabled scientific discovery. This position paper aims to support the scientific community in understanding the transformative role of FMs and to foster reflection on the future of scientific discovery. Our project is available at https://github.com/usail-hkust/Awesome-Foundation-Models-for-Scientific-Discovery.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15280</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 03:40:26 +0000</pubDate>
|
||||
<title>MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.16641</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16641.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Young-Jun Lee, Byung-Kwan Lee, Jianshu Zhang, Yechan Hwang, Byungsoo Ko, Han-Gyu Kim, Dongyu Yao, Xuankun Rong, Eojin Joo, Seung-Ho Han, Bowon Ko, Ho-Jin Choi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Vision-and-Language Models (VLMs) have shown impressive capabilities on single-turn benchmarks, yet real-world applications often demand more intricate multi-turn dialogues. Existing multi-turn datasets (e.g, MMDU, ConvBench) only partially capture the breadth and depth of conversational scenarios encountered by users. In this work, we introduce MultiVerse, a novel multi-turn conversation benchmark featuring 647 dialogues - each averaging four turns - derived from a diverse set of 12 popular VLM evaluation benchmarks. With 484 tasks and 484 interaction goals, MultiVerse covers a wide range of topics, from factual knowledge and perception to advanced reasoning tasks such as mathematics and coding. To facilitate robust assessment, we propose a checklist-based evaluation method that leverages GPT-4o as the automated evaluator, measuring performance across 37 key aspects, including perceptual accuracy, linguistic clarity, and factual correctness. We evaluate 18 VLMs on MultiVerse, revealing that even the strongest models (e.g., GPT-4o) achieve only a 50% success rate in complex multi-turn conversations, highlighting the dataset's challenging nature. Notably, we find that providing full dialogue context significantly enhances performance for smaller or weaker models, emphasizing the importance of in-context learning. We believe MultiVerse is a landscape of evaluating multi-turn interaction abilities for VLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16641</guid>
|
||||
<pubDate>Sat, 18 Oct 2025 21:00:12 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Latent Diffusion Model without Variational Autoencoder</title>
|
||||
<link>https://arxiv.org/abs/2510.15301</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minglei Shi, Haolin Wang, Wenzhao Zheng, Ziyang Yuan, Xiaoshi Wu, Xintao Wang, Pengfei Wan, Jie Zhou, Jiwen Lu</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational autoencoders (VAEs). While effective for high-fidelity synthesis, this VAE+diffusion paradigm suffers from limited training efficiency, slow inference, and poor transferability to broader vision tasks. These issues stem from a key limitation of VAE latent spaces: the lack of clear semantic separation and strong discriminative structure. Our analysis confirms that these properties are crucial not only for perception and understanding tasks, but also for the stable and efficient training of latent diffusion models. Motivated by this insight, we introduce SVG, a novel latent diffusion model without variational autoencoders, which leverages self-supervised representations for visual generation. SVG constructs a feature space with clear semantic discriminability by leveraging frozen DINO features, while a lightweight residual branch captures fine-grained details for high-fidelity reconstruction. Diffusion models are trained directly on this semantically structured latent space to facilitate more efficient learning. As a result, SVG enables accelerated diffusion training, supports few-step sampling, and improves generative quality. Experimental results further show that SVG preserves the semantic and discriminative capabilities of the underlying self-supervised representations, providing a principled pathway toward task-general, high-quality visual representations.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15301</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 04:17:44 +0000</pubDate>
|
||||
<title>Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI</title>
|
||||
<link>https://arxiv.org/abs/2510.16720</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16720.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jitao Sang, Jinlin Xiao, Jiarun Han, Jilin Chen, Xiaoyi Chen, Shuyu Wei, Yongjie Sun, Yuhang Wang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> The rapid evolution of agentic AI marks a new phase in artificial intelligence, where Large Language Models (LLMs) no longer merely respond but act, reason, and adapt. This survey traces the paradigm shift in building agentic AI: from Pipeline-based systems, where planning, tool use, and memory are orchestrated by external logic, to the emerging Model-native paradigm, where these capabilities are internalized within the model's parameters. We first position Reinforcement Learning (RL) as the algorithmic engine enabling this paradigm shift. By reframing learning from imitating static data to outcome-driven exploration, RL underpins a unified solution of LLM + RL + Task across language, vision and embodied domains. Building on this, the survey systematically reviews how each capability -- Planning, Tool use, and Memory -- has evolved from externally scripted modules to end-to-end learned behaviors. Furthermore, it examines how this paradigm shift has reshaped major agent applications, specifically the Deep Research agent emphasizing long-horizon reasoning and the GUI agent emphasizing embodied interaction. We conclude by discussing the continued internalization of agentic capabilities like Multi-agent collaboration and Reflection, alongside the evolving roles of the system and model layers in future agentic AI. Together, these developments outline a coherent trajectory toward model-native agentic AI as an integrated learning and interaction framework, marking the transition from constructing systems that apply intelligence to developing models that grow intelligence through experience.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16720</guid>
|
||||
<pubDate>Sun, 19 Oct 2025 05:23:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.15444</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhi Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Lan-Zhe Guo, Yu-Feng Li, Xiaoxing Ma</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding computational resources. A prevalent approach within the field is sampling-based test-time scaling methods, which enhance reasoning by generating multiple reasoning paths for a given input during inference. However, despite its practical success, the theoretical foundations remain underexplored. In this paper, we provide the first theoretical framework for analyzing sampling-based test-time scaling methods, grounded in the perspective of confidence estimation. Based on the framework, we analyze two dominant paradigms: self-consistency and perplexity, and reveal key limitations: self-consistency suffers from high estimation error while perplexity exhibits substantial modeling error and possible degradation of the estimation error convergence. To address these limitations, we introduce RPC, a hybrid method that leverages our theoretical insights through two key components: Perplexity Consistency and Reasoning Pruning. Perplexity Consistency combines the strengths of self-consistency and perplexity, boosting the convergence rate of estimation error from linear to exponential while preserving model error. Reasoning Pruning prevents degradation by eliminating low-probability reasoning paths. Both theoretical analysis and empirical results across seven benchmark datasets demonstrate that RPC has a strong potential for reducing reasoning error. Notably, RPC achieves reasoning performance comparable to self-consistency while not only enhancing confidence reliability but also reducing sampling costs by 50%. The code and resources are available at https://wnjxyk.github.io/RPC.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15444</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 08:59:30 +0000</pubDate>
|
||||
<title>Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.16727</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16727.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sanskar Pandey, Ruhaan Chopra, Angkul Puniya, Sohom Pal</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models internalize a structural trade-off between truthfulness and obsequious flattery, emerging from reward optimization that conflates helpfulness with polite submission. This latent bias, known as sycophancy, manifests as a preference for user agreement over principled reasoning. We introduce Beacon, a single-turn forced-choice benchmark that isolates this bias independent of conversational context, enabling precise measurement of the tension between factual accuracy and submissive bias. Evaluations across twelve state-of-the-art models reveal that sycophancy decomposes into stable linguistic and affective sub-biases, each scaling with model capacity. We further propose prompt-level and activation-level interventions that modulate these biases in opposing directions, exposing the internal geometry of alignment as a dynamic manifold between truthfulness and socially compliant judgment. Beacon reframes sycophancy as a measurable form of normative misgeneralization, providing a reproducible foundation for studying and mitigating alignment drift in large-scale generative systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16727</guid>
|
||||
<pubDate>Sun, 19 Oct 2025 06:36:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.15564</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15564.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoming Zhu, Xu Huang, Qinghongbing Xie, Zhi Deng, Junsheng Yu, Yirui Guan, Zhongyuan Liu, Lin Zhu, Qijun Zhao, Ligang Liu, Long Zeng</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Generating artistic and coherent 3D scene layouts is crucial in digital content creation. Traditional optimization-based methods are often constrained by cumbersome manual rules, while deep generative models face challenges in producing content with richness and diversity. Furthermore, approaches that utilize large language models frequently lack robustness and fail to accurately capture complex spatial relationships. To address these challenges, this paper presents a novel vision-guided 3D layout generation system. We first construct a high-quality asset library containing 2,037 scene assets and 147 3D scene layouts. Subsequently, we employ an image generation model to expand prompt representations into images, fine-tuning it to align with our asset library. We then develop a robust image parsing module to recover the 3D layout of scenes based on visual semantics and geometric information. Finally, we optimize the scene layout using scene graphs and overall visual semantics to ensure logical coherence and alignment with the images. Extensive user testing demonstrates that our algorithm significantly outperforms existing methods in terms of layout richness and quality. The code and dataset will be available at https://github.com/HiHiAllen/Imaginarium.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15564</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 11:48:08 +0000</pubDate>
|
||||
<title>Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling</title>
|
||||
<link>https://arxiv.org/abs/2510.16751</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16751.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Erik Riise, Mehmet Onurcan Kaya, Dim P. Papadopoulos</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited benefits, with simple random sampling often performing best. We demonstrate that the discrete, sequential nature of visual autoregressive models enables effective search for image generation. We show that beam search substantially improves text-to-image generation, enabling a 2B parameter autoregressive model to outperform a 12B parameter diffusion model across benchmarks. Systematic ablations show that this advantage comes from the discrete token space, which allows early pruning and computational reuse, and our verifier analysis highlights trade-offs between speed and reasoning capability. These findings suggest that model architecture, not just scale, is critical for inference-time optimization in visual generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16751</guid>
|
||||
<pubDate>Sun, 19 Oct 2025 08:28:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation</title>
|
||||
<link>https://arxiv.org/abs/2510.15624</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15624.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ed Li, Junyu Ren, Xintian Pan, Cat Yan, Chuanhao Li, Dirk Bergemann, Zhuoran Yang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that cannot adapt to intermediate findings, and inadequate context management that hinders long-horizon research. We present freephdlabor, an open-source multiagent framework featuring fully dynamic workflows determined by real-time agent reasoning and a \textit{modular architecture} enabling seamless customization -- users can modify, add, or remove agents to address domain-specific requirements. The framework provides comprehensive infrastructure including automatic context compaction, workspace-based communication to prevent information degradation, memory persistence across sessions, and non-blocking human intervention mechanisms. These features collectively transform automated research from isolated, single-run attempts into continual research programs that build systematically on prior explorations and incorporate human feedback. By providing both the architectural principles and practical implementation for building customizable co-scientist systems, this work aims to facilitate broader adoption of automated research across scientific domains, enabling practitioners to deploy interactive multiagent systems that autonomously conduct end-to-end research -- from ideation through experimentation to publication-ready manuscripts.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15624</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 13:13:32 +0000</pubDate>
|
||||
<title>DeepAnalyze: Agentic Large Language Models for Autonomous Data Science</title>
|
||||
<link>https://arxiv.org/abs/2510.16872</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaolei Zhang, Ju Fan, Meihao Fan, Guoliang Li, Xiaoyong Du</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Autonomous data science, from raw data sources to analyst-grade deep research reports, has been a long-standing challenge, and is now becoming feasible with the emergence of powerful large language models (LLMs). Recent workflow-based data agents have shown promising results on specific data tasks but remain fundamentally limited in achieving fully autonomous data science due to their reliance on predefined workflows. In this paper, we introduce DeepAnalyze-8B, the first agentic LLM designed for autonomous data science, capable of automatically completing the end-toend pipeline from data sources to analyst-grade deep research reports. To tackle high-complexity data science tasks, we propose a curriculum-based agentic training paradigm that emulates the learning trajectory of human data scientists, enabling LLMs to progressively acquire and integrate multiple capabilities in real-world environments. We also introduce a data-grounded trajectory synthesis framework that constructs high-quality training data. Through agentic training, DeepAnalyze learns to perform a broad spectrum of data tasks, ranging from data question answering and specialized analytical tasks to open-ended data research. Experiments demonstrate that, with only 8B parameters, DeepAnalyze outperforms previous workflow-based agents built on most advanced proprietary LLMs. The model, code, and training data of DeepAnalyze are open-sourced, paving the way toward autonomous data science.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16872</guid>
|
||||
<pubDate>Sun, 19 Oct 2025 15:13:42 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset</title>
|
||||
<link>https://arxiv.org/abs/2510.15742</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15742.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyan Bai, Qiuyu Wang, Hao Ouyang, Yue Yu, Hanlin Wang, Wen Wang, Ka Leong Cheng, Shuailei Ma, Yanhong Zeng, Zichen Liu, Yinghao Xu, Yujun Shen, Qifeng Chen</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Instruction-based video editing promises to democratize content creation, yet its progress is severely hampered by the scarcity of large-scale, high-quality training data. We introduce Ditto, a holistic framework designed to tackle this fundamental challenge. At its heart, Ditto features a novel data generation pipeline that fuses the creative diversity of a leading image editor with an in-context video generator, overcoming the limited scope of existing models. To make this process viable, our framework resolves the prohibitive cost-quality trade-off by employing an efficient, distilled model architecture augmented by a temporal enhancer, which simultaneously reduces computational overhead and improves temporal coherence. Finally, to achieve full scalability, this entire pipeline is driven by an intelligent agent that crafts diverse instructions and rigorously filters the output, ensuring quality control at scale. Using this framework, we invested over 12,000 GPU-days to build Ditto-1M, a new dataset of one million high-fidelity video editing examples. We trained our model, Editto, on Ditto-1M with a curriculum learning strategy. The results demonstrate superior instruction-following ability and establish a new state-of-the-art in instruction-based video editing.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15742</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 15:31:40 +0000</pubDate>
|
||||
<title>Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback</title>
|
||||
<link>https://arxiv.org/abs/2510.16888</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.16888.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zongjian Li, Zheyuan Liu, Qihui Zhang, Bin Lin, Shenghai Yuan, Zhiyuan Yan, Yang Ye, Wangbo Yu, Yuwei Niu, Li Yuan</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Instruction-based image editing has achieved remarkable progress; however, models solely trained via supervised fine-tuning often overfit to annotated patterns, hindering their ability to explore and generalize beyond training distributions. To this end, we introduce Edit-R1, a novel post-training framework for instruction-based image editing based on policy optimization. Specifically, we utilize Diffusion Negative-aware Finetuning (DiffusionNFT), a likelihood-free policy optimization method consistent with the flow matching forward process, thereby enabling the use of higher-order samplers and more efficient training. Another key challenge here is the absence of a universal reward model, resulting from the diverse nature of editing instructions and tasks. To bridge this gap, we employ a Multimodal Large Language Model (MLLM) as a unified, training-free reward model, leveraging its output logits to provide fine-grained feedback. Furthermore, we carefully design a low-variance group filtering mechanism to reduce MLLM scoring noise and stabilize optimization. UniWorld-V2, trained with this framework, achieves state-of-the-art results on the ImgEdit and GEdit-Bench benchmarks, scoring 4.49 and 7.83, respectively. Crucially, our framework is model-agnostic, delivering substantial performance gains when applied to diverse base models like Qwen-Image-Edit and FLUX-Kontext, demonstrating its wide applicability. Code and models are publicly available at https://github.com/PKU-YuanGroup/UniWorld-V2.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.16888</guid>
|
||||
<pubDate>Sun, 19 Oct 2025 15:38:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>VISTA: A Test-Time Self-Improving Video Generation Agent</title>
|
||||
<link>https://arxiv.org/abs/2510.15831</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15831.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Do Xuan Long, Xingchen Wan, Hootan Nakhost, Chen-Yu Lee, Tomas Pfister, Sercan Ö. Arık</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Despite rapid advances in text-to-video synthesis, generated video quality remains critically dependent on precise user prompts. Existing test-time optimization methods, successful in other domains, struggle with the multi-faceted nature of video. In this work, we introduce VISTA (Video Iterative Self-improvemenT Agent), a novel multi-agent system that autonomously improves video generation through refining prompts in an iterative loop. VISTA first decomposes a user idea into a structured temporal plan. After generation, the best video is identified through a robust pairwise tournament. This winning video is then critiqued by a trio of specialized agents focusing on visual, audio, and contextual fidelity. Finally, a reasoning agent synthesizes this feedback to introspectively rewrite and enhance the prompt for the next generation cycle. Experiments on single- and multi-scene video generation scenarios show that while prior methods yield inconsistent gains, VISTA consistently improves video quality and alignment with user intent, achieving up to 60% pairwise win rate against state-of-the-art baselines. Human evaluators concur, preferring VISTA outputs in 66.4% of comparisons.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15831</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:12:08 +0000</pubDate>
|
||||
<title>FineVision: Open Data Is All You Need</title>
|
||||
<link>https://arxiv.org/abs/2510.17269</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17269.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luis Wiedmann, Orr Zohar, Amir Mahla, Xiaohan Wang, Rui Li, Thibaud Frere, Leandro von Werra, Aritra Roy Gosthipaty, Andrés Marafioti</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The advancement of vision-language models (VLMs) is hampered by a fragmented landscape of inconsistent and contaminated public datasets. We introduce FineVision, a meticulously collected, curated, and unified corpus of 24 million samples - the largest open resource of its kind. We unify more than 200 sources into 185 subsets via a semi-automated, human-in-the-loop pipeline: automation performs bulk ingestion and schema mapping, while reviewers audit mappings and spot-check outputs to verify faithful consumption of annotations, appropriate formatting and diversity, and safety; issues trigger targeted fixes and re-runs. The workflow further applies rigorous de-duplication within and across sources and decontamination against 66 public benchmarks. FineVision also encompasses agentic/GUI tasks with a unified action space; reviewers validate schemas and inspect a sample of trajectories to confirm executable fidelity. Models trained on FineVision consistently outperform those trained on existing open mixtures across a broad evaluation suite, underscoring the benefits of scale, data hygiene, and balanced automation with human oversight. We release the corpus and curation tools to accelerate data-centric VLM research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17269</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 07:54:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Paper2Web: Let's Make Your Paper Alive!</title>
|
||||
<link>https://arxiv.org/abs/2510.15842</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhang Chen, Tianpeng Lv, Siyi Zhang, Yixiang Yin, Yao Wan, Philip S. Yu, Dongping Chen</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Academic project websites can more effectively disseminate research when they clearly present core content and enable intuitive navigation and interaction. However, current approaches such as direct Large Language Model (LLM) generation, templates, or direct HTML conversion struggle to produce layout-aware, interactive sites, and a comprehensive evaluation suite for this task has been lacking. In this paper, we introduce Paper2Web, a benchmark dataset and multi-dimensional evaluation framework for assessing academic webpage generation. It incorporates rule-based metrics like Connectivity, Completeness and human-verified LLM-as-a-Judge (covering interactivity, aesthetics, and informativeness), and PaperQuiz, which measures paper-level knowledge retention. We further present PWAgent, an autonomous pipeline that converts scientific papers into interactive and multimedia-rich academic homepages. The agent iteratively refines both content and layout through MCP tools that enhance emphasis, balance, and presentation quality. Our experiments show that PWAgent consistently outperforms end-to-end baselines like template-based webpages and arXiv/alphaXiv versions by a large margin while maintaining low cost, achieving the Pareto-front in academic webpage generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15842</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:35:58 +0000</pubDate>
|
||||
<title>Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.17354</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenghao Zhang, Guanting Dong, Xinyu Yang, Zhicheng Dou</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) by retrieving relevant documents from an external corpus. However, existing RAG systems primarily focus on unimodal text documents, and often fall short in real-world scenarios where both queries and documents may contain mixed modalities (such as text and images). In this paper, we address the challenge of Universal Retrieval-Augmented Generation (URAG), which involves retrieving and reasoning over mixed-modal information to improve vision-language generation. To this end, we propose Nyx, a unified mixed-modal to mixed-modal retriever tailored for URAG scenarios. To mitigate the scarcity of realistic mixed-modal data, we introduce a four-stage automated pipeline for generation and filtering, leveraging web documents to construct NyxQA, a dataset comprising diverse mixed-modal question-answer pairs that better reflect real-world information needs. Building on this high-quality dataset, we adopt a two-stage training framework for Nyx: we first perform pre-training on NyxQA along with a variety of open-source retrieval datasets, followed by supervised fine-tuning using feedback from downstream vision-language models (VLMs) to align retrieval outputs with generative preferences. Experimental results demonstrate that Nyx not only performs competitively on standard text-only RAG benchmarks, but also excels in the more general and realistic URAG setting, significantly improving generation quality in vision-language tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17354</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 09:56:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>BLIP3o-NEXT: Next Frontier of Native Image Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.15857</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15857.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiuhai Chen, Le Xue, Zhiyang Xu, Xichen Pan, Shusheng Yang, Can Qin, An Yan, Honglu Zhou, Zeyuan Chen, Lifu Huang, Tianyi Zhou, Junnan Li, Silvio Savarese, Caiming Xiong, Ran Xu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present BLIP3o-NEXT, a fully open-source foundation model in the BLIP3 series that advances the next frontier of native image generation. BLIP3o-NEXT unifies text-to-image generation and image editing within a single architecture, demonstrating strong image generation and image editing capabilities. In developing the state-of-the-art native image generation model, we identify four key insights: (1) Most architectural choices yield comparable performance; an architecture can be deemed effective provided it scales efficiently and supports fast inference; (2) The successful application of reinforcement learning can further push the frontier of native image generation; (3) Image editing still remains a challenging task, yet instruction following and the consistency between generated and reference images can be significantly enhanced through post-training and data engine; (4) Data quality and scale continue to be decisive factors that determine the upper bound of model performance. Building upon these insights, BLIP3o-NEXT leverages an Autoregressive + Diffusion architecture in which an autoregressive model first generates discrete image tokens conditioned on multimodal inputs, whose hidden states are then used as conditioning signals for a diffusion model to generate high-fidelity images. This architecture integrates the reasoning strength and instruction following of autoregressive models with the fine-detail rendering ability of diffusion models, achieving a new level of coherence and realism. Extensive evaluations of various text-to-image and image-editing benchmarks show that BLIP3o-NEXT achieves superior performance over existing models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15857</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:50:58 +0000</pubDate>
|
||||
<title>Agentic Reinforcement Learning for Search is Unsafe</title>
|
||||
<link>https://arxiv.org/abs/2510.17431</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17431.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yushi Yang, Shreyansh Padarha, Andrew Lee, Adam Mahdi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not well understood. In this study, we show that RL-trained search models inherit refusal from instruction tuning and often deflect harmful requests by turning them into safe queries. However, this safety is fragile. Two simple attacks, one that forces the model to begin response with search (Search attack), another that encourages models to repeatedly search (Multi-search attack), trigger cascades of harmful searches and answers. Across two model families (Qwen, Llama) with both local and web search, these attacks lower refusal rates by up to 60.0%, answer safety by 82.5%, and search-query safety by 82.4%. The attacks succeed by triggering models to generate harmful, request-mirroring search queries before they can generate the inherited refusal tokens. This exposes a core weakness of current RL training: it rewards continued generation of effective queries without accounting for their harmfulness. As a result, RL search models have vulnerabilities that users can easily exploit, making it urgent to develop safety-aware agentic RL pipelines optimising for safe search.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17431</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 11:19:37 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training</title>
|
||||
<link>https://arxiv.org/abs/2510.15859</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15859.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengkai Wang, Qi Zuo, Pengwei Liu, Zhijie Sang, Congkai Xie, Hongxia Yang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large Language Models (LLMs) have shown substantial advances through reinforcement learning (RL), particularly in domains where rewards can be programmatically verified, such as mathematics and code. In these areas, models benefit from a well-defined operational base guided by explicit rule-based objectives. However, this progress reveals a significant limitation: in open-ended domains where rewards are ambiguous, subjective, or context-dependent, such as creative writing, scientific reasoning, and notably medical consultation, robust reward functions are lacking, making these areas challenging for current RL strategies. To bridge this gap, we introduce ORBIT, an open-ended rubric-based incremental training framework specifically designed for high-stakes medical dialogue. ORBIT integrates syn- thetic dialogue generation with the dynamic creation of rubrics, employing these rubrics to direct an incremental RL process. In particular, this approach does not depend on external medical knowledge or manual rules, instead utilizing rubric-guided feedback to shape learning. When implemented on the Qwen3-4B-Instruct model, our method can greatly enhance its performance on the HealthBench-Hard benchmark from 7.0 to 27.2 using only 2k samples, thus achieving state-of-the-art results for models of this scale. Our analysis confirms that rubric-driven RL fos-ters consistent performance gains across diverse consultation scenarios, going beyond simple numerical improvements. These findings underscore rubric-based feedback as a scalable strategy for advancing LLMs in intricate, open-ended tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15859</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:51:28 +0000</pubDate>
|
||||
<title>Deep Self-Evolving Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2510.17498</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17498.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Liu, Shun Zheng, Xumeng Wen, Yang Wang, Jiang Bian, Mao Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Long-form chain-of-thought reasoning has become a cornerstone of advanced reasoning in large language models. While recent verification-refinement frameworks have enabled proprietary models to solve Olympiad-level problems, their effectiveness hinges on strong, reliable verification and correction capabilities, which remain fragile in open-weight, smaller-scale models. This work demonstrates that even with weak verification and refinement capabilities on hard tasks, the reasoning limits of such models can be substantially extended through a probabilistic paradigm we call Deep Self-Evolving Reasoning (DSER). We conceptualize iterative reasoning as a Markov chain, where each step represents a stochastic transition in the solution space. The key insight is that convergence to a correct solution is guaranteed as long as the probability of improvement marginally exceeds that of degradation. By running multiple long-horizon, self-evolving processes in parallel, DSER amplifies these small positive tendencies, enabling the model to asymptotically approach correct answers. Empirically, we apply DSER to the DeepSeek-R1-0528-Qwen3-8B model. On the challenging AIME 2024-2025 benchmark, DSER solves 5 out of 9 previously unsolvable problems and boosts overall performance, enabling this compact model to surpass the single-turn accuracy of its 600B-parameter teacher through majority voting. Beyond its immediate utility for test-time scaling, the DSER framework serves to diagnose the fundamental limitations of current open-weight reasoners. By clearly delineating their shortcomings in self-verification, refinement, and stability, our findings establish a clear research agenda for developing next-generation models with powerful, intrinsic self-evolving capabilities.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17498</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 12:51:42 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal</title>
|
||||
<link>https://arxiv.org/abs/2510.15868</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15868.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shr-Ruei Tsai, Wei-Cheng Chang, Jie-Ying Lee, Chih-Hai Su, Yu-Lun Liu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Lens flare significantly degrades image quality, impacting critical computer vision tasks like object detection and autonomous driving. Recent Single Image Flare Removal (SIFR) methods perform poorly when off-frame light sources are incomplete or absent. We propose LightsOut, a diffusion-based outpainting framework tailored to enhance SIFR by reconstructing off-frame light sources. Our method leverages a multitask regression module and LoRA fine-tuned diffusion model to ensure realistic and physically consistent outpainting results. Comprehensive experiments demonstrate LightsOut consistently boosts the performance of existing SIFR methods across challenging scenarios without additional retraining, serving as a universally applicable plug-and-play preprocessing solution. Project page: https://ray-1026.github.io/lightsout/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15868</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:59:50 +0000</pubDate>
|
||||
<title>Annotation-Efficient Universal Honesty Alignment</title>
|
||||
<link>https://arxiv.org/abs/2510.17509</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17509.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyu Ni, Keping Bi, Jiafeng Guo, Minghao Tang, Jingtong Wu, Zengxin Han, Xueqi Cheng</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Honesty alignment-the ability of large language models (LLMs) to recognize their knowledge boundaries and express calibrated confidence-is essential for trustworthy deployment. Existing methods either rely on training-free confidence estimation (e.g., token probabilities, self-consistency) or training-based calibration with correctness annotations. While effective, achieving universal honesty alignment with training-based calibration requires costly, large-scale labeling. To support annotation-efficient training, we introduce Elicitation-Then-Calibration (EliCal), a two-stage framework that first elicits internal confidence using inexpensive self-consistency supervision, then calibrates this confidence with a small set of correctness annotations. To support a large-scale study, we release HonestyBench, a benchmark covering ten free-form QA datasets with 560k training and 70k evaluation instances annotated with correctness and self-consistency signals. Experiments show that EliCal achieves near-optimal alignment with only 1k correctness annotations (0.18% of full supervision) and better alignment performance on unseen MMLU tasks than the calibration-only baseline, offering a scalable solution toward universal honesty alignment in LLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17509</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 13:05:22 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery</title>
|
||||
<link>https://arxiv.org/abs/2510.15869</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15869.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai, Wei-Cheng Chang, Chung-Ho Wu, Jiewen Chan, Zhenjun Zhao, Chieh Hubert Lin, Yu-Lun Liu</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task in providing immersive and embodied applications. The challenges lie in the lack of large-scale and high-quality real-world 3D scans for training generalizable generative models. In this paper, we take an alternative route to create large-scale 3D scenes by synergizing the readily available satellite imagery that supplies realistic coarse geometry and the open-domain diffusion model for creating high-quality close-up appearances. We propose Skyfall-GS, the first city-block scale 3D scene creation framework without costly 3D annotations, also featuring real-time, immersive 3D exploration. We tailor a curriculum-driven iterative refinement strategy to progressively enhance geometric completeness and photorealistic textures. Extensive experiments demonstrate that Skyfall-GS provides improved cross-view consistent geometry and more realistic textures compared to state-of-the-art approaches. Project page: https://skyfall-gs.jayinnn.dev/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15869</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:59:51 +0000</pubDate>
|
||||
<title>PICABench: How Far Are We from Physically Realistic Image Editing?</title>
|
||||
<link>https://arxiv.org/abs/2510.17681</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17681.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuandong Pu, Le Zhuo, Songhao Han, Jinbo Xing, Kaiwen Zhu, Shuo Cao, Bin Fu, Si Liu, Hongsheng Li, Yu Qiao, Wenlong Zhang, Xi Chen, Yihao Liu</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond completing the editing instructions, the accompanying physical effects are the key to the generation realism. For example, removing an object should also remove its shadow, reflections, and interactions with nearby objects. Unfortunately, existing models and benchmarks mainly focus on instruction completion but overlook these physical effects. So, at this moment, how far are we from physically realistic image editing? To answer this, we introduce PICABench, which systematically evaluates physical realism across eight sub-dimension (spanning optics, mechanics, and state transitions) for most of the common editing operations (add, remove, attribute change, etc). We further propose the PICAEval, a reliable evaluation protocol that uses VLM-as-a-judge with per-case, region-level human annotations and questions. Beyond benchmarking, we also explore effective solutions by learning physics from videos and construct a training dataset PICA-100K. After evaluating most of the mainstream models, we observe that physical realism remains a challenging problem with large rooms to explore. We hope that our benchmark and proposed solutions can serve as a foundation for future work moving from naive content editing toward physically consistent realism.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17681</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 15:53:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM</title>
|
||||
<link>https://arxiv.org/abs/2510.15870</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.15870.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanrong Ye, Chao-Han Huck Yang, Arushi Goel, Wei Huang, Ligeng Zhu, Yuanhang Su, Sean Lin, An-Chieh Cheng, Zhen Wan, Jinchuan Tian, Yuming Lou, Dong Yang, Zhijian Liu, Yukang Chen, Ambrish Dantrey, Ehsan Jahangiri, Sreyan Ghosh, Daguang Xu, Ehsan Hosseini-Asl, Danial Mohseni Taheri, Vidya Murali, Sifei Liu, Jason Lu, Oluwatobi Olabiyi, Frank Wang, Rafael Valle, Bryan Catanzaro, Andrew Tao, Song Han, Jan Kautz, Hongxu Yin, Pavlo Molchanov</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Advancing machine intelligence requires developing the ability to perceive across multiple modalities, much as humans sense the world. We introduce OmniVinci, an initiative to build a strong, open-source, omni-modal LLM. We carefully study the design choices across model architecture and data curation. For model architecture, we present three key innovations: (i) OmniAlignNet for strengthening alignment between vision and audio embeddings in a shared omni-modal latent space; (ii) Temporal Embedding Grouping for capturing relative temporal alignment between vision and audio signals; and (iii) Constrained Rotary Time Embedding for encoding absolute temporal information in omni-modal embeddings. We introduce a curation and synthesis pipeline that generates 24M single-modal and omni-modal conversations. We find that modalities reinforce one another in both perception and reasoning. Our model, OmniVinci, outperforms Qwen2.5-Omni with +19.05 on DailyOmni (cross-modal understanding), +1.7 on MMAR (audio), and +3.9 on Video-MME (vision), while using just 0.2T training tokens - a 6 times reduction compared to Qwen2.5-Omni's 1.2T. We finally demonstrate omni-modal advantages in downstream applications spanning robotics, medical AI, and smart factory.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.15870</guid>
|
||||
<pubDate>Fri, 17 Oct 2025 17:59:59 +0000</pubDate>
|
||||
<title>QueST: Incentivizing LLMs to Generate Difficult Problems</title>
|
||||
<link>https://arxiv.org/abs/2510.17715</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17715.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanxu Hu, Xingxing Zhang, Jannis Vamvas, Rico Sennrich, Furu Wei</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Large Language Models have achieved strong performance on reasoning tasks, solving competition-level coding and math problems. However, their scalability is limited by human-labeled datasets and the lack of large-scale, challenging coding problem training data. Existing competitive coding datasets contain only thousands to tens of thousands of problems. Previous synthetic data generation methods rely on either augmenting existing instruction datasets or selecting challenging problems from human-labeled data. In this paper, we propose QueST, a novel framework which combines difficulty-aware graph sampling and difficulty-aware rejection fine-tuning that directly optimizes specialized generators to create challenging coding problems. Our trained generators demonstrate superior capability compared to even GPT-4o at creating challenging problems that benefit downstream performance. We leverage QueST to generate large-scale synthetic coding problems, which we then use to distill from strong teacher models with long chain-of-thought or to conduct reinforcement learning for smaller models, proving effective in both scenarios. Our distillation experiments demonstrate significant performance gains. Specifically, after fine-tuning Qwen3-8B-base on 100K difficult problems generated by QueST, we surpass the performance of the original Qwen3-8B on LiveCodeBench. With an additional 112K examples (i.e., 28K human-written problems paired with multiple synthetic solutions), our 8B model matches the performance of the much larger DeepSeek-R1-671B. These findings indicate that generating complex problems via QueST offers an effective and scalable approach to advancing the frontiers of competitive coding and reasoning for large language models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17715</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 16:29:53 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action</title>
|
||||
<link>https://arxiv.org/abs/2510.17790</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17790.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Yang, Zhen Yang, Zi-Yi Dou, Anh Nguyen, Keen You, Omar Attia, Andrew Szot, Michael Feng, Ram Ramrakhya, Alexander Toshev, Chao Huang, Yinfei Yang, Zhe Gan</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal agents for computer use rely exclusively on primitive actions (click, type, scroll) that require accurate visual grounding and lengthy execution chains, leading to cascading failures and performance bottlenecks. While other agents leverage rich programmatic interfaces (APIs, MCP servers, tools), computer-use agents (CUAs) remain isolated from these capabilities. We present UltraCUA, a foundation model that bridges this gap through hybrid action -- seamlessly integrating GUI primitives with high-level programmatic tool calls. To achieve this, our approach comprises four key components: (1) an automated pipeline that scales programmatic tools from software documentation, open-source repositories, and code generation; (2) a synthetic data engine producing over 17,000 verifiable tasks spanning real-world computer-use scenarios; (3) a large-scale high-quality hybrid action trajectory collection with both low-level GUI actions and high-level programmatic tool calls; and (4) a two-stage training pipeline combining supervised fine-tuning with online reinforcement learning, enabling strategic alternation between low-level and high-level actions. Experiments with our 7B and 32B models demonstrate substantial improvements over state-of-the-art agents. On OSWorld, UltraCUA models achieve an average 22% relative improvement over base models, while being 11% faster in terms of steps. Out-of-domain evaluation on WindowsAgentArena shows our model reaches 21.7% success rate, outperforming baselines trained on Windows data. The hybrid action mechanism proves critical, reducing error propagation while maintaining execution efficiency.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17790</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 17:48:26 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains</title>
|
||||
<link>https://arxiv.org/abs/2510.17793</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Austin Xu, Xuan-Phi Nguyen, Yilun Zhou, Chien-Sheng Wu, Caiming Xiong, Shafiq Joty</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Finetuning specialized generative evaluators has emerged as a popular paradigm to meet the increasing demand for scalable evaluation during both training and test-time. However, recent work has largely focused on applying new methodology, such as reinforcement learning (RL), to training evaluators, shying away from large-scale, data-driven development. In this work, we focus on data scaling, curating a set of 2.5M samples spanning five unique evaluation tasks (pairwise, step-level, reference-free and reference-based verification, and single rating) and multiple domains focused on reasoning evaluation. With our data, we train Foundational Automatic Reasoning Evaluators (FARE), a family of 8B and 20B (with 3.6B active) parameter evaluators, with a simple iterative rejection-sampling supervised finetuning (SFT) approach. FARE-8B challenges larger specialized RL-trained evaluators and FARE-20B sets the new standard for open-source evaluators, surpassing specialized 70B+ evaluators. Beyond static benchmarks, we evaluate FARE in real-world tasks: As inference-time rerankers, FARE-20B achieves near-oracle performance on MATH. As verifiers in RL training, FARE improves the downstream RL-trained model performance by up to 14.1% vs. string-matching verifiers. When initialized from FARE, a continually-finetuned FARE-Code outperforms gpt-oss-20B by 65% on evaluating test-case quality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17793</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 17:52:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Executable Knowledge Graphs for Replicating AI Research</title>
|
||||
<link>https://arxiv.org/abs/2510.17795</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17795.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujie Luo, Zhuoyun Yu, Xuehai Wang, Yuqi Zhu, Ningyu Zhang, Lanning Wei, Lun Du, Da Zheng, Huajun Chen</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of retrieval-augmented generation (RAG) methods, which fail to capture latent technical details hidden in referenced papers. Furthermore, previous approaches tend to overlook valuable implementation-level code signals and lack structured knowledge representations that support multi-granular retrieval and reuse. To overcome these challenges, we propose Executable Knowledge Graphs (xKG), a modular and pluggable knowledge base that automatically integrates technical insights, code snippets, and domain-specific knowledge extracted from scientific literature. When integrated into three agent frameworks with two different LLMs, xKG shows substantial performance gains (10.9% with o3-mini) on PaperBench, demonstrating its effectiveness as a general and extensible solution for automated AI research replication. Code will released at https://github.com/zjunlp/xKG.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17795</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 17:53:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics</title>
|
||||
<link>https://arxiv.org/abs/2510.17797</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17797.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Akshara Prabhakar, Roshan Ram, Zixiang Chen, Silvio Savarese, Frank Wang, Caiming Xiong, Huan Wang, Weiran Yao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> As information grows exponentially, enterprises face increasing pressure to transform unstructured data into coherent, actionable insights. While autonomous agents show promise, they often struggle with domain-specific nuances, intent alignment, and enterprise integration. We present Enterprise Deep Research (EDR), a multi-agent system that integrates (1) a Master Planning Agent for adaptive query decomposition, (2) four specialized search agents (General, Academic, GitHub, LinkedIn), (3) an extensible MCP-based tool ecosystem supporting NL2SQL, file analysis, and enterprise workflows, (4) a Visualization Agent for data-driven insights, and (5) a reflection mechanism that detects knowledge gaps and updates research direction with optional human-in-the-loop steering guidance. These components enable automated report generation, real-time streaming, and seamless enterprise deployment, as validated on internal datasets. On open-ended benchmarks including DeepResearch Bench and DeepConsult, EDR outperforms state-of-the-art agentic systems without any human steering. We release the EDR framework and benchmark trajectories to advance research on multi-agent reasoning applications. Code at https://github.com/SalesforceAIResearch/enterprise-deep-research and Dataset at https://huggingface.co/datasets/Salesforce/EDR-200</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17797</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 17:55:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Glyph: Scaling Context Windows via Visual-Text Compression</title>
|
||||
<link>https://arxiv.org/abs/2510.17800</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive computational and memory costs, limiting the practicality of long-context LLMs. In this work, we take a different perspective-visual context scaling-to tackle this challenge. Instead of extending token-based sequences, we propose Glyph, a framework that renders long texts into images and processes them with vision-language models (VLMs). This approach substantially compresses textual input while preserving semantic information, and we further design an LLM-driven genetic search to identify optimal visual rendering configurations for balancing accuracy and compression. Through extensive experiments, we demonstrate that our method achieves 3-4x token compression while maintaining accuracy comparable to leading LLMs such as Qwen3-8B on various long-context benchmarks. This compression also leads to around 4x faster prefilling and decoding, and approximately 2x faster SFT training. Furthermore, under extreme compression, a 128K-context VLM could scale to handle 1M-token-level text tasks. In addition, the rendered text data benefits real-world multimodal tasks, such as document understanding. Our code and model are released at https://github.com/thu-coai/Glyph.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17800</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 17:58:56 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ConsistEdit: Highly Consistent and Precise Training-free Visual Editing</title>
|
||||
<link>https://arxiv.org/abs/2510.17803</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixin Yin, Ling-Hao Chen, Lionel Ni, Xili Dai</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent advances in training-free attention control methods have enabled flexible and efficient text-guided editing capabilities for existing generation models. However, current approaches struggle to simultaneously deliver strong editing strength while preserving consistency with the source. This limitation becomes particularly critical in multi-round and video editing, where visual errors can accumulate over time. Moreover, most existing methods enforce global consistency, which limits their ability to modify individual attributes such as texture while preserving others, thereby hindering fine-grained editing. Recently, the architectural shift from U-Net to MM-DiT has brought significant improvements in generative performance and introduced a novel mechanism for integrating text and vision modalities. These advancements pave the way for overcoming challenges that previous methods failed to resolve. Through an in-depth analysis of MM-DiT, we identify three key insights into its attention mechanisms. Building on these, we propose ConsistEdit, a novel attention control method specifically tailored for MM-DiT. ConsistEdit incorporates vision-only attention control, mask-guided pre-attention fusion, and differentiated manipulation of the query, key, and value tokens to produce consistent, prompt-aligned edits. Extensive experiments demonstrate that ConsistEdit achieves state-of-the-art performance across a wide range of image and video editing tasks, including both structure-consistent and structure-inconsistent scenarios. Unlike prior methods, it is the first approach to perform editing across all inference steps and attention layers without handcraft, significantly enhancing reliability and consistency, which enables robust multi-round and multi-region editing. Furthermore, it supports progressive adjustment of structural consistency, enabling finer control.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.17803</guid>
|
||||
<pubDate>Mon, 20 Oct 2025 17:59:52 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user