diff --git a/feed.xml b/feed.xml index c647441..5cbac27 100644 --- a/feed.xml +++ b/feed.xml @@ -7,510 +7,370 @@ http://www.rssboard.org/rss-specification python-feedgen en - Wed, 04 Feb 2026 00:04:06 +0000 + Thu, 05 Feb 2026 00:04:52 +0000 - Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation - https://arxiv.org/abs/2601.14691 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.14691.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn, Yunxiang Zhang, Moontae Lee, Hao Peng, Lu Wang, Honglak Lee</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories including chain-of-thought (CoT) reasoning. This paradigm implicitly assumes that the agent's CoT faithfully reflects both its internal reasoning and the underlying environment state. We show this assumption is brittle: LLM judges are highly susceptible to manipulation of agent reasoning traces. By systematically rewriting agent CoTs while holding actions and observations fixed, we demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks. We study manipulation strategies spanning style-based approaches that alter only the presentation of reasoning and content-based approaches that fabricate signals of task progress, and find that content-based manipulations are consistently more effective. We evaluate prompting-based techniques and scaling judge-time compute, which reduce but do not fully eliminate susceptibility to manipulation. Our findings reveal a fundamental vulnerability in LLM-based evaluation and highlight the need for judging mechanisms that verify reasoning claims against observable evidence.</p> - https://arxiv.org/abs/2601.14691 - Wed, 21 Jan 2026 06:07:43 +0000 + Glance and Focus Reinforcement for Pan-cancer Screening + https://arxiv.org/abs/2601.19103 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.19103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linshan Wu, Jiaxin Zhuang, Hao Chen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Pan-cancer screening in large-scale CT scans remains challenging for existing AI methods, primarily due to the difficulty of localizing diverse types of tiny lesions in large CT volumes. The extreme foreground-background imbalance significantly hinders models from focusing on diseased regions, while redundant focus on healthy regions not only decreases the efficiency but also increases false positives. Inspired by radiologists' glance and focus diagnostic strategy, we introduce GF-Screen, a Glance and Focus reinforcement learning framework for pan-cancer screening. GF-Screen employs a Glance model to localize the diseased regions and a Focus model to precisely segment the lesions, where segmentation results of the Focus model are leveraged to reward the Glance model via Reinforcement Learning (RL). Specifically, the Glance model crops a group of sub-volumes from the entire CT volume and learns to select the sub-volumes with lesions for the Focus model to segment. Given that the selecting operation is non-differentiable for segmentation training, we propose to employ the segmentation results to reward the Glance model. To optimize the Glance model, we introduce a novel group relative learning paradigm, which employs group relative comparison to prioritize high-advantage predictions and discard low-advantage predictions within sub-volume groups, not only improving efficiency but also reducing false positives. In this way, for the first time, we effectively extend cutting-edge RL techniques to tackle the specific challenges in pan-cancer screening. Extensive experiments on 16 internal and 7 external datasets across 9 lesion types demonstrated the effectiveness of GF-Screen. Notably, GF-Screen leads the public validation leaderboard of MICCAI FLARE25 pan-cancer challenge, surpassing the FLARE24 champion solution by a large margin (+25.6% DSC and +28.2% NSD).</p> + https://arxiv.org/abs/2601.19103 + Tue, 27 Jan 2026 02:10:34 +0000 - On the Relationship Between Representation Geometry and Generalization in Deep Neural Networks - https://arxiv.org/abs/2602.00130 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00130.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sumit Yadav</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We investigate the relationship between representation geometry and neural network performance. Analyzing 52 pretrained ImageNet models across 13 architecture families, we show that effective dimension -- an unsupervised geometric metric -- strongly predicts accuracy. Output effective dimension achieves partial r=0.75 (p < 10^(-10)) after controlling for model capacity, while total compression achieves partial r=-0.72. These findings replicate across ImageNet and CIFAR-10, and generalize to NLP: effective dimension predicts performance for 8 encoder models on SST-2/MNLI and 15 decoder-only LLMs on AG News (r=0.69, p=0.004), while model size does not (r=0.07). We establish bidirectional causality: degrading geometry via noise causes accuracy loss (r=-0.94, p < 10^(-9)), while improving geometry via PCA maintains accuracy across architectures (-0.03pp at 95% variance). This relationship is noise-type agnostic -- Gaussian, Uniform, Dropout, and Salt-and-pepper noise all show |r| > 0.90. These results establish that effective dimension provides domain-agnostic predictive and causal information about neural network performance, computed entirely without labels.</p> - https://arxiv.org/abs/2602.00130 - Wed, 28 Jan 2026 04:33:41 +0000 + WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models + https://arxiv.org/abs/2602.02537 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02537.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runjie Zhou, Youbo Shao, Haoyu Lu, Bowei Xing, Tongtong Bai, Yujie Chen, Jie Zhao, Lin Sui, Haotian Yao, Zijia Zhao, Hao Yang, Haoning Wu, Zaida Zhou, Jinguo Zhu, Zhiqi Huang, Yiping Bao, Yangyang Liu, Y. Charles, Xinyu Zhou</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce WorldVQA, a benchmark designed to evaluate the atomic visual world knowledge of Multimodal Large Language Models (MLLMs). Unlike current evaluations, which often conflate visual knowledge retrieval with reasoning, WorldVQA decouples these capabilities to strictly measure "what the model memorizes." The benchmark assesses the atomic capability of grounding and naming visual entities across a stratified taxonomy, spanning from common head-class objects to long-tail rarities. We expect WorldVQA to serve as a rigorous test for visual factuality, thereby establishing a standard for assessing the encyclopedic breadth and hallucination rates of current and next-generation frontier models.</p> + https://arxiv.org/abs/2602.02537 + Wed, 28 Jan 2026 11:27:22 +0000 - AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios - https://arxiv.org/abs/2601.20613 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.20613.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiyuan Chen, Qimin Wu, Taiyu Hou, Tianhao Tang, Xueyu Hu, Yuchen Hou, Bikun Li, Chengming Qian, Guoyin Wang, Haolin Chen, Haotong Tian, Haoye Zhang, Haoyu Bian, Hongbing Pan, Hongkang Zhang, Hongyi Zhou, Jiaqi Cai, Jiewu Rao, Jiyuan Ren, Keduan Huang, Lucia Zhu Huang, Mingyu Yuan, Naixu Guo, Qicheng Tang, Qinyan Zhang, Shuai Chen, Siheng Chen, Ting Ting Li, Xiaoxing Guo, Yaocheng Zuo, Yaoqi Guo, Yinan Wang, Yinzhou Yu, Yize Wang, Yuan Jiang, Yuan Tian, Yuanshuo Zhang, Yuxuan Liu, Yvette Yan Zeng, Zenyu Shan, Zihan Yin, Xiaobo Hu, Yang Liu, Yixin Ren, Yuan Gong</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and complex problem-solving evaluations. However, in daily scenarios, the perception of these advanced AI capabilities among general users remains limited. We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks necessary to cover the daily work, life, and learning activities of a broad demographic. To address this, we propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks. These tasks require not only solving problems through dialogue but also understanding various attachment types and delivering tangible file-based results. The benchmark is structured around three user-centric categories: Open Workflow Execution, which assesses adherence to explicit and complex workflows; Latent Instruction, which requires agents to infer implicit instructions from attachments; and Iterative Refinement, which involves modifying or expanding upon ongoing work. We employ instance-level rubrics and a refined evaluation pipeline that aligns LLM-based verification with human judgment, achieving an 80.1% agreement rate using Gemini-3-Pro. AgentIF-OneDay comprises 104 tasks covering 767 scoring points. We benchmarked four leading general AI agents and found that agent products built based on APIs and ChatGPT agents based on agent RL remain in the first tier simultaneously. Leading LLM APIs and open-source models have internalized agentic capabilities, enabling AI application teams to develop cutting-edge Agent products.</p> - https://arxiv.org/abs/2601.20613 - Wed, 28 Jan 2026 13:49:18 +0000 + Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification + https://arxiv.org/abs/2601.21244 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.21244.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiju Guo, Tianyi Hu, Zexu Sun, Yankai Lin</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low sampling success and unstable training in complex tasks. We find that many exploration failures arise not from problem difficulty, but from a small number of prompt tokens that introduce interference. Building on this insight, we propose the Less Noise Sampling Framework (LENS), which first prompts by identifying and removing interference tokens. then transfers successful rollouts from the purification process to supervise policy optimization on the original noisy prompts, enabling the model to learn to ignore interference in the real-world, noisy prompting settings. Experimental results show that LENS significantly outperforms GRPO, delivering higher performance and faster convergence, with a 3.88% average gain and over 1.6times speedup. Our work highlights the critical role of pruning interference tokens in improving rollout efficiency, offering a new perspective for RLVR research.</p> + https://arxiv.org/abs/2601.21244 + Thu, 29 Jan 2026 04:08:24 +0000 - CUA-Skill: Develop Skills for Computer Using Agent - https://arxiv.org/abs/2601.21123 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.21123.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyi Chen, Yinheng Li, Michael Solodko, Sen Wang, Nan Jiang, Tingyuan Cui, Junheng Hao, Jongwoo Ko, Sara Abdali, Suzhen Zheng, Leon Xu, Hao Fan, Pashmina Cameron, Justin Wagle, Kazuhito Koishida</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Computer-Using Agents (CUAs) aim to autonomously operate computer systems to complete real-world tasks. However, existing agentic systems remain difficult to scale and lag behind human performance. A key limitation is the absence of reusable and structured skill abstractions that capture how humans interact with graphical user interfaces and how to leverage these skills. We introduce CUA-Skill, a computer-using agentic skill base that encodes human computer-use knowledge as skills coupled with parameterized execution and composition graphs. CUA-Skill is a large-scale library of carefully engineered skills spanning common Windows applications, serving as a practical infrastructure and tool substrate for scalable, reliable agent development. Built upon this skill base, we construct CUA-Skill Agent, an end-to-end computer-using agent that supports dynamic skill retrieval, argument instantiation, and memory-aware failure recovery. Our results demonstrate that CUA-Skill substantially improves execution success rates and robustness on challenging end-to-end agent benchmarks, establishing a strong foundation for future computer-using agent development. On WindowsAgentArena, CUA-Skill Agent achieves state-of-the-art 57.5% (best of three) successful rate while being significantly more efficient than prior and concurrent approaches. The project page is available at https://microsoft.github.io/cua_skill/.</p> - https://arxiv.org/abs/2601.21123 - Wed, 28 Jan 2026 23:38:25 +0000 + Position: Agentic Evolution is the Path to Evolving LLMs + https://arxiv.org/abs/2602.00359 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00359.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minhua Lin, Hanqing Lu, Zhan Shi, Bing He, Rui Mao, Zhiwei Zhang, Zongyu Wu, Xianfeng Tang, Hui Liu, Zhenwei Dai, Xiang Zhang, Suhang Wang, Benoit Dumoulin, Jian Pei</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time and inference-time compute improves static capability but does not close this train-deploy gap. We argue that addressing this limitation requires a new scaling axis-evolution. Existing deployment-time adaptation methods, whether parametric fine-tuning or heuristic memory accumulation, lack the strategic agency needed to diagnose failures and produce durable improvements. Our position is that agentic evolution represents the inevitable future of LLM adaptation, elevating evolution itself from a fixed pipeline to an autonomous evolver agent. We instantiate this vision in a general framework, A-Evolve, which treats deployment-time improvement as a deliberate, goal-directed optimization process over persistent system state. We further propose the evolution-scaling hypothesis: the capacity for adaptation scales with the compute allocated to evolution, positioning agentic evolution as a scalable path toward sustained, open-ended adaptation in the real world.</p> + https://arxiv.org/abs/2602.00359 + Fri, 30 Jan 2026 22:15:58 +0000 - Influence Guided Sampling for Domain Adaptation of Text Retrievers - https://arxiv.org/abs/2601.21759 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.21759.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meet Doshi, Vishwajeet Kumar, Yulong Li, Jaydeep Sen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> General-purpose open-domain dense retrieval systems are usually trained with a large, eclectic mix of corpora and search tasks. How should these diverse corpora and tasks be sampled for training? Conventional approaches sample them uniformly, proportional to their instance population sizes, or depend on human-level expert supervision. It is well known that the training data sampling strategy can greatly impact model performance. However, how to find the optimal strategy has not been adequately studied in the context of embedding models. We propose Inf-DDS, a novel reinforcement learning driven sampling framework that adaptively reweighs training datasets guided by influence-based reward signals and is much more lightweight with respect to GPU consumption. Our technique iteratively refines the sampling policy, prioritizing datasets that maximize model performance on a target development set. We evaluate the efficacy of our sampling strategy on a wide range of text retrieval tasks, demonstrating strong improvements in retrieval performance and better adaptation compared to existing gradient-based sampling methods, while also being 1.5x to 4x cheaper in GPU compute. Our sampling strategy achieves a 5.03 absolute NDCG@10 improvement while training a multilingual bge-m3 model and an absolute NDCG@10 improvement of 0.94 while training all-MiniLM-L6-v2, even when starting from expert-assigned weights on a large pool of training datasets.</p> - https://arxiv.org/abs/2601.21759 - Thu, 29 Jan 2026 14:14:29 +0000 + MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers + https://arxiv.org/abs/2602.00398 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00398.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ajay Jaiswal, Lauren Hannah, Han-Byul Kim, Duc Hoang, Arnav Kundu, Mehrdad Farajtabar, Minsik Cho</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Understanding how transformer components operate in LLMs is important, as it is at the core of recent technological advances in artificial intelligence. In this work, we revisit the challenges associated with interpretability of feed-forward modules (FFNs) and propose MemoryLLM, which aims to decouple FFNs from self-attention and enables us to study the decoupled FFNs as context-free token-wise neural retrieval memory. In detail, we investigate how input tokens access memory locations within FFN parameters and the importance of FFN memory across different downstream tasks. MemoryLLM achieves context-free FFNs by training them in isolation from self-attention directly using the token embeddings. This approach allows FFNs to be pre-computed as token-wise lookups (ToLs), enabling on-demand transfer between VRAM and storage, additionally enhancing inference efficiency. We also introduce Flex-MemoryLLM, positioning it between a conventional transformer design and MemoryLLM. This architecture bridges the performance gap caused by training FFNs with context-free token-wise embeddings.</p> + https://arxiv.org/abs/2602.00398 + Fri, 30 Jan 2026 23:25:20 +0000 - OVD: On-policy Verbal Distillation - https://arxiv.org/abs/2601.21968 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.21968.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Xiong, Hui Shen, Shansan Gong, Yuxin Cheng, Jianghan Shen, Chaofan Tao, Haochen Tan, Haoli Bai, Lifeng Shang, Ngai Wong</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the student and teacher models, which restricts the student model's exploration ability, prevent effective use of interactive environment feedback, and suffer from severe memory bottlenecks in reinforcement learning. We introduce On-policy Verbal Distillation (OVD), a memory-efficient framework that replaces token-level probability matching with trajectory matching using discrete verbal scores (0--9) from teacher models. OVD dramatically reduces memory consumption while enabling on-policy distillation from teacher models with verbal feedback, and avoids token-level alignment, allowing the student model to freely explore the output space. Extensive experiments on Web question answering and mathematical reasoning tasks show that OVD substantially outperforms existing methods, delivering up to +12.9% absolute improvement in average EM on Web Q&A tasks and a up to +25.7% gain on math benchmarks (when trained with only one random samples), while also exhibiting superior training efficiency. Our project page is available at https://OVD.github.io</p> - https://arxiv.org/abs/2601.21968 - Thu, 29 Jan 2026 16:48:14 +0000 + RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment + https://arxiv.org/abs/2602.00682 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00682.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuecheng Li, Hengwei Ju, Zeyu Song, Wei Yang, Chi Lu, Peng Jiang, Kun Gai</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Multimodal recommendation systems typically integrates user behavior with multimodal data from items, thereby capturing more accurate user preferences. Concurrently, with the rise of large models (LMs), multimodal recommendation is increasingly leveraging their strengths in semantic understanding and contextual reasoning. However, LM representations are inherently optimized for general semantic tasks, while recommendation models rely heavily on sparse user/item unique identity (ID) features. Existing works overlook the fundamental representational divergence between large models and recommendation systems, resulting in incompatible multimodal representations and suboptimal recommendation performance. To bridge this gap, we propose RecGOAT, a novel yet simple dual semantic alignment framework for LLM-enhanced multimodal recommendation, which offers theoretically guaranteed alignment capability. RecGOAT first employs graph attention networks to enrich collaborative semantics by modeling item-item, user-item, and user-user relationships, leveraging user/item LM representations and interaction history. Furthermore, we design a dual-granularity progressive multimodality-ID alignment framework, which achieves instance-level and distribution-level semantic alignment via cross-modal contrastive learning (CMCL) and optimal adaptive transport (OAT), respectively. Theoretically, we demonstrate that the unified representations derived from our alignment framework exhibit superior semantic consistency and comprehensiveness. Extensive experiments on three public benchmarks show that our RecGOAT achieves state-of-the-art performance, empirically validating our theoretical insights. Additionally, the deployment on a large-scale online advertising platform confirms the model's effectiveness and scalability in industrial recommendation scenarios. Code available at https://github.com/6lyc/RecGOAT-LLM4Rec.</p> + https://arxiv.org/abs/2602.00682 + Sat, 31 Jan 2026 11:58:38 +0000 - Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models - https://arxiv.org/abs/2601.22060 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.22060.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenxuan Huang, Yu Zeng, Qiuchen Wang, Zhen Fang, Shaosheng Cao, Zheng Chu, Qingyu Yin, Shuang Chen, Zhenfei Yin, Lin Chen, Zehui Chen, Yao Hu, Philip Torr, Feng Zhao, Wanli Ouyang</p><p><b>Upvotes:</b> 125</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by ``reasoning-then-tool-call'' for visual and textual search engines to obtain substantial gains on tasks requiring extensive factual information. However, these approaches typically define multimodal search in a naive setting, assuming that a single full-level or entity-level image query and few text query suffices to retrieve the key evidence needed to answer the question, which is unrealistic in real-world scenarios with substantial visual noise. Moreover, they are often limited in the reasoning depth and search breadth, making it difficult to solve complex questions that require aggregating evidence from diverse visual and textual sources. Building on this, we propose Vision-DeepResearch, which proposes one new multimodal deep-research paradigm, i.e., performs multi-turn, multi-entity and multi-scale visual and textual search to robustly hit real-world search engines under heavy noise. Our Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions, while internalizing deep-research capabilities into the MLLM via cold-start supervision and RL training, resulting in a strong end-to-end multimodal deep-research MLLM. It substantially outperforming existing multimodal deep-research MLLMs, and workflows built on strong closed-source foundation model such as GPT-5, Gemini-2.5-pro and Claude-4-Sonnet. The code will be released in https://github.com/Osilly/Vision-DeepResearch.</p> - https://arxiv.org/abs/2601.22060 - Thu, 29 Jan 2026 17:58:40 +0000 + Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training + https://arxiv.org/abs/2602.00747 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengrui Li, Fei Zhao, Kaiyan Zhao, Jieying Ye, Haifeng Liu, Fangcheng Shi, Zheyong Xie, Yao Hu, Shaosheng Cao</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Determining an effective data mixture is a key factor in Large Language Model (LLM) pre-training, where models must balance general competence with proficiency on hard tasks such as math and code. However, identifying an optimal mixture remains an open challenge, as existing approaches either rely on unreliable tiny-scale proxy experiments or require prohibitively expensive large-scale exploration. To address this, we propose Decouple Searching from Training Mix (DeMix), a novel framework that leverages model merging to predict optimal data ratios. Instead of training proxy models for every sampled mixture, DeMix trains component models on candidate datasets at scale and derives data mixture proxies via weighted model merging. This paradigm decouples search from training costs, enabling evaluation of unlimited sampled mixtures without extra training burden and thus facilitating better mixture discovery through more search trials. Extensive experiments demonstrate that DeMix breaks the trade-off between sufficiency, accuracy and efficiency, obtaining the optimal mixture with higher benchmark performance at lower search cost. Additionally, we release the DeMix Corpora, a comprehensive 22T-token dataset comprising high-quality pre-training data with validated mixtures to facilitate open research. Our code and DeMix Corpora is available at https://github.com/Lucius-lsr/DeMix.</p> + https://arxiv.org/abs/2602.00747 + Sat, 31 Jan 2026 14:27:46 +0000 - ParalESN: Enabling parallel information processing in Reservoir Computing - https://arxiv.org/abs/2601.22296 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.22296.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Matteo Pinna, Giacomo Lagomarsini, Andrea Ceni, Claudio Gallicchio</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reservoir Computing (RC) has established itself as an efficient paradigm for temporal processing. However, its scalability remains severely constrained by (i) the necessity of processing temporal data sequentially and (ii) the prohibitive memory footprint of high-dimensional reservoirs. In this work, we revisit RC through the lens of structured operators and state space modeling to address these limitations, introducing Parallel Echo State Network (ParalESN). ParalESN enables the construction of high-dimensional and efficient reservoirs based on diagonal linear recurrence in the complex space, enabling parallel processing of temporal data. We provide a theoretical analysis demonstrating that ParalESN preserves the Echo State Property and the universality guarantees of traditional Echo State Networks while admitting an equivalent representation of arbitrary linear reservoirs in the complex diagonal form. Empirically, ParalESN matches the predictive accuracy of traditional RC on time series benchmarks, while delivering substantial computational savings. On 1-D pixel-level classification tasks, ParalESN achieves competitive accuracy with fully trainable neural networks while reducing computational costs and energy consumption by orders of magnitude. Overall, ParalESN offers a promising, scalable, and principled pathway for integrating RC within the deep learning landscape.</p> - https://arxiv.org/abs/2601.22296 - Thu, 29 Jan 2026 20:18:27 +0000 + LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents + https://arxiv.org/abs/2602.01053 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01053.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyesung Jeon, Hyeongju Ha, Jae-Joon Kim</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Role specialization in multi-LLM agent systems is often realized via multi-LoRA, where agents share a pretrained backbone and differ only through lightweight adapters. Despite sharing base model weights, each agent independently builds and stores its own KV cache for the same long, tool-augmented trajectories, incurring substantial memory and compute overhead. Existing KV cache sharing methods largely overlook this multi-LoRA setting. We observe that, across agents, cache differences are dominated by adapter outputs, while activations from the shared pretrained backbone remain highly similar. Based on this observation, we propose LRAgent, a KV cache sharing framework for multi-LoRA agents that decomposes the cache into a shared base component from the pretrained weights and an adapter-dependent component from LoRA weights. LRAgent reduces memory overhead by sharing the base component and storing the adapter component in its inherent low-rank form, and further reduces compute overhead, enabled by shared-A multi-LoRA architectures, by also sharing the low-rank cache and avoiding redundant computations for contexts already processed by other agents. To efficiently reconstruct adapter contributions at runtime, we introduce Flash-LoRA-Attention, a kernel that reorders attention computation to avoid materializing the low-rank cache to full dimension. LRAgent achieves throughput and time-to-first-token latency close to fully shared caching, while preserving accuracy near the non-shared caching baseline across agentic question-answering benchmarks.</p> + https://arxiv.org/abs/2602.01053 + Sun, 01 Feb 2026 06:36:46 +0000 - YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation - https://arxiv.org/abs/2602.00168 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ranjan Sapkota, Manoj Karkee</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> This paper presents YOLOE-26, a unified framework that integrates the deployment-optimized YOLO26(or YOLOv26) architecture with the open-vocabulary learning paradigm of YOLOE for real-time open-vocabulary instance segmentation. Building on the NMS-free, end-to-end design of YOLOv26, the proposed approach preserves the hallmark efficiency and determinism of the YOLO family while extending its capabilities beyond closed-set recognition. YOLOE-26 employs a convolutional backbone with PAN/FPN-style multi-scale feature aggregation, followed by end-to-end regression and instance segmentation heads. A key architectural contribution is the replacement of fixed class logits with an object embedding head, which formulates classification as similarity matching against prompt embeddings derived from text descriptions, visual examples, or a built-in vocabulary. To enable efficient open-vocabulary reasoning, the framework incorporates Re-Parameterizable Region-Text Alignment (RepRTA) for zero-overhead text prompting, a Semantic-Activated Visual Prompt Encoder (SAVPE) for example-guided segmentation, and Lazy Region Prompt Contrast for prompt-free inference. All prompting modalities operate within a unified object embedding space, allowing seamless switching between text-prompted, visual-prompted, and fully autonomous segmentation. Extensive experiments demonstrate consistent scaling behavior and favorable accuracy-efficiency trade-offs across model sizes in both prompted and prompt-free settings. The training strategy leverages large-scale detection and grounding datasets with multi-task optimization and remains fully compatible with the Ultralytics ecosystem for training, validation, and deployment. Overall, YOLOE-26 provides a practical and scalable solution for real-time open-vocabulary instance segmentation in dynamic, real-world environments.</p> - https://arxiv.org/abs/2602.00168 - Thu, 29 Jan 2026 23:35:48 +0000 + SimpleGPT: Improving GPT via A Simple Normalization Strategy + https://arxiv.org/abs/2602.01212 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Marco Chen, Xianbiao Qi, Yelin He, Jiaquan Ye, Rong Xiao</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the Hessian matrix, and the maximum tolerable learning rate. We introduce a simple normalization strategy, termed SimpleNorm, which stabilizes intermediate activation scales by construction. Then, by analyzing the Hessian of the loss with respect to network activations, we theoretically show that SimpleNorm significantly reduces the spectral norm of the Hessian, thereby permitting larger stable learning rates. We validate our theoretical findings through extensive experiments on large GPT models at parameter scales 1B, 1.4B, 7B and 8B. Empirically, SimpleGPT, our SimpleNorm-based network, tolerates learning rates 3times-10times larger than standard convention, consistently demonstrates strong optimization stability, and achieves substantially better performance than well-established baselines. Specifically, when training 7B-scale models for 60K steps, SimpleGPT achieves a training loss that is 0.08 lower than that of LLaMA2 with QKNorm, reducing the loss from 2.290 to 2.208. Our source code will be released at https://github.com/Ocram7/SimpleGPT.</p> + https://arxiv.org/abs/2602.01212 + Sun, 01 Feb 2026 13:07:17 +0000 - Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry - https://arxiv.org/abs/2601.22588 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.22588.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuochun Li, Yong Zhang, Ming Li, Yuelyu Ji, Yiming Zeng, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao, Daqing He</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design. In this work, we investigate whether smaller models can serve as efficient evaluators by leveraging internal representations instead of surface generation. We uncover a consistent empirical pattern: small LMs, despite with weak generative ability, encode rich evaluative signals in their hidden states. This motivates us to propose the Semantic Capacity Asymmetry Hypothesis: evaluation requires significantly less semantic capacity than generation and can be grounded in intermediate representations, suggesting that evaluation does not necessarily need to rely on large-scale generative models but can instead leverage latent features from smaller ones. Our findings motivate a paradigm shift from LLM-as-a-Judge to Representation-as-a-Judge, a decoding-free evaluation strategy that probes internal model structure rather than relying on prompted output. We instantiate this paradigm through INSPECTOR, a probing-based framework that predicts aspect-level evaluation scores from small model representations. Experiments on reasoning benchmarks (GSM8K, MATH, GPQA) show that INSPECTOR substantially outperforms prompting-based small LMs and closely approximates full LLM judges, while offering a more efficient, reliable, and interpretable alternative for scalable evaluation.</p> - https://arxiv.org/abs/2601.22588 - Fri, 30 Jan 2026 05:34:24 +0000 + Balancing Understanding and Generation in Discrete Diffusion Models + https://arxiv.org/abs/2602.01362 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01362.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Liu, Yuzhong Zhao, Zheyong Xie, Qixiang Ye, Jianbin Jiao, Yao Hu, Shaosheng Cao, Yunfan Liu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> In discrete generative modeling, two dominant paradigms demonstrate divergent capabilities: Masked Diffusion Language Models (MDLM) excel at semantic understanding and zero-shot generalization, whereas Uniform-noise Diffusion Language Models (UDLM) achieve strong few-step generation quality, yet neither attains balanced performance across both dimensions. To address this, we propose XDLM, which bridges the two paradigms via a stationary noise kernel. XDLM offers two key contributions: (1) it provides a principled theoretical unification of MDLM and UDLM, recovering each paradigm as a special case; and (2) an alleviated memory bottleneck enabled by an algebraic simplification of the posterior probabilities. Experiments demonstrate that XDLM advances the Pareto frontier between understanding capability and generation quality. Quantitatively, XDLM surpasses UDLM by 5.4 points on zero-shot text benchmarks and outperforms MDLM in few-step image generation (FID 54.1 vs. 80.8). When scaled to tune an 8B-parameter large language model, XDLM achieves 15.0 MBPP in just 32 steps, effectively doubling the baseline performance. Finally, analysis of training dynamics reveals XDLM's superior potential for long-term scaling. Code is available at https://github.com/MzeroMiko/XDLM</p> + https://arxiv.org/abs/2602.01362 + Sun, 01 Feb 2026 18:00:35 +0000 - A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation - https://arxiv.org/abs/2601.22599 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.22599.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Li, Jintao Cheng, Chang Zeng, Zijun Yan, Helin Wang, Zixiong Su, Bo Zheng, Xiaolin Hu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Query-based universal sound separation is fundamental to intelligent auditory systems, aiming to isolate specific sources from mixtures. Despite recent advances, existing methods continue to suffer from residual interference in complex acoustic scenes. This performance limitation stems largely from a data bottleneck: in-the-wild datasets contain weak labels and severe co-occurrence of events. These flaws induce models to learn spurious correlations between background noise and target categories instead of robust acoustic features. To address this, we propose an automated pipeline that eliminates co-occurrence of events by mining high-purity single-event segments from in-the-wild datasets via a semantically consistent synthesis protocol. Utilizing this pipeline, we constructed Hive, a high-quality synthetic dataset comprising 2.4k hours of raw audio. Experimental results demonstrate that, compared with the state-of-the-art model SAM-Audio which was trained on a huge dataset sim500 times larger than Hive, certain open-source models trained on Hive achieve competitive separation accuracy and perceptual quality. Moreover, these models exhibited remarkable zero-shot generalization on out-of-distribution evaluation benchmarks. These findings highlight that prioritizing purity of supervised signals enables significant data efficiency, offering a new paradigm for training robust auditory foundation models with reduced computational costs. Code and dataset are available at https://shandaai.github.io/Hive.</p> - https://arxiv.org/abs/2601.22599 - Fri, 30 Jan 2026 05:43:57 +0000 + Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents + https://arxiv.org/abs/2602.01405 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikhil Sharma, Zheng Zhang, Daniel Lee, Namita Krishnan, Guang-Jie Ren, Ziang Xiao, Yunyao Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> High-quality feedback is essential for effective human-AI interaction. It bridges knowledge gaps, corrects digressions, and shapes system behavior; both during interaction and throughout model development. Yet despite its importance, human feedback to AI is often infrequent and low quality. This gap motivates a critical examination of human feedback during interactions with AIs. To understand and overcome the challenges preventing users from giving high-quality feedback, we conducted two studies examining feedback dynamics between humans and conversational agents (CAs). Our formative study, through the lens of Grice's maxims, identified four Feedback Barriers -- Common Ground, Verifiability, Communication, and Informativeness -- that prevent high-quality feedback by users. Building on these findings, we derive three design desiderata and show that systems incorporating scaffolds aligned with these desiderata enabled users to provide higher-quality feedback. Finally, we detail a call for action to the broader AI community for advances in Large Language Models capabilities to overcome Feedback Barriers.</p> + https://arxiv.org/abs/2602.01405 + Sun, 01 Feb 2026 19:16:23 +0000 - VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration - https://arxiv.org/abs/2601.22674 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.22674.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanxun Yu, Wentong Li, Xuan Qu, Song Wang, Junbo Chen, Jianke Zhu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline components and often neglect textual alignment, leading to performance degradation. In this paper, we propose VisionTrim, a unified framework for training-free MLLM acceleration, integrating two effective plug-and-play modules: 1) the Dominant Vision Token Selection (DVTS) module, which preserves essential visual tokens via a global-local view, and 2) the Text-Guided Vision Complement (TGVC) module, which facilitates context-aware token merging guided by textual cues. Extensive experiments across diverse image and video multimodal benchmarks demonstrate the performance superiority of our VisionTrim, advancing practical MLLM deployment in real-world applications. The code is available at: https://github.com/hanxunyu/VisionTrim.</p> - https://arxiv.org/abs/2601.22674 - Fri, 30 Jan 2026 07:45:48 +0000 + You Need an Encoder for Native Position-Independent Caching + https://arxiv.org/abs/2602.01519 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01519.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiju Zhao, Junhao Hu, Jiaqi Zheng, Guihai Chen</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The Key-Value (KV) cache of Large Language Models (LLMs) is prefix-based, making it highly inefficient for processing contexts retrieved in arbitrary order. Position-Independent Caching (PIC) has been proposed to enable KV reuse without positional constraints; however, existing approaches often incur substantial accuracy degradation, limiting their practical adoption. To address this issue, we propose native PIC by reintroducing the encoder to prevalent decoder-only LLMs and explicitly training it to support PIC. We further develop COMB, a PIC-aware caching system that integrates seamlessly with existing inference frameworks. Experimental results show that COMB reduces Time-to-First-Token (TTFT) by 51-94% and increases throughput by 3times with comparable accuracy. Furthermore, the quality improvement when using DeepSeek-V2-Lite-Chat demonstrates the applicability of COMB to other types of decoder-only LLMs. Our code is available at https://github.com/shijuzhao/Comb.</p> + https://arxiv.org/abs/2602.01519 + Mon, 02 Feb 2026 01:23:13 +0000 - AI-Generated Image Detectors Overrely on Global Artifacts: Evidence from Inpainting Exchange - https://arxiv.org/abs/2602.00192 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elif Nebioglu, Emirhan Bilgiç, Adrian Popescu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Modern deep learning-based inpainting enables realistic local image manipulation, raising critical challenges for reliable detection. However, we observe that current detectors primarily rely on global artifacts that appear as inpainting side effects, rather than on locally synthesized content. We show that this behavior occurs because VAE-based reconstruction induces a subtle but pervasive spectral shift across the entire image, including unedited regions. To isolate this effect, we introduce Inpainting Exchange (INP-X), an operation that restores original pixels outside the edited region while preserving all synthesized content. We create a 90K test dataset including real, inpainted, and exchanged images to evaluate this phenomenon. Under this intervention, pretrained state-of-the-art detectors, including commercial ones, exhibit a dramatic drop in accuracy (e.g., from 91\% to 55\%), frequently approaching chance level. We provide a theoretical analysis linking this behavior to high-frequency attenuation caused by VAE information bottlenecks. Our findings highlight the need for content-aware detection. Indeed, training on our dataset yields better generalization and localization than standard inpainting. Our dataset and code are publicly available at https://github.com/emirhanbilgic/INP-X.</p> - https://arxiv.org/abs/2602.00192 - Fri, 30 Jan 2026 09:14:10 +0000 + Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks + https://arxiv.org/abs/2602.01630 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bohan Zeng, Kaixin Zhu, Daili Hua, Bozhou Li, Chengzhuo Tong, Yuran Wang, Xinyi Huang, Yifan Dai, Zixiang Zhang, Yifan Yang, Zhou Liu, Hao Liang, Xiaochen Ma, Ruichuan An, Tianyi Bai, Hongcheng Gao, Junbo Niu, Yang Shi, Xinlong Chen, Yue Ding, Minglei Shi, Kai Zeng, Yiwen Tang, Yuanxing Zhang, Pengfei Wan, Xintao Wang, Wentao Zhang</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> World models have emerged as a critical frontier in AI research, aiming to enhance large models by infusing them with physical dynamics and world knowledge. The core objective is to enable agents to understand, predict, and interact with complex environments. However, current research landscape remains fragmented, with approaches predominantly focused on injecting world knowledge into isolated tasks, such as visual prediction, 3D estimation, or symbol grounding, rather than establishing a unified definition or framework. While these task-specific integrations yield performance gains, they often lack the systematic coherence required for holistic world understanding. In this paper, we analyze the limitations of such fragmented approaches and propose a unified design specification for world models. We suggest that a robust world model should not be a loose collection of capabilities but a normative framework that integrally incorporates interaction, perception, symbolic reasoning, and spatial representation. This work aims to provide a structured perspective to guide future research toward more general, robust, and principled models of the world.</p> + https://arxiv.org/abs/2602.01630 + Mon, 02 Feb 2026 04:42:44 +0000 - Clipping-Free Policy Optimization for Large Language Models - https://arxiv.org/abs/2601.22801 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.22801.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ömer Veysel Çağatan, Barış Akgün, Gözde Gül Şahin, Xuandong Zhao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reinforcement learning has become central to post-training large language models, yet dominant algorithms rely on clipping mechanisms that introduce optimization issues at scale, including zero-gradient regions, reward hacking, and training instability. We propose Clipping-Free Policy Optimization (CFPO), which replaces heuristic clipping with a convex quadratic penalty derived from Total Variation divergence constraints, yielding an everywhere-differentiable objective that enforces stable policy updates without hard boundaries. We evaluate CFPO across both reasoning and alignment settings. In reasoning, CFPO matches clipping-based methods on downstream benchmarks while extending the stable training regime. In alignment, CFPO mitigates verbosity exploitation and reduces capability degradation, while achieving competitive instruction-following performance. CFPO requires only a one-line code change and no additional hyperparameters. Our results suggest that CFPO is a promising drop-in alternative to clipping-based methods for LLM post-training.</p> - https://arxiv.org/abs/2601.22801 - Fri, 30 Jan 2026 10:32:37 +0000 + ObjEmbed: Towards Universal Multimodal Object Embeddings + https://arxiv.org/abs/2602.01753 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01753.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenghao Fu, Yukun Su, Fengyun Rao, Jing Lyu, Xiaohua Xie, Wei-Shi Zheng</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often struggle with fine-grained alignment between image regions and specific phrases. In this work, we present ObjEmbed, a novel MLLM embedding model that decomposes the input image into multiple regional embeddings, each corresponding to an individual object, along with global embeddings. It supports a wide range of visual understanding tasks like visual grounding, local image retrieval, and global image retrieval. ObjEmbed enjoys three key properties: (1) Object-Oriented Representation: It captures both semantic and spatial aspects of objects by generating two complementary embeddings for each region: an object embedding for semantic matching and an IoU embedding that predicts localization quality. The final object matching score combines semantic similarity with the predicted IoU, enabling more accurate retrieval. (2) Versatility: It seamlessly handles both region-level and image-level tasks. (3) Efficient Encoding: All objects in an image, along with the full image, are encoded in a single forward pass for high efficiency. Superior performance on 18 diverse benchmarks demonstrates its strong semantic discrimination.</p> + https://arxiv.org/abs/2602.01753 + Mon, 02 Feb 2026 07:38:45 +0000 - Mano: Restriking Manifold Optimization for LLM Training - https://arxiv.org/abs/2601.23000 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.23000.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufei Gu, Zeke Xie</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> While large language models (LLMs) have emerged as a significant advancement in artificial intelligence, the hardware and computational costs for training LLMs are also significantly burdensome. Among the state-of-the-art optimizers, AdamW relies on diagonal curvature estimates and ignores structural properties, while Muon applies global spectral normalization at the expense of losing curvature information. In this study, we restriked manifold optimization methods for training LLMs, which may address both optimizers' limitations, while conventional manifold optimization methods have been largely overlooked due to the poor performance in large-scale model optimization. By innovatively projecting the momentum onto the tangent space of model parameters and constraining it on a rotational Oblique manifold, we propose a novel, powerful, and efficient optimizer **Mano** that is the first to bridge the performance gap between manifold optimization and modern optimizers. Extensive experiments on the LLaMA and Qwen3 models demonstrate that Mano consistently and significantly outperforms AdamW and Muon even with less memory consumption and computational complexity, respectively, suggesting an expanded Pareto frontier in terms of space and time efficiency.</p> - https://arxiv.org/abs/2601.23000 - Fri, 30 Jan 2026 14:07:03 +0000 + CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding + https://arxiv.org/abs/2602.01785 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01785.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuling Shi, Chaoxiang Xie, Zhensu Sun, Yeheng Chen, Chenxu Zhang, Longfei Yun, Chengcheng Wan, Hongyu Zhang, David Lo, Xiaodong Gu</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely on a text-based paradigm that treats source code as a linear sequence of tokens, which leads to a linear increase in context length and associated computational costs. The rapid advancement of Multimodal LLMs (MLLMs) introduces an opportunity to optimize efficiency by representing source code as rendered images. Unlike text, which is difficult to compress without losing semantic meaning, the image modality is inherently suitable for compression. By adjusting resolution, images can be scaled to a fraction of their original token cost while remaining recognizable to vision-capable models. To explore the feasibility of this approach, we conduct the first systematic study on the effectiveness of MLLMs for code understanding. Our experiments reveal that: (1) MLLMs can effectively understand code with substantial token reduction, achieving up to 8x compression; (2) MLLMs can effectively leverage visual cues such as syntax highlighting, improving code completion performance under 4x compression; and (3) Code-understanding tasks like clone detection exhibit exceptional resilience to visual compression, with some compression ratios even slightly outperforming raw text inputs. Our findings highlight both the potential and current limitations of MLLMs in code understanding, which points out a shift toward image-modality code representation as a pathway to more efficient inference.</p> + https://arxiv.org/abs/2602.01785 + Mon, 02 Feb 2026 08:10:21 +0000 - VoxServe: Streaming-Centric Serving System for Speech Language Models - https://arxiv.org/abs/2602.00269 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00269.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keisuke Kamahori, Wei-Tzu Lee, Atindra Jha, Rohan Kadekodi, Stephanie Wang, Arvind Krishnamurthy, Baris Kasikci</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly and efficiently. We present VoxServe, a unified serving system for SpeechLMs that optimizes streaming performance. VoxServe introduces a model-execution abstraction that decouples model architecture from system-level optimizations, thereby enabling support for diverse SpeechLM architectures within a single framework. Building on this abstraction, VoxServe implements streaming-aware scheduling and an asynchronous inference pipeline to improve end-to-end efficiency. Evaluations across multiple modern SpeechLMs show that VoxServe achieves 10-20x higher throughput than existing implementations at comparable latency while maintaining high streaming viability. The code of VoxServe is available at https://github.com/vox-serve/vox-serve.</p> - https://arxiv.org/abs/2602.00269 - Fri, 30 Jan 2026 19:45:59 +0000 + daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently + https://arxiv.org/abs/2602.02619 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohan Jiang, Dayuan Fu, Junhao Shi, Ji Zeng, Weiye Si, Keyu Li, Xuefeng Li, Yang Xiao, Wenjie Li, Dequan Wang, Pengfei Liu</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> While Large Language Models (LLMs) excel at short-term tasks, scaling them to long-horizon agentic workflows remains challenging. The core bottleneck lies in the scarcity of training data that captures authentic long-dependency structures and cross-stage evolutionary dynamics--existing synthesis methods either confine to single-feature scenarios constrained by model distribution, or incur prohibitive human annotation costs, failing to provide scalable, high-quality supervision. We address this by reconceptualizing data synthesis through the lens of real-world software evolution. Our key insight: Pull Request (PR) sequences naturally embody the supervision signals for long-horizon learning. They decompose complex objectives into verifiable submission units, maintain functional coherence across iterations, and encode authentic refinement patterns through bug-fix histories. Building on this, we propose daVinci-Agency, which systematically mines structured supervision from chain-of-PRs through three interlocking mechanisms: (1) progressive task decomposition via continuous commits, (2) long-term consistency enforcement through unified functional objectives, and (3) verifiable refinement from authentic bug-fix trajectories. Unlike synthetic trajectories that treat each step independently, daVinci-Agency's PR-grounded structure inherently preserves the causal dependencies and iterative refinements essential for teaching persistent goal-directed behavior and enables natural alignment with project-level, full-cycle task modeling. The resulting trajectories are substantial--averaging 85k tokens and 116 tool calls--yet remarkably data-efficient: fine-tuning GLM-4.6 on 239 daVinci-Agency samples yields broad improvements across benchmarks, notably achieving a 47% relative gain on Toolathlon. Beyond benchmark performance, our analysis confirms...</p> + https://arxiv.org/abs/2602.02619 + Mon, 02 Feb 2026 13:23:39 +0000 - Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory - https://arxiv.org/abs/2602.00521 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junhyuk Choi, Sohhyung Park, Chanhee Cho, Hyeonchu Park, Bugeun Kim</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> While LLM-as-a-Judge is widely used in automated evaluation, existing validation practices primarily operate at the level of observed outputs, offering limited insight into whether LLM judges themselves function as stable and reliable measurement instruments. To address this limitation, we introduce a two-phase diagnostic framework for assessing reliability of LLM-as-a-Judge, grounded in Item Response Theory (IRT). The framework adopts Graded Response Model (GRM) of IRT and formalizes reliability along two complementary dimensions: (1) intrinsic consistency, defined as the stability of measurement behavior under prompt variations, and (2) human alignment, capturing correspondence with human quality assessments. We empirically examine diverse LLM judges with this framework, and show that leveraging IRT-GRM yields interpretable signals for diagnosing judgments systematically. These signals provide practical guidance for verifying reliablity of LLM-as-a-Judge and identifying potential causes of unreliability.</p> - https://arxiv.org/abs/2602.00521 - Sat, 31 Jan 2026 05:24:08 +0000 + No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs + https://arxiv.org/abs/2602.02103 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liyan Xu, Mo Yu, Fandong Meng, Jie Zhou</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs) is shown latent planning of subsequent reasoning prior to CoT emergence, thereby diminishing the significance of explicit CoT; whereas CoT remains critical for tasks requiring multi-step reasoning. To deepen the understanding between LLM's internal states and its verbalized reasoning trajectories, we investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains. Our empirical results indicate that LLMs exhibit a myopic horizon, primarily conducting incremental transitions without precise global planning. Leveraging this characteristic, we propose a hypothesis on enhancing uncertainty estimation of CoT, which we validate that a small subset of CoT positions can effectively represent the uncertainty of the entire path. We further underscore the significance of exploiting CoT dynamics, and demonstrate that automatic recognition of CoT bypass can be achieved without performance degradation. Our code, data and models are released at https://github.com/lxucs/tele-lens.</p> + https://arxiv.org/abs/2602.02103 + Mon, 02 Feb 2026 13:46:56 +0000 - Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning - https://arxiv.org/abs/2602.00759 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00759.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhipeng Chen, Xiaobo Qin, Wayne Xin Zhao, Youbin Wu, Ji-Rong Wen</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the reasoning ability of large language models (LLMs). However, due to the limited amount of information provided during the RLVR process, the model can only engage in largely blind exploration, which often results in failure on challenging problems. To provide additional information for the RLVR process without relying on a teacher model, we propose A^2D, an Adaptive Ability Decomposing method for enhancing the effectiveness of RLVR. Specifically, we first train a decomposer via RLVR without distillation, enabling it to decompose complex questions into a set of simpler sub-questions. Next, we use this decomposer to annotate sub-questions for each question in the training dataset, and then train the reasoner under RLVR with sub-question guidance. To better understand A^2D, we first compare its performance with competitive baselines, showing its effectiveness. Next, we observe that our method functions as a plug-and-play module that can be applied to different RLVR algorithms. Furthermore, we conduct an analysis of the decomposer, revealing how the RLVR process affects its performance and behavior, and which type of guidance is better suited for enhancing the reasoner's exploration and exploitation abilities.</p> - https://arxiv.org/abs/2602.00759 - Sat, 31 Jan 2026 14:48:23 +0000 + LangMap: A Hierarchical Benchmark for Open-Vocabulary Goal Navigation + https://arxiv.org/abs/2602.02220 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo Miao, Weijia Liu, Jun Luo, Lachlan Shinnick, Jian Liu, Thomas Hamilton-Smith, Yuhe Yang, Zijie Wu, Vanja Videnovic, Feras Dayoub, Anton van den Hengel</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The relationships between objects and language are fundamental to meaningful communication between humans and AI, and to practically useful embodied intelligence. We introduce HieraNav, a multi-granularity, open-vocabulary goal navigation task where agents interpret natural language instructions to reach targets at four semantic levels: scene, room, region, and instance. To this end, we present Language as a Map (LangMap), a large-scale benchmark built on real-world 3D indoor scans with comprehensive human-verified annotations and tasks spanning these levels. LangMap provides region labels, discriminative region descriptions, discriminative instance descriptions covering 414 object categories, and over 18K navigation tasks. Each target features both concise and detailed descriptions, enabling evaluation across different instruction styles. LangMap achieves superior annotation quality, outperforming GOAT-Bench by 23.8% in discriminative accuracy using four times fewer words. Comprehensive evaluations of zero-shot and supervised models on LangMap reveal that richer context and memory improve success, while long-tailed, small, context-dependent, and distant goals, as well as multi-goal completion, remain challenging. HieraNav and LangMap establish a rigorous testbed for advancing language-driven embodied navigation. Project: https://bo-miao.github.io/LangMap</p> + https://arxiv.org/abs/2602.02220 + Mon, 02 Feb 2026 15:26:19 +0000 - Green-VLA: Staged Vision-Language-Action Model for Generalist Robots - https://arxiv.org/abs/2602.00919 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00919.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> I. Apanasevich, M. Artemyev, R. Babakyan, P. Fedotova, D. Grankin, E. Kupryashin, A. Misailidi, D. Nerus, A. Nutalapati, G. Sidorov, I. Efremov, M. Gerasyov, D. Pikurov, Y. Senchenko, S. Davidenko, D. Kulikov, M. Sultankin, K. Askarbek, O. Shamanin, D. Statovoy, E. Zalyaev, I. Zorin, A. Letkin, E. Rusakov, A. Silchenko, V. Vorobyov, S. Sobolnikov, A. Postnikov</p><p><b>Upvotes:</b> 172</p><p><b>Summary:</b> We introduce Green-VLA, a staged Vision-Language-Action (VLA) framework for real-world deployment on the Green humanoid robot while maintaining generalization across diverse embodiments. Green-VLA follows a five stage curriculum: (L0) foundational VLMs, (L1) multimodal grounding, (R0) multi-embodiment pretraining, (R1) embodiment-specific adaptation, and (R2) reinforcement-learning (RL) policy alignment. We couple a scalable data-processing pipeline (3,000 hours of demonstrations) with temporal alignment and quality filtering, and use a unified, embodiment-aware action interface enabling a single policy to control humanoids, mobile manipulators, and fixed-base arms. At inference, the VLA controller is enhanced with episode-progress prediction, out-of-distribution detection, and joint-prediction-based guidance to improve safety and precise target selection. Experiments on Simpler BRIDGE WidowX and CALVIN ABC-D, as well as real-robot evaluations, show strong generalization and performance gains from RL alignment in success rate, robustness, and long-horizon efficiency.</p> - https://arxiv.org/abs/2602.00919 - Sat, 31 Jan 2026 22:13:23 +0000 + Unified Personalized Reward Model for Vision Generation + https://arxiv.org/abs/2602.02380 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02380.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibin Wang, Yuhang Zang, Feng Han, Jiazi Bu, Yujie Zhou, Cheng Jin, Jiaqi Wang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and subsequently optimize visual generation models via reinforcement learning. However, current RMs suffer from inherent limitations: they often follow a one-size-fits-all paradigm that assumes a monolithic preference distribution or relies on fixed evaluation rubrics. As a result, they are insensitive to content-specific visual cues, leading to systematic misalignment with subjective and context-dependent human preferences. To this end, inspired by human assessment, we propose UnifiedReward-Flex, a unified personalized reward model for vision generation that couples reward modeling with flexible and context-adaptive reasoning. Specifically, given a prompt and the generated visual content, it first interprets the semantic intent and grounds on visual evidence, then dynamically constructs a hierarchical assessment by instantiating fine-grained criteria under both predefined and self-generated high-level dimensions. Our training pipeline follows a two-stage process: (1) we first distill structured, high-quality reasoning traces from advanced closed-source VLMs to bootstrap SFT, equipping the model with flexible and context-adaptive reasoning behaviors; (2) we then perform direct preference optimization (DPO) on carefully curated preference pairs to further strengthen reasoning fidelity and discriminative alignment. To validate the effectiveness, we integrate UnifiedReward-Flex into the GRPO framework for image and video synthesis, and extensive results demonstrate its superiority.</p> + https://arxiv.org/abs/2602.02380 + Mon, 02 Feb 2026 17:44:21 +0000 - Sparse Reward Subsystem in Large Language Models - https://arxiv.org/abs/2602.00986 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.00986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guowei Xu, Mert Yuksekgonul, James Zou</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> In this paper, we identify a sparse reward subsystem within the hidden states of Large Language Models (LLMs), drawing an analogy to the biological reward subsystem in the human brain. We demonstrate that this subsystem contains value neurons that represent the model's internal expectation of state value, and through intervention experiments, we establish the importance of these neurons for reasoning. Our experiments reveal that these value neurons are robust across diverse datasets, model scales, and architectures; furthermore, they exhibit significant transferability across different datasets and models fine-tuned from the same base model. By examining cases where value predictions and actual rewards diverge, we identify dopamine neurons within the reward subsystem which encode reward prediction errors (RPE). These neurons exhibit high activation when the reward is higher than expected and low activation when the reward is lower than expected.</p> - https://arxiv.org/abs/2602.00986 - Sun, 01 Feb 2026 02:55:31 +0000 + Didactic to Constructive: Turning Expert Solutions into Learnable Reasoning + https://arxiv.org/abs/2602.02405 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ethan Mendes, Jungsoo Park, Alan Ritter</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However, many difficult problems remain intractable for even current frontier models, preventing the extraction of valid training signals. A promising alternative is to leverage high-quality expert human solutions, yet naive imitation of this data fails because it is fundamentally out of distribution: expert solutions are typically didactic, containing implicit reasoning gaps intended for human readers rather than computational models. Furthermore, high-quality expert solutions are expensive, necessitating generalizable sample-efficient training methods. We propose Distribution Aligned Imitation Learning (DAIL), a two-step method that bridges the distributional gap by first transforming expert solutions into detailed, in-distribution reasoning traces and then applying a contrastive objective to focus learning on expert insights and methodologies. We find that DAIL can leverage fewer than 1000 high-quality expert solutions to achieve 10-25% pass@k gains on Qwen2.5-Instruct and Qwen3 models, improve reasoning efficiency by 2x to 4x, and enable out-of-domain generalization.</p> + https://arxiv.org/abs/2602.02405 + Mon, 02 Feb 2026 18:03:43 +0000 - Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning - https://arxiv.org/abs/2602.01058 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01058.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dylan Zhang, Yufeng Xu, Haojin Wang, Qingzhi Chen, Hao Peng</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Post-training of reasoning LLMs is a holistic process that typically consists of an offline SFT stage followed by an online reinforcement learning (RL) stage. However, SFT is often optimized in isolation to maximize SFT performance alone. We show that, after identical RL training, models initialized from stronger SFT checkpoints can significantly underperform those initialized from weaker ones. We attribute this to a mismatch typical in current SFT-RL pipelines: the distribution that generates the offline SFT data can differ substantially from the policy optimized during online RL, which learns from its own rollouts. We propose PEAR (Policy Evaluation-inspired Algorithm for Offline Learning Loss Re-weighting), an SFT-stage method that corrects this mismatch and better prepares the model for RL. PEAR uses importance sampling to reweight the SFT loss, with three variants operating at the token, block, and sequence levels. It can be used to augment standard SFT objectives and incurs little additional training overhead once probabilities for the offline data are collected. We conduct controlled experiments on verifiable reasoning games and mathematical reasoning tasks on Qwen 2.5 and 3 and DeepSeek-distilled models. PEAR consistently improves post-RL performance over canonical SFT, with pass at 8 gains up to a 14.6 percent on AIME2025. Our results suggest that PEAR is an effective step toward more holistic LLM post-training by designing and evaluating SFT with downstream RL in mind rather than in isolation.</p> - https://arxiv.org/abs/2602.01058 - Sun, 01 Feb 2026 06:53:45 +0000 + SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration + https://arxiv.org/abs/2602.02419 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingni Wang, Yue Fan, Xin Eric Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Graphical User Interface (GUI) grounding aims to translate natural language instructions into executable screen coordinates, enabling automated GUI interaction. Nevertheless, incorrect grounding can result in costly, hard-to-reverse actions (e.g., erroneous payment approvals), raising concerns about model reliability. In this paper, we introduce SafeGround, an uncertainty-aware framework for GUI grounding models that enables risk-aware predictions through calibrations before testing. SafeGround leverages a distribution-aware uncertainty quantification method to capture the spatial dispersion of stochastic samples from outputs of any given model. Then, through the calibration process, SafeGround derives a test-time decision threshold with statistically guaranteed false discovery rate (FDR) control. We apply SafeGround on multiple GUI grounding models for the challenging ScreenSpot-Pro benchmark. Experimental results show that our uncertainty measure consistently outperforms existing baselines in distinguishing correct from incorrect predictions, while the calibrated threshold reliably enables rigorous risk control and potentials of substantial system-level accuracy improvements. Across multiple GUI grounding models, SafeGround improves system-level accuracy by up to 5.38% percentage points over Gemini-only inference.</p> + https://arxiv.org/abs/2602.02419 + Mon, 02 Feb 2026 18:22:45 +0000 - PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers - https://arxiv.org/abs/2602.01077 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01077.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haopeng Li, Shitong Shao, Wenliang Zhong, Zikai Zhou, Lichen Bai, Hui Xiong, Zeke Xie</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value blocks, it suffers from degradation at high sparsity by discarding context. In this work, we discover that attention scores of non-critical blocks exhibit distributional stability, allowing them to be approximated accurately and efficiently rather than discarded, which is essentially important for sparse attention design. Motivated by this key insight, we propose PISA, a training-free Piecewise Sparse Attention that covers the full attention span with sub-quadratic complexity. Unlike the conventional keep-or-drop paradigm that directly drop the non-critical block information, PISA introduces a novel exact-or-approximate strategy: it maintains exact computation for critical blocks while efficiently approximating the remainder through block-wise Taylor expansion. This design allows PISA to serve as a faithful proxy to full attention, effectively bridging the gap between speed and quality. Experimental results demonstrate that PISA achieves 1.91 times and 2.57 times speedups on Wan2.1-14B and Hunyuan-Video, respectively, while consistently maintaining the highest quality among sparse attention methods. Notably, even for image generation on FLUX, PISA achieves a 1.2 times acceleration without compromising visual quality. Code is available at: https://github.com/xie-lab-ml/piecewise-sparse-attention.</p> - https://arxiv.org/abs/2602.01077 - Sun, 01 Feb 2026 07:47:06 +0000 + WideSeek: Advancing Wide Research via Multi-Agent Scaling + https://arxiv.org/abs/2602.02636 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02636.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyang Huang, Haolin Ren, Xiaowei Yuan, Jiawei Wang, Zhongtao Jiang, Kun Xu, Shizhu He, Jun Zhao, Kang Liu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the lack of dedicated benchmarks and optimization methodologies for search breadth. To address these challenges, we take a deep dive into Wide Research from two perspectives: Data Pipeline and Agent Optimization. First, we produce WideSeekBench, a General Broad Information Seeking (GBIS) benchmark constructed via a rigorous multi-phase data pipeline to ensure diversity across the target information volume, logical constraints, and domains. Second, we introduce WideSeek, a dynamic hierarchical multi-agent architecture that can autonomously fork parallel sub-agents based on task requirements. Furthermore, we design a unified training framework that linearizes multi-agent trajectories and optimizes the system using end-to-end RL. Experimental results demonstrate the effectiveness of WideSeek and multi-agent RL, highlighting that scaling the number of agents is a promising direction for advancing the Wide Research paradigm.</p> + https://arxiv.org/abs/2602.02636 + Mon, 02 Feb 2026 18:32:48 +0000 - Interacted Planes Reveal 3D Line Mapping - https://arxiv.org/abs/2602.01296 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01296.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeran Ke, Bin Tan, Gui-Song Xia, Yujun Shen, Nan Xue</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> 3D line mapping from multi-view RGB images provides a compact and structured visual representation of scenes. We study the problem from a physical and topological perspective: a 3D line most naturally emerges as the edge of a finite 3D planar patch. We present LiP-Map, a line-plane joint optimization framework that explicitly models learnable line and planar primitives. This coupling enables accurate and detailed 3D line mapping while maintaining strong efficiency (typically completing a reconstruction in 3 to 5 minutes per scene). LiP-Map pioneers the integration of planar topology into 3D line mapping, not by imposing pairwise coplanarity constraints but by explicitly constructing interactions between plane and line primitives, thus offering a principled route toward structured reconstruction in man-made environments. On more than 100 scenes from ScanNetV2, ScanNet++, Hypersim, 7Scenes, and Tanks\&Temple, LiP-Map improves both accuracy and completeness over state-of-the-art methods. Beyond line mapping quality, LiP-Map significantly advances line-assisted visual localization, establishing strong performance on 7Scenes. Our code is released at https://github.com/calmke/LiPMAP for reproducible research.</p> - https://arxiv.org/abs/2602.01296 - Sun, 01 Feb 2026 15:52:55 +0000 + RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval + https://arxiv.org/abs/2602.02444 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tyler Skow, Alexander Martin, Benjamin Van Durme, Rama Chellappa, Reno Kriz</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Reranking is a critical component of modern retrieval systems, which typically pair an efficient first-stage retriever with a more expressive model to refine results. While large reasoning models have driven rapid progress in text-centric reranking, reasoning-based reranking for video retrieval remains underexplored. To address this gap, we introduce RANKVIDEO, a reasoning-based reranker for video retrieval that explicitly reasons over query-video pairs using video content to assess relevance. RANKVIDEO is trained using a two-stage curriculum consisting of perception-grounded supervised fine-tuning followed by reranking training that combines pointwise, pairwise, and teacher confidence distillation objectives, and is supported by a data synthesis pipeline for constructing reasoning-intensive query-video pairs. Experiments on the large-scale MultiVENT 2.0 benchmark demonstrate that RANKVIDEO consistently improves retrieval performance within a two-stage framework, yielding an average improvement of 31% on nDCG@10 and outperforming text-only and vision-language reranking alternatives, while more efficient.</p> + https://arxiv.org/abs/2602.02444 + Mon, 02 Feb 2026 18:40:37 +0000 - PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding - https://arxiv.org/abs/2602.01322 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01322.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Panagiotis Koromilas, Andreas D. Demou, James Oldfield, Yannis Panagakis, Mihalis Nicolaou</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Sparse autoencoders (SAEs) have emerged as a promising method for interpreting neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume that features combine additively through linear reconstruction, an assumption that cannot capture compositional structure: linear models cannot distinguish whether "Starbucks" arises from the composition of "star" and "coffee" features or merely their co-occurrence. This forces SAEs to allocate monolithic features for compound concepts rather than decomposing them into interpretable constituents. We introduce PolySAE, which extends the SAE decoder with higher-order terms to model feature interactions while preserving the linear encoder essential for interpretability. Through low-rank tensor factorization on a shared projection subspace, PolySAE captures pairwise and triple feature interactions with small parameter overhead (3% on GPT2). Across four language models and three SAE variants, PolySAE achieves an average improvement of approximately 8% in probing F1 while maintaining comparable reconstruction error, and produces 2-10times larger Wasserstein distances between class-conditional feature distributions. Critically, learned interaction weights exhibit negligible correlation with co-occurrence frequency (r = 0.06 vs. r = 0.82 for SAE feature covariance), suggesting that polynomial terms capture compositional structure, such as morphological binding and phrasal composition, largely independent of surface statistics.</p> - https://arxiv.org/abs/2602.01322 - Sun, 01 Feb 2026 16:34:45 +0000 + MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training + https://arxiv.org/abs/2602.02494 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02494.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dulhan Jayalath, Oiwi Parker Jones</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Clinical brain-to-text interfaces are designed for paralysed patients who cannot provide extensive training recordings. Pre-training improves data-efficient generalisation by learning statistical priors across subjects, but these priors critically depend on context. While natural speech might unfold gradually over minutes, most methods pre-train with only a few seconds of context. Thus, we propose MEG-XL, a model pre-trained with 2.5 minutes of MEG context per sample, 5-300x longer than prior work, and equivalent to 191k tokens, capturing extended neural context. Fine-tuning on the task of word decoding from brain data, MEG-XL matches supervised performance with a fraction of the data (e.g. 1hr vs 50hrs) and outperforms brain foundation models. We find that models pre-trained with longer contexts learn representations that transfer better to word decoding. Our results indicate that long-context pre-training helps exploit extended neural context that other methods unnecessarily discard. Code, model weights, and instructions are available at https://github.com/neural-processing-lab/MEG-XL .</p> + https://arxiv.org/abs/2602.02494 + Mon, 02 Feb 2026 18:59:50 +0000 - Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning - https://arxiv.org/abs/2602.01335 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01335.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Xu, Yuxin Zhang, Juan Cao, Lin Gao, Chunyu Wang, Oliver Deussen, Tong-Yee Lee, Fan Tang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models remain largely confined to pixel-level instruction alignment and surface-level appearance preservation, failing to capture the underlying abstract logic necessary for genuine metaphorical generation. To bridge this gap, we introduce the task of Visual Metaphor Transfer (VMT), which challenges models to autonomously decouple the "creative essence" from a reference image and re-materialize that abstract logic onto a user-specified target subject. We propose a cognitive-inspired, multi-agent framework that operationalizes Conceptual Blending Theory (CBT) through a novel Schema Grammar ("G"). This structured representation decouples relational invariants from specific visual entities, providing a rigorous foundation for cross-domain logic re-instantiation. Our pipeline executes VMT through a collaborative system of specialized agents: a perception agent that distills the reference into a schema, a transfer agent that maintains generic space invariance to discover apt carriers, a generation agent for high-fidelity synthesis and a hierarchical diagnostic agent that mimics a professional critic, performing closed-loop backtracking to identify and rectify errors across abstract logic, component selection, and prompt encoding. Extensive experiments and human evaluations demonstrate that our method significantly outperforms SOTA baselines in metaphor consistency, analogy appropriateness, and visual creativity, paving the way for automated high-impact creative applications in advertising and media. Source code will be made publicly available.</p> - https://arxiv.org/abs/2602.01335 - Sun, 01 Feb 2026 17:01:36 +0000 + MARS: Modular Agent with Reflective Search for Automated AI Research + https://arxiv.org/abs/2602.02660 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam, Rui Meng, Tomas Pfister, Jinsung Yoon</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Automating AI research differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution. Current LLM-based agents struggle here, often generating monolithic scripts that ignore execution costs and causal factors. We introduce MARS (Modular Agent with Reflective Search), a framework optimized for autonomous AI research. MARS relies on three pillars: (1) Budget-Aware Planning via cost-constrained Monte Carlo Tree Search (MCTS) to explicitly balance performance with execution expense; (2) Modular Construction, employing a "Design-Decompose-Implement" pipeline to manage complex research repositories; and (3) Comparative Reflective Memory, which addresses credit assignment by analyzing solution differences to distill high-signal insights. MARS achieves state-of-the-art performance among open-source frameworks on MLE-Bench under comparable settings, maintaining competitiveness with the global leaderboard's top methods. Furthermore, the system exhibits qualitative "Aha!" moments, where 63% of all utilized lessons originate from cross-branch transfer, demonstrating that the agent effectively generalizes insights across search paths.</p> + https://arxiv.org/abs/2602.02660 + Mon, 02 Feb 2026 19:00:03 +0000 - PromptRL: Prompt Matters in RL for Flow-Based Image Generation - https://arxiv.org/abs/2602.01382 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01382.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fu-Yun Wang, Han Zhang, Michael Gharbi, Hongsheng Li, Taesung Park</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Flow matching models (FMs) have revolutionized text-to-image (T2I) generation, with reinforcement learning (RL) serving as a critical post-training strategy for alignment with reward objectives. In this research, we show that current RL pipelines for FMs suffer from two underappreciated yet important limitations: sample inefficiency due to insufficient generation diversity, and pronounced prompt overfitting, where models memorize specific training formulations and exhibit dramatic performance collapse when evaluated on semantically equivalent but stylistically varied prompts. We present PromptRL (Prompt Matters in RL for Flow-Based Image Generation), a framework that incorporates language models (LMs) as trainable prompt refinement agents directly within the flow-based RL optimization loop. This design yields two complementary benefits: rapid development of sophisticated prompt rewriting capabilities and, critically, a synergistic training regime that reshapes the optimization dynamics. PromptRL achieves state-of-the-art performance across multiple benchmarks, obtaining scores of 0.97 on GenEval, 0.98 on OCR accuracy, and 24.05 on PickScore. Furthermore, we validate the effectiveness of our RL approach on large-scale image editing models, improving the EditReward of FLUX.1-Kontext from 1.19 to 1.43 with only 0.06 million rollouts, surpassing Gemini 2.5 Flash Image (also known as Nano Banana), which scores 1.37, and achieving comparable performance with ReasonNet (1.44), which relied on fine-grained data annotations along with a complex multi-stage training. Our extensive experiments empirically demonstrate that PromptRL consistently achieves higher performance ceilings while requiring over 2times fewer rollouts compared to naive flow-only RL. Our code is available at https://github.com/G-U-N/UniRL.</p> - https://arxiv.org/abs/2602.01382 - Sun, 01 Feb 2026 18:31:06 +0000 + AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process + https://arxiv.org/abs/2602.02676 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xintong Zhang, Xiaowen Zhang, Jongrong Wu, Zhi Gao, Shilin Yan, Zhenxin Diao, Kunpeng Gao, Xuanyan Chen, Yuwei Wu, Yunde Jia, Qing Li</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text reasoning to enhance both effectiveness and efficiency. However, existing evaluations rely on static difficulty labels and simplistic metrics, which fail to capture the dynamic nature of difficulty relative to varying model capacities. Consequently, they obscure the distinction between adaptive mode selection and general performance while neglecting fine-grained process analyses. In this paper, we propose AdaptMMBench, a comprehensive benchmark for adaptive multimodal reasoning across five domains: real-world, OCR, GUI, knowledge, and math, encompassing both direct perception and complex reasoning tasks. AdaptMMBench utilizes a Matthews Correlation Coefficient (MCC) metric to evaluate the selection rationality of different reasoning modes, isolating this meta-cognition ability by dynamically identifying task difficulties based on models' capability boundaries. Moreover, AdaptMMBench facilitates multi-dimensional process evaluation across key step coverage, tool effectiveness, and computational efficiency. Our evaluation reveals that while adaptive mode selection scales with model capacity, it notably decouples from final accuracy. Conversely, key step coverage aligns with performance, though tool effectiveness remains highly inconsistent across model architectures.</p> + https://arxiv.org/abs/2602.02676 + Mon, 02 Feb 2026 19:00:27 +0000 - Rethinking Selective Knowledge Distillation - https://arxiv.org/abs/2602.01395 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01395.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Almog Tavor, Itay Ebenspanger, Neil Cnaan, Mor Geva</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Growing efforts to improve knowledge distillation (KD) in large language models (LLMs) replace dense teacher supervision with selective distillation, which uses a subset of token positions, vocabulary classes, or training samples for supervision. However, it remains unclear which importance signals, selection policies, and their interplay are most effective. In this work, we revisit where and how to distill in autoregressive LLMs. We disentangle selective KD along the position, class, and sample axes and systematically compare importance signals and selection policies. Then, guided by this analysis, we identify underexplored opportunities and introduce student-entropy-guided position selection (SE-KD). Across a suite of benchmarks, SE-KD often improves accuracy, downstream task adherence, and memory efficiency over dense distillation. Extending this approach across the class and sample axes (SE-KD 3X) yields complementary efficiency gains that make offline teacher caching feasible. In practice, this reduces wall time by 70% and peak memory by 18%, while cutting storage usage by 80% over prior methods without sacrificing performance.</p> - https://arxiv.org/abs/2602.01395 - Sun, 01 Feb 2026 18:58:27 +0000 + Scaling Small Agents Through Strategy Auctions + https://arxiv.org/abs/2602.02751 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02751.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lisa Alazraki, William F. Shen, Yoram Bachrach, Akhil Mathur</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Small language models are increasingly viewed as a promising, cost-effective approach to agentic AI, with proponents claiming they are sufficiently capable for agentic workflows. However, while smaller agents can closely match larger ones on simple tasks, it remains unclear how their performance scales with task complexity, when large models become necessary, and how to better leverage small agents for long-horizon workloads. In this work, we empirically show that small agents' performance fails to scale with task complexity on deep search and coding tasks, and we introduce Strategy Auctions for Workload Efficiency (SALE), an agent framework inspired by freelancer marketplaces. In SALE, agents bid with short strategic plans, which are scored by a systematic cost-value mechanism and refined via a shared auction memory, enabling per-task routing and continual self-improvement without training a separate router or running all models to completion. Across deep search and coding tasks of varying complexity, SALE reduces reliance on the largest agent by 53%, lowers overall cost by 35%, and consistently improves upon the largest agent's pass@1 with only a negligible overhead beyond executing the final trace. In contrast, established routers that rely on task descriptions either underperform the largest agent or fail to reduce cost -- often both -- underscoring their poor fit for agentic workflows. These results suggest that while small agents may be insufficient for complex workloads, they can be effectively "scaled up" through coordinated task allocation and test-time self-improvement. More broadly, they motivate a systems-level view of agentic AI in which performance gains come less from ever-larger individual models and more from market-inspired coordination mechanisms that organize heterogeneous agents into efficient, adaptive ecosystems.</p> + https://arxiv.org/abs/2602.02751 + Mon, 02 Feb 2026 20:05:51 +0000 - Where to Attend: A Principled Vision-Centric Position Encoding with Parabolas - https://arxiv.org/abs/2602.01418 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01418.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Christoffer Koo Øhrstrøm, Rafael I. Cabral Muchacho, Yifei Dong, Filippos Moumtzidellis, Ronja Güldenring, Florian T. Pokorny, Lazaros Nalpantidis</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We propose Parabolic Position Encoding (PaPE), a parabola-based position encoding for vision modalities in attention-based architectures. Given a set of vision tokens-such as images, point clouds, videos, or event camera streams-our objective is to encode their positions while accounting for the characteristics of vision modalities. Prior works have largely extended position encodings from 1D-sequences in language to nD-structures in vision, but only with partial account of vision characteristics. We address this gap by designing PaPE from principles distilled from prior work: translation invariance, rotation invariance (PaPE-RI), distance decay, directionality, and context awareness. We evaluate PaPE on 8 datasets that span 4 modalities. We find that either PaPE or PaPE-RI achieves the top performance on 7 out of 8 datasets. Extrapolation experiments on ImageNet-1K show that PaPE extrapolates remarkably well, improving in absolute terms by up to 10.5% over the next-best position encoding. Code is available at https://github.com/DTU-PAS/parabolic-position-encoding.</p> - https://arxiv.org/abs/2602.01418 - Sun, 01 Feb 2026 19:51:27 +0000 + FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights + https://arxiv.org/abs/2602.02905 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02905.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Wang, Fan Bai, Zhongyan Luo, Jinyan Su, Kaiser Sun, Xinle Yu, Jieyuan Liu, Kun Zhou, Claire Cardie, Mark Dredze, Eric P. Xing, Zhiting Hu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a trade-off: they either heavily rely on LLM-as-judge evaluations of automatically generated research outputs or optimize convenient yet isolated performance metrics that provide coarse proxies for scientific insight. To address this gap, we introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery of established findings from recent, high-impact machine learning research. Agents are given only a high-level research question extracted from a published, verified study and must autonomously explore ideas, design experiments, implement code, execute their plans, and derive conclusions supported by empirical evidence. We evaluate a range of state-of-the-art agents with frontier LLMs backbones like gpt-5 on FIRE-Bench. Our results show that full-cycle scientific research remains challenging for current agent systems: even the strongest agents achieve limited rediscovery success (<50 F1), exhibit high variance across runs, and display recurring failure modes in experimental design, execution, and evidence-based reasoning. FIRE-Bench provides a rigorous and diagnostic framework for measuring progress toward reliable agent-driven scientific discovery.</p> + https://arxiv.org/abs/2602.02905 + Mon, 02 Feb 2026 23:21:13 +0000 - Ebisu: Benchmarking Large Language Models in Japanese Finance - https://arxiv.org/abs/2602.01479 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xueqing Peng, Ruoyu Xiang, Fan Zhang, Mingzi Song, Mingyang Jiang, Yan Wang, Lingfei Qian, Taiki Hara, Yuqing Guo, Jimin Huang, Junichi Tsujii, Sophia Ananiadou</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Japanese finance combines agglutinative, head-final linguistic structure, mixed writing systems, and high-context communication norms that rely on indirect expression and implicit commitment, posing a substantial challenge for LLMs. We introduce Ebisu, a benchmark for native Japanese financial language understanding, comprising two linguistically and culturally grounded, expert-annotated tasks: JF-ICR, which evaluates implicit commitment and refusal recognition in investor-facing Q&A, and JF-TE, which assesses hierarchical extraction and ranking of nested financial terminology from professional disclosures. We evaluate a diverse set of open-source and proprietary LLMs spanning general-purpose, Japanese-adapted, and financial models. Results show that even state-of-the-art systems struggle on both tasks. While increased model scale yields limited improvements, language- and domain-specific adaptation does not reliably improve performance, leaving substantial gaps unresolved. Ebisu provides a focused benchmark for advancing linguistically and culturally grounded financial NLP. All datasets and evaluation scripts are publicly released.</p> - https://arxiv.org/abs/2602.01479 - Sun, 01 Feb 2026 23:02:21 +0000 + FaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction + https://arxiv.org/abs/2602.02914 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02914.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqi Guo, Shan Du</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Transformation-based privacy-preserving face recognition (PPFR) aims to verify identities while hiding facial data from attackers and malicious service providers. Existing evaluations mostly treat privacy as resistance to pixel-level reconstruction, measured by PSNR and SSIM. We show that this reconstruction-centric view fails. We present FaceLinkGen, an identity extraction attack that performs linkage/matching and face regeneration directly from protected templates without recovering original pixels. On three recent PPFR systems, FaceLinkGen reaches over 98.5\% matching accuracy and above 96\% regeneration success, and still exceeds 92\% matching and 94\% regeneration in a near zero knowledge setting. These results expose a structural gap between pixel distortion metrics, which are widely used in PPFR evaluation, and real privacy. We show that visual obfuscation leaves identity information broadly exposed to both external intruders and untrusted service providers.</p> + https://arxiv.org/abs/2602.02914 + Mon, 02 Feb 2026 23:41:14 +0000 - Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training - https://arxiv.org/abs/2602.01511 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01511.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ran Xu, Tianci Liu, Zihan Dong, Tony You, Ilgee Hong, Carl Yang, Linjun Zhang, Tao Zhao, Haoyu Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-ended instruction following. To address this limitation, we propose Rubric-ARM, a framework that jointly optimizes a rubric generator and a judge using reinforcement learning from preference feedback. Unlike existing methods that rely on static rubrics or disjoint training pipelines, our approach treats rubric generation as a latent action learned to maximize judgment accuracy. We introduce an alternating optimization strategy to mitigate the non-stationarity of simultaneous updates, providing theoretical analysis that demonstrates how this schedule reduces gradient variance during training. Extensive experiments show that Rubric-ARM achieves state-of-the-art performance among baselines on multiple benchmarks and significantly improves downstream policy alignment in both offline and online reinforcement learning settings.</p> - https://arxiv.org/abs/2602.01511 - Mon, 02 Feb 2026 00:50:53 +0000 + CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs + https://arxiv.org/abs/2602.03048 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03048.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Yao, Yi-Kai Zhang, Yuxin Chen, Yueqing Sun, Zishan Xu, Yu Yang, Tianhao Hu, Qi Gu, Hui Su, Xunliang Cai</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning.However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading to resource inefficiency. Moreover, existing adaptive methods often rely on instance-level metrics, such as task pass rates, failing to capture the model's dynamic learning state. To address these limitations, we propose CoBA-RL, a reinforcement learning algorithm designed to adaptively allocate rollout budgets based on the model's evolving capability. Specifically, CoBA-RL utilizes a Capability-Oriented Value function to map tasks to their potential training gains and employs a heap-based greedy strategy to efficiently self-calibrate the distribution of computational resources to samples with high training value. Extensive experiments demonstrate that our approach effectively orchestrates the trade-off between exploration and exploitation, delivering consistent generalization improvements across multiple challenging benchmarks. These findings underscore that quantifying sample training value and optimizing budget allocation are pivotal for advancing LLM post-training efficiency.</p> + https://arxiv.org/abs/2602.03048 + Tue, 03 Feb 2026 03:14:36 +0000 - Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars - https://arxiv.org/abs/2602.01538 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01538.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youliang Zhang, Zhengguang Zhou, Zhentao Yu, Ziyao Huang, Teng Hu, Sen Liang, Guozhen Zhang, Ziqiao Peng, Shunkai Li, Yi Chen, Zixiang Zhou, Yuan Zhou, Qinglin Lu, Xiu Li</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Generating talking avatars is a fundamental task in video generation. Although existing methods can generate full-body talking avatars with simple human motion, extending this task to grounded human-object interaction (GHOI) remains an open challenge, requiring the avatar to perform text-aligned interactions with surrounding objects. This challenge stems from the need for environmental perception and the control-quality dilemma in GHOI generation. To address this, we propose a novel dual-stream framework, InteractAvatar, which decouples perception and planning from video synthesis for grounded human-object interaction. Leveraging detection to enhance environmental perception, we introduce a Perception and Interaction Module (PIM) to generate text-aligned interaction motions. Additionally, an Audio-Interaction Aware Generation Module (AIM) is proposed to synthesize vivid talking avatars performing object interactions. With a specially designed motion-to-video aligner, PIM and AIM share a similar network structure and enable parallel co-generation of motions and plausible videos, effectively mitigating the control-quality dilemma. Finally, we establish a benchmark, GroundedInter, for evaluating GHOI video generation. Extensive experiments and comparisons demonstrate the effectiveness of our method in generating grounded human-object interactions for talking avatars. Project page: https://interactavatar.github.io</p> - https://arxiv.org/abs/2602.01538 - Mon, 02 Feb 2026 02:12:09 +0000 + Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning + https://arxiv.org/abs/2602.03086 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03086.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayao Mai, Bangyan Liao, Zhenjun Zhao, Yingping Zeng, Haoang Li, Javier Civera, Tailin Wu, Yi Zhou, Peidong Liu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for these problems typically follow a predictor-corrector (PC) structure, but rely on hand-crafted heuristics for step sizes and iteration termination, which are often suboptimal and task-specific. To address this, we unify these problems under a single framework, which enables the design of a general neural solver. Building on this unified view, we propose Neural Predictor-Corrector (NPC), which replaces hand-crafted heuristics with automatically learned policies. NPC formulates policy selection as a sequential decision-making problem and leverages reinforcement learning to automatically discover efficient strategies. To further enhance generalization, we introduce an amortized training mechanism, enabling one-time offline training for a class of problems and efficient online inference on new instances. Experiments on four representative homotopy problems demonstrate that our method generalizes effectively to unseen instances. It consistently outperforms classical and specialized baselines in efficiency while demonstrating superior stability across tasks, highlighting the value of unifying homotopy methods into a single neural framework.</p> + https://arxiv.org/abs/2602.03086 + Tue, 03 Feb 2026 04:19:48 +0000 - Toward Cognitive Supersensing in Multimodal Large Language Model - https://arxiv.org/abs/2602.01541 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01541.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyi Li, Yifan Shen, Yuanzhe Liu, Yifan Xu, Jiateng Liu, Xinzhuo Li, Zhengyuan Li, Jingyuan Zhu, Yunhan Zhong, Fangzhou Lan, Jianguo Cao, James M. Rehg, Heng Ji, Ismini Lourentzou, Xu Cao</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited, especially when visual details are abstract and require visual memory. Current approaches primarily scale Chain-of-Thought (CoT) reasoning in the text space, even when language alone is insufficient for clear and structured reasoning, and largely neglect visual reasoning mechanisms analogous to the human visuospatial sketchpad and visual imagery. To mitigate this deficiency, we introduce Cognitive Supersensing, a novel training paradigm that endows MLLMs with human-like visual imagery capabilities by integrating a Latent Visual Imagery Prediction (LVIP) head that jointly learns sequences of visual cognitive latent embeddings and aligns them with the answer, thereby forming vision-based internal reasoning chains. We further introduce a reinforcement learning stage that optimizes text reasoning paths based on this grounded visual latent. To evaluate the cognitive capabilities of MLLMs, we present CogSense-Bench, a comprehensive visual question answering (VQA) benchmark assessing five cognitive dimensions. Extensive experiments demonstrate that MLLMs trained with Cognitive Supersensing significantly outperform state-of-the-art baselines on CogSense-Bench and exhibit superior generalization on out-of-domain mathematics and science VQA benchmarks, suggesting that internal visual imagery is potentially key to bridging the gap between perceptual recognition and cognitive understanding. We will open-source the CogSense-Bench and our model weights.</p> - https://arxiv.org/abs/2602.01541 - Mon, 02 Feb 2026 02:19:50 +0000 + Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis + https://arxiv.org/abs/2602.03139 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianhe Wu, Ruibin Li, Lei Zhang, Kede Ma</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Distribution matching distillation (DMD) aligns a multi-step generator with its few-step counterpart to enable high-quality generation under low inference cost. However, DMD tends to suffer from mode collapse, as its reverse-KL formulation inherently encourages mode-seeking behavior, for which existing remedies typically rely on perceptual or adversarial regularization, thereby incurring substantial computational overhead and training instability. In this work, we propose a role-separated distillation framework that explicitly disentangles the roles of distilled steps: the first step is dedicated to preserving sample diversity via a target-prediction (e.g., v-prediction) objective, while subsequent steps focus on quality refinement under the standard DMD loss, with gradients from the DMD objective blocked at the first step. We term this approach Diversity-Preserved DMD (DP-DMD), which, despite its simplicity -- no perceptual backbone, no discriminator, no auxiliary networks, and no additional ground-truth images -- preserves sample diversity while maintaining visual quality on par with state-of-the-art methods in extensive text-to-image experiments.</p> + https://arxiv.org/abs/2602.03139 + Tue, 03 Feb 2026 05:45:25 +0000 - FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents - https://arxiv.org/abs/2602.01566 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01566.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chiwei Zhu, Benfeng Xu, Mingxuan Du, Shaohan Wang, Xiaorui Wang, Zhendong Mao, Yongdong Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits, compressing token budgets for both evidence collection and report writing, and preventing effective test-time scaling. We introduce FS-Researcher, a file-system-based, dual-agent framework that scales deep research beyond the context window via a persistent workspace. Specifically, a Context Builder agent acts as a librarian which browses the internet, writes structured notes, and archives raw sources into a hierarchical knowledge base that can grow far beyond context length. A Report Writer agent then composes the final report section by section, treating the knowledge base as the source of facts. In this framework, the file system serves as a durable external memory and a shared coordination medium across agents and sessions, enabling iterative refinement beyond the context window. Experiments on two open-ended benchmarks (DeepResearch Bench and DeepConsult) show that FS-Researcher achieves state-of-the-art report quality across different backbone models. Further analyses demonstrate a positive correlation between final report quality and the computation allocated to the Context Builder, validating effective test-time scaling under the file-system paradigm. The code and data are anonymously open-sourced at https://github.com/Ignoramus0817/FS-Researcher.</p> - https://arxiv.org/abs/2602.01566 - Mon, 02 Feb 2026 03:00:19 +0000 + Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch + https://arxiv.org/abs/2602.03183 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03183.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyunwoo Kim, Niloofar Mireshghallah, Michael Duan, Rui Xin, Shuyue Stella Li, Jaehun Jung, David Acuna, Qi Pang, Hanshen Xiao, G. Edward Suh, Sewoong Oh, Yulia Tsvetkov, Pang Wei Koh, Yejin Choi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Research involving privacy-sensitive data has always been constrained by data scarcity, standing in sharp contrast to other areas that have benefited from data scaling. This challenge is becoming increasingly urgent as modern AI agents--such as OpenClaw and Gemini Agent--are granted persistent access to highly sensitive personal information. To tackle this longstanding bottleneck and the rising risks, we present Privasis (i.e., privacy oasis), the first million-scale fully synthetic dataset entirely built from scratch--an expansive reservoir of texts with rich and diverse private information--designed to broaden and accelerate research in areas where processing sensitive social data is inevitable. Compared to existing datasets, Privasis, comprising 1.4 million records, offers orders-of-magnitude larger scale with quality, and far greater diversity across various document types, including medical history, legal documents, financial records, calendars, and text messages with a total of 55.1 million annotated attributes such as ethnicity, date of birth, workplace, etc. We leverage Privasis to construct a parallel corpus for text sanitization with our pipeline that decomposes texts and applies targeted sanitization. Our compact sanitization models (<=4B) trained on this dataset outperform state-of-the-art large language models, such as GPT-5 and Qwen-3 235B. We plan to release data, models, and code to accelerate future research on privacy-sensitive domains and agents.</p> + https://arxiv.org/abs/2602.03183 + Tue, 03 Feb 2026 06:54:46 +0000 - Generative Visual Code Mobile World Models - https://arxiv.org/abs/2602.01576 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Woosung Koh, Sungjun Han, Segyu Lee, Se-Young Yun, Jamin Shin</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Mobile Graphical User Interface (GUI) World Models (WMs) offer a promising path for improving mobile GUI agent performance at train- and inference-time. However, current approaches face a critical trade-off: text-based WMs sacrifice visual fidelity, while the inability of visual WMs in precise text rendering led to their reliance on slow, complex pipelines dependent on numerous external models. We propose a novel paradigm: visual world modeling via renderable code generation, where a single Vision-Language Model (VLM) predicts the next GUI state as executable web code that renders to pixels, rather than generating pixels directly. This combines the strengths of both approaches: VLMs retain their linguistic priors for precise text rendering while their pre-training on structured web code enables high-fidelity visual generation. We introduce gWorld (8B, 32B), the first open-weight visual mobile GUI WMs built on this paradigm, along with a data generation framework (gWorld) that automatically synthesizes code-based training data. In extensive evaluation across 4 in- and 2 out-of-distribution benchmarks, gWorld sets a new pareto frontier in accuracy versus model size, outperforming 8 frontier open-weight models over 50.25x larger. Further analyses show that (1) scaling training data via gWorld yields meaningful gains, (2) each component of our pipeline improves data quality, and (3) stronger world modeling improves downstream mobile GUI policy performance.</p> - https://arxiv.org/abs/2602.01576 - Mon, 02 Feb 2026 03:12:16 +0000 + Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection + https://arxiv.org/abs/2602.03216 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03216.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongwon Jo, Beomseok Kang, Jiwon Song, Jae-Joon Kim</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods either sparsify the attention map with structured patterns or permanently evict tokens at specific layers, which can retain irrelevant tokens or rely on irreversible early decisions despite the layer-/head-wise dynamics of token importance. In this paper, we propose Token Sparse Attention, a lightweight and dynamic token-level sparsification mechanism that compresses per-head Q, K, V to a reduced token set during attention and then decompresses the output back to the original sequence, enabling token information to be reconsidered in subsequent layers. Furthermore, Token Sparse Attention exposes a new design point at the intersection of token selection and sparse attention. Our approach is fully compatible with dense attention implementations, including Flash Attention, and can be seamlessly composed with existing sparse attention kernels. Experimental results show that Token Sparse Attention consistently improves accuracy-latency trade-off, achieving up to times3.23 attention speedup at 128K context with less than 1% accuracy degradation. These results demonstrate that dynamic and interleaved token-level sparsification is a complementary and effective strategy for scalable long-context inference.</p> + https://arxiv.org/abs/2602.03216 + Tue, 03 Feb 2026 07:31:14 +0000 - Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles - https://arxiv.org/abs/2602.01590 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaohan Wang, Benfeng Xu, Licheng Zhang, Mingxuan Du, Chiwei Zhu, Xiaorui Wang, Zhendong Mao, Yongdong Zhang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Deep Research Agents (DRAs) have demonstrated remarkable capabilities in autonomous information retrieval and report generation, showing great potential to assist humans in complex research tasks. Current evaluation frameworks primarily rely on LLM-generated references or LLM-derived evaluation dimensions. While these approaches offer scalability, they often lack the reliability of expert-verified content and struggle to provide objective, fine-grained assessments of critical dimensions. To bridge this gap, we introduce Wiki Live Challenge (WLC), a live benchmark that leverages the newest Wikipedia Good Articles (GAs) as expert-level references. Wikipedia's strict standards for neutrality, comprehensiveness, and verifiability serve as a great challenge for DRAs, with GAs representing the pinnacle of which. We curate a dataset of 100 recent Good Articles and propose Wiki Eval, a comprehensive evaluation framework comprising a fine-grained evaluation method with 39 criteria for writing quality and rigorous metrics for factual verifiability. Extensive experiments on various DRA systems demonstrate a significant gap between current DRAs and human expert-level Wikipedia articles, validating the effectiveness of WLC in advancing agent research. We release our benchmark at https://github.com/WangShao2000/Wiki_Live_Challenge</p> - https://arxiv.org/abs/2602.01590 - Mon, 02 Feb 2026 03:30:13 +0000 + The Necessity of a Unified Framework for LLM-Based Agent Evaluation + https://arxiv.org/abs/2602.03238 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03238.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengyu Zhu, Li Sun, Philip S. Yu, Sen Su</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> With the advent of Large Language Models (LLMs), general-purpose agents have seen fundamental advancements. However, evaluating these agents presents unique challenges that distinguish them from static QA benchmarks. We observe that current agent benchmarks are heavily confounded by extraneous factors, including system prompts, toolset configurations, and environmental dynamics. Existing evaluations often rely on fragmented, researcher-specific frameworks where the prompt engineering for reasoning and tool usage varies significantly, making it difficult to attribute performance gains to the model itself. Additionally, the lack of standardized environmental data leads to untraceable errors and non-reproducible results. This lack of standardization introduces substantial unfairness and opacity into the field. We propose that a unified evaluation framework is essential for the rigorous advancement of agent evaluation. To this end, we introduce a proposal aimed at standardizing agent evaluation.</p> + https://arxiv.org/abs/2602.03238 + Tue, 03 Feb 2026 08:18:37 +0000 - SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia - https://arxiv.org/abs/2602.01618 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Panuthep Tasawong, Jian Gang Ngui, Alham Fikri Aji, Trevor Cohn, Peerat Limkonchotiwat</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Culturally aware safeguards are crucial for AI alignment in real-world settings, where safety extends beyond common sense and encompasses diverse local values, norms, and region-specific regulations. However, building large-scale, culturally grounded datasets is challenging due to limited resources and a scarcity of native annotators. Consequently, many safeguard models rely on machine translation of English datasets, often missing regional and cultural nuances. We present a novel agentic data-generation framework to scalably create authentic, region-specific safety datasets for Southeast Asia (SEA). On this foundation, we introduce the SEA-Guard family, the first multilingual safeguard models grounded in SEA cultural contexts. Evaluated across multiple benchmarks and cultural variants, SEA-Guard consistently outperforms existing safeguards at detecting regionally sensitive or harmful content while maintaining strong general safety performance.</p> - https://arxiv.org/abs/2602.01618 - Mon, 02 Feb 2026 04:20:35 +0000 + POP: Prefill-Only Pruning for Efficient Large Model Inference + https://arxiv.org/abs/2602.03295 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junhui He, Zhihui Fu, Jun Wang, Qingan Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities. However, their deployment is hindered by significant computational costs. Existing structured pruning methods, while hardware-efficient, often suffer from significant accuracy degradation. In this paper, we argue that this failure stems from a stage-agnostic pruning approach that overlooks the asymmetric roles between the prefill and decode stages. By introducing a virtual gate mechanism, our importance analysis reveals that deep layers are critical for next-token prediction (decode) but largely redundant for context encoding (prefill). Leveraging this insight, we propose Prefill-Only Pruning (POP), a stage-aware inference strategy that safely omits deep layers during the computationally intensive prefill stage while retaining the full model for the sensitive decode stage. To enable the transition between stages, we introduce independent Key-Value (KV) projections to maintain cache integrity, and a boundary handling strategy to ensure the accuracy of the first generated token. Extensive experiments on Llama-3.1, Qwen3-VL, and Gemma-3 across diverse modalities demonstrate that POP achieves up to 1.37times speedup in prefill latency with minimal performance loss, effectively overcoming the accuracy-efficiency trade-off limitations of existing structured pruning methods.</p> + https://arxiv.org/abs/2602.03295 + Tue, 03 Feb 2026 09:22:26 +0000 - PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards - https://arxiv.org/abs/2602.01624 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01624.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minh-Quan Le, Gaurav Mittal, Cheng Zhao, David Gu, Dimitris Samaras, Mei Chen</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality and semantic alignment of generated videos. However, recent methods either rely on large-scale human preference annotations or operate on misaligned embeddings from pre-trained vision-language models, leading to limited scalability or suboptimal supervision. We present PISCES, an annotation-free post-training algorithm that addresses these limitations via a novel Dual Optimal Transport (OT)-aligned Rewards module. To align reward signals with human judgment, PISCES uses OT to bridge text and video embeddings at both distributional and discrete token levels, enabling reward supervision to fulfill two objectives: (i) a Distributional OT-aligned Quality Reward that captures overall visual quality and temporal coherence; and (ii) a Discrete Token-level OT-aligned Semantic Reward that enforces semantic, spatio-temporal correspondence between text and video tokens. To our knowledge, PISCES is the first to improve annotation-free reward supervision in generative post-training through the lens of OT. Experiments on both short- and long-video generation show that PISCES outperforms both annotation-based and annotation-free methods on VBench across Quality and Semantic scores, with human preference studies further validating its effectiveness. We show that the Dual OT-aligned Rewards module is compatible with multiple optimization paradigms, including direct backpropagation and reinforcement learning fine-tuning.</p> - https://arxiv.org/abs/2602.01624 - Mon, 02 Feb 2026 04:37:11 +0000 + MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning + https://arxiv.org/abs/2602.03320 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengyuan Liu, Liuxin Bao, Qi Yang, Wanting Geng, Boyun Zheng, Chenxin Li, Wenting Chen, Houwen Peng, Yixuan Yuan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Medical image segmentation is evolving from task-specific models toward generalizable frameworks. Recent research leverages Multi-modal Large Language Models (MLLMs) as autonomous agents, employing reinforcement learning with verifiable reward (RLVR) to orchestrate specialized tools like the Segment Anything Model (SAM). However, these approaches often rely on single-turn, rigid interaction strategies and lack process-level supervision during training, which hinders their ability to fully exploit the dynamic potential of interactive tools and leads to redundant actions. To bridge this gap, we propose MedSAM-Agent, a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process. First, we introduce a hybrid prompting strategy for expert-curated trajectory generation, enabling the model to internalize human-like decision heuristics and adaptive refinement strategies. Furthermore, we develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification with a clinical-fidelity process reward design to promote interaction parsimony and decision efficiency. Extensive experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance, effectively unifying autonomous medical reasoning with robust, iterative optimization. Code is available https://github.com/CUHK-AIM-Group/MedSAM-Agent{here}.</p> + https://arxiv.org/abs/2602.03320 + Tue, 03 Feb 2026 09:47:49 +0000 - CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation - https://arxiv.org/abs/2602.01660 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongyuan Peng, Caijun Xu, Changyi Xiao, Shibo Hong, Eli Zhang, Stephen Huang, Yixin Cao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large Reasoning Models (LRMs) benefit substantially from training on challenging competition-level questions. However, existing automated question synthesis methods lack precise difficulty control, incur high computational costs, and struggle to generate competition-level questions at scale. In this paper, we propose CoDiQ (Controllable Difficult Question Generation), a novel framework enabling fine-grained difficulty control via test-time scaling while ensuring question solvability. Specifically, first, we identify a test-time scaling tendency (extended reasoning token budget boosts difficulty but reduces solvability) and the intrinsic properties defining the upper bound of a model's ability to generate valid, high-difficulty questions. Then, we develop CoDiQ-Generator from Qwen3-8B, which improves the upper bound of difficult question generation, making it particularly well-suited for challenging question construction. Building on the CoDiQ framework, we build CoDiQ-Corpus (44K competition-grade question sequences). Human evaluations show these questions are significantly more challenging than LiveCodeBench/AIME with over 82% solvability. Training LRMs on CoDiQ-Corpus substantially improves reasoning performance, verifying that scaling controlled-difficulty training questions enhances reasoning capabilities. We open-source CoDiQ-Corpus, CoDiQ-Generator, and implementations to support related research.</p> - https://arxiv.org/abs/2602.01660 - Mon, 02 Feb 2026 05:28:26 +0000 + SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training + https://arxiv.org/abs/2602.03411 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03411.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huatong Song, Lisheng Huang, Shuang Sun, Jinhao Jiang, Ran Le, Daixuan Cheng, Guoxin Chen, Yiwen Hu, Zongchao Chen, Wayne Xin Zhao, Yang Song, Tao Zhang, Ji-Rong Wen</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4\% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8\% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.</p> + https://arxiv.org/abs/2602.03411 + Tue, 03 Feb 2026 11:38:48 +0000 - TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios - https://arxiv.org/abs/2602.01675 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01675.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanzhe Shen, Zisu Huang, Zhengyuan Wang, Muzhao Tian, Zhengkang Guo, Chenyang Zhang, Shuaiyu Zhou, Zengjie Hu, Dailin Li, Jingwen Xu, Kaimin Wang, Wenhao Liu, Tianlong Li, Fengpeng Yue, Feng Hong, Cao Liu, Ke Zeng</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior over long, multi-turn interactions. To bridge this gap, we introduce TRIP-Bench, a long-horizon benchmark grounded in realistic travel-planning scenarios. TRIP-Bench leverages real-world data, offers 18 curated tools and 40+ travel requirements, and supports automated evaluation. It includes splits of varying difficulty; the hard split emphasizes long and ambiguous interactions, style shifts, feasibility changes, and iterative version revision. Dialogues span up to 15 user turns, can involve 150+ tool calls, and may exceed 200k tokens of context. Experiments show that even advanced models achieve at most 50\% success on the easy split, with performance dropping below 10\% on hard subsets. We further propose GTPO, an online multi-turn reinforcement learning method with specialized reward normalization and reward differencing. Applied to Qwen2.5-32B-Instruct, GTPO improves constraint satisfaction and interaction robustness, outperforming Gemini-3-Pro in our evaluation. We expect TRIP-Bench to advance practical long-horizon interactive agents, and GTPO to provide an effective online RL recipe for robust long-horizon training.</p> - https://arxiv.org/abs/2602.01675 - Mon, 02 Feb 2026 05:43:08 +0000 + SWE-World: Building Software Engineering Agents in Docker-Free Environments + https://arxiv.org/abs/2602.03419 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuang Sun, Huatong Song, Lisheng Huang, Jinhao Jiang, Ran Le, Zhihao Lv, Zongchao Chen, Yiwen Hu, Wenyang Luo, Wayne Xin Zhao, Yang Song, Hongteng Xu, Tao Zhang, Ji-Rong Wen</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Recent advances in large language models (LLMs) have enabled software engineering agents to tackle complex code modification tasks. Most existing approaches rely on execution feedback from containerized environments, which require dependency-complete setup and physical execution of programs and tests. While effective, this paradigm is resource-intensive and difficult to maintain, substantially complicating agent training and limiting scalability. We propose SWE-World, a Docker-free framework that replaces physical execution environments with a learned surrogate for training and evaluating software engineering agents. SWE-World leverages LLM-based models trained on real agent-environment interaction data to predict intermediate execution outcomes and final test feedback, enabling agents to learn without interacting with physical containerized environments. This design preserves the standard agent-environment interaction loop while eliminating the need for costly environment construction and maintenance during agent optimization and evaluation. Furthermore, because SWE-World can simulate the final evaluation outcomes of candidate trajectories without real submission, it enables selecting the best solution among multiple test-time attempts, thereby facilitating effective test-time scaling (TTS) in software engineering tasks. Experiments on SWE-bench Verified demonstrate that SWE-World raises Qwen2.5-Coder-32B from 6.2\% to 52.0\% via Docker-free SFT, 55.0\% with Docker-free RL, and 68.2\% with further TTS. The code is available at https://github.com/RUCAIBox/SWE-World</p> + https://arxiv.org/abs/2602.03419 + Tue, 03 Feb 2026 11:44:39 +0000 - Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation - https://arxiv.org/abs/2602.01756 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01756.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jun He, Junyan Ye, Zilong Huang, Dongzhi Jiang, Chenjue Zhang, Leqi Zhu, Renrui Zhang, Xiang Zhang, Weijia Li</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> While text-to-image generation has achieved unprecedented fidelity, the vast majority of existing models function fundamentally as static text-to-pixel decoders. Consequently, they often fail to grasp implicit user intentions. Although emerging unified understanding-generation models have improved intent comprehension, they still struggle to accomplish tasks involving complex knowledge reasoning within a single model. Moreover, constrained by static internal priors, these models remain unable to adapt to the evolving dynamics of the real world. To bridge these gaps, we introduce Mind-Brush, a unified agentic framework that transforms generation into a dynamic, knowledge-driven workflow. Simulating a human-like 'think-research-create' paradigm, Mind-Brush actively retrieves multimodal evidence to ground out-of-distribution concepts and employs reasoning tools to resolve implicit visual constraints. To rigorously evaluate these capabilities, we propose Mind-Bench, a comprehensive benchmark comprising 500 distinct samples spanning real-time news, emerging concepts, and domains such as mathematical and Geo-Reasoning. Extensive experiments demonstrate that Mind-Brush significantly enhances the capabilities of unified models, realizing a zero-to-one capability leap for the Qwen-Image baseline on Mind-Bench, while achieving superior results on established benchmarks like WISE and RISE.</p> - https://arxiv.org/abs/2602.01756 - Mon, 02 Feb 2026 07:42:13 +0000 + Contextualized Visual Personalization in Vision-Language Models + https://arxiv.org/abs/2602.03454 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03454.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yeongtak Oh, Sangwon Yu, Junsung Park, Han Cheol Moon, Jisoo Mok, Sungroh Yoon</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Despite recent progress in vision-language models (VLMs), existing approaches often fail to generate personalized responses based on the user's specific experiences, as they lack the ability to associate visual inputs with a user's accumulated visual-textual context. We newly formalize this challenge as contextualized visual personalization, which requires the visual recognition and textual retrieval of personalized visual experiences by VLMs when interpreting new images. To address this issue, we propose CoViP, a unified framework that treats personalized image captioning as a core task for contextualized visual personalization and improves this capability through reinforcement-learning-based post-training and caption-augmented generation. We further introduce diagnostic evaluations that explicitly rule out textual shortcut solutions and verify whether VLMs truly leverage visual context. Extensive experiments demonstrate that existing open-source and proprietary VLMs exhibit substantial limitations, while CoViP not only improves personalized image captioning but also yields holistic gains across downstream personalization tasks. These results highlight CoViP as a crucial stage for enabling robust and generalizable contextualized visual personalization.</p> + https://arxiv.org/abs/2602.03454 + Tue, 03 Feb 2026 12:21:26 +0000 - Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention - https://arxiv.org/abs/2602.01801 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01801.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dvir Samuel, Issar Tzachor, Matan Levy, Micahel Green, Gal Chechik, Rami Ben-Ari</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines. However, their core attention layers become a major bottleneck at inference time: as generation progresses, the KV cache grows, causing both increasing latency and escalating GPU memory, which in turn restricts usable temporal context and harms long-range consistency. In this work, we study redundancy in autoregressive video diffusion and identify three persistent sources: near-duplicate cached keys across frames, slowly evolving (largely semantic) queries/keys that make many attention computations redundant, and cross-attention over long prompts where only a small subset of tokens matters per frame. Building on these observations, we propose a unified, training-free attention framework for autoregressive diffusion: TempCache compresses the KV cache via temporal correspondence to bound cache growth; AnnCA accelerates cross-attention by selecting frame-relevant prompt tokens using fast approximate nearest neighbor (ANN) matching; and AnnSA sparsifies self-attention by restricting each query to semantically matched keys, also using a lightweight ANN. Together, these modules reduce attention, compute, and memory and are compatible with existing autoregressive diffusion backbones and world models. Experiments demonstrate up to x5--x10 end-to-end speedups while preserving near-identical visual quality and, crucially, maintaining stable throughput and nearly constant peak GPU memory usage over long rollouts, where prior methods progressively slow down and suffer from increasing memory usage.</p> - https://arxiv.org/abs/2602.01801 - Mon, 02 Feb 2026 08:31:21 +0000 + Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation + https://arxiv.org/abs/2602.03619 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changze Lv, Jie Zhou, Wentao Zhao, Jingwen Xu, Zisu Huang, Muzhao Tian, Shihan Dou, Tao Gui, Le Tian, Xiao Zhou, Xiaoqing Zheng, Xuanjing Huang, Jie Zhou</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Nowadays, training and evaluating DeepResearch-generated reports remain challenging due to the lack of verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on coarse, pre-defined rubrics that lack sufficient granularity, or depend on manually constructed query-specific rubrics that are costly and difficult to scale. In this paper, we propose a pipeline to train human-preference-aligned query-specific rubric generators tailored for DeepResearch report generation. We first construct a dataset of DeepResearch-style queries annotated with human preferences over paired reports, and train rubric generators via reinforcement learning with a hybrid reward combining human preference supervision and LLM-based rubric evaluation. To better handle long-horizon reasoning, we further introduce a Multi-agent Markov-state (MaMs) workflow for report generation. We empirically show that our proposed rubric generators deliver more discriminative and better human-aligned supervision than existing rubric design strategies. Moreover, when integrated into the MaMs training framework, DeepResearch systems equipped with our rubric generators consistently outperform all open-source baselines on the DeepResearch Bench and achieve performance comparable to that of leading closed-source models.</p> + https://arxiv.org/abs/2602.03619 + Tue, 03 Feb 2026 15:09:56 +0000 - INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery - https://arxiv.org/abs/2602.01815 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhui Jang, Seonghyun Park, Jaehyung Kim, Sungsoo Ahn</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Multi-agent systems have emerged as a powerful paradigm for automating scientific discovery. To differentiate agent behavior in the multi-agent system, current frameworks typically assign generic role-based personas such as ''reviewer'' or ''writer'' or rely on coarse grained keyword-based personas. While functional, this approach oversimplifies how human scientists operate, whose contributions are shaped by their unique research trajectories. In response, we propose INDIBATOR, a framework for molecular discovery that grounds agents in individualized scientist profiles constructed from two modalities: publication history for literature-derived knowledge and molecular history for structural priors. These agents engage in multi-turn debate through proposal, critique, and voting phases. Our evaluation demonstrates that these fine-grained individuality-grounded agents consistently outperform systems relying on coarse-grained personas, achieving competitive or state-of-the-art performance. These results validate that capturing the ``scientific DNA'' of individual agents is essential for high-quality discovery.</p> - https://arxiv.org/abs/2602.01815 - Mon, 02 Feb 2026 08:47:36 +0000 + Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration + https://arxiv.org/abs/2602.03647 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowei He, Minda Hu, Zenan Xu, Hongru Wang, Licheng Zong, Yankai Chen, Chen Ma, Xue Liu, Pluto Zhou, Irwin King</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Search-integrated reasoning enables language agents to transcend static parametric knowledge by actively querying external sources. However, training these agents via reinforcement learning is hindered by the multi-scale credit assignment problem: existing methods typically rely on sparse, trajectory-level rewards that fail to distinguish between high-quality reasoning and fortuitous guesses, leading to redundant or misleading search behaviors. To address this, we propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention, with both components jointly optimized during training. Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories, and a Meta-Refiner, which selectively diagnoses and repairs flawed steps via a 'cut-and-regenerate' mechanism. To provide fine-grained supervision, we introduce a hybrid reward design that couples outcome correctness with a dense process reward quantifying the information density of retrieved evidence. Theoretically, we formalize the Actor-Refiner interaction as a smoothed mixture policy, proving that selective correction yields strict performance gains over strong baselines. Extensive experiments across various general and multi-hop QA datasets demonstrate that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales, achieving superior reasoning accuracy with minimal overhead.</p> + https://arxiv.org/abs/2602.03647 + Tue, 03 Feb 2026 15:32:09 +0000 - Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models - https://arxiv.org/abs/2602.01842 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinbin Bai, Yixuan Li, Yuchen Zhu, Yi Xin, Qingyu Shi, Aosong Feng, Xiaohong Liu, Molei Tao, Jianru Xue, Xiangtai Li, Ming-Hsuan Yang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their parallel decoding over the entire sequence. As a result, developing effective and efficient TTS methods to unlock dLLMs' full generative potential remains an underexplored challenge. To address this, we propose Prism (Pruning, Remasking, and Integrated Self-verification Method), an efficient TTS framework for dLLMs that (i) performs Hierarchical Trajectory Search (HTS) which dynamically prunes and reallocates compute in an early-to-mid denoising window, (ii) introduces Local branching with partial remasking to explore diverse implementations while preserving high-confidence tokens, and (iii) replaces external verifiers with Self-Verified Feedback (SVF) obtained via self-evaluation prompts on intermediate completions. Across four mathematical reasoning and code generation benchmarks on three dLLMs, including LLaDA 8B Instruct, Dream 7B Instruct, and LLaDA 2.0-mini, our Prism achieves a favorable performance-efficiency trade-off, matching best-of-N performance with substantially fewer function evaluations (NFE). The code is released at https://github.com/viiika/Prism.</p> - https://arxiv.org/abs/2602.01842 - Mon, 02 Feb 2026 09:14:51 +0000 + Instruction Anchors: Dissecting the Causal Dynamics of Modality Arbitration + https://arxiv.org/abs/2602.03677 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03677.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zhang, Mufan Xu, Xuefeng Bai, Kehai chen, Pengfei Zhang, Yang Xiang, Min Zhang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Modality following serves as the capacity of multimodal large language models (MLLMs) to selectively utilize multimodal contexts based on user instructions. It is fundamental to ensuring safety and reliability in real-world deployments. However, the underlying mechanisms governing this decision-making process remain poorly understood. In this paper, we investigate its working mechanism through an information flow lens. Our findings reveal that instruction tokens function as structural anchors for modality arbitration: Shallow attention layers perform non-selective information transfer, routing multimodal cues to these anchors as a latent buffer; Modality competition is resolved within deep attention layers guided by the instruction intent, while MLP layers exhibit semantic inertia, acting as an adversarial force. Furthermore, we identify a sparse set of specialized attention heads that drive this arbitration. Causal interventions demonstrate that manipulating a mere 5% of these critical heads can decrease the modality-following ratio by 60% through blocking, or increase it by 60% through targeted amplification of failed samples. Our work provides a substantial step toward model transparency and offers a principled framework for the orchestration of multimodal information in MLLMs.</p> + https://arxiv.org/abs/2602.03677 + Tue, 03 Feb 2026 15:59:24 +0000 - How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing - https://arxiv.org/abs/2602.01851 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01851.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huanyu Zhang, Xuehai Bai, Chengzu Li, Chen Liang, Haochen Tian, Haodong Li, Ruichuan An, Yifan Zhang, Anna Korhonen, Zhang Zhang, Liang Wang, Tieniu Tan</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In contrast, human communication is inherently multimodal, where visual instructions such as sketches efficiently convey spatial and structural intent. To address this gap, we introduce VIBE, the Visual Instruction Benchmark for Image Editing with a three-level interaction hierarchy that captures deictic grounding, morphological manipulation, and causal reasoning. Across these levels, we curate high-quality and diverse test cases that reflect progressively increasing complexity in visual instruction following. We further propose a robust LMM-as-a-judge evaluation framework with task-specific metrics to enable scalable and fine-grained assessment. Through a comprehensive evaluation of 17 representative open-source and proprietary image editing models, we find that proprietary models exhibit early-stage visual instruction-following capabilities and consistently outperform open-source models. However, performance degrades markedly with increasing task difficulty even for the strongest systems, highlighting promising directions for future research.</p> - https://arxiv.org/abs/2602.01851 - Mon, 02 Feb 2026 09:24:45 +0000 + No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding + https://arxiv.org/abs/2602.03709 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03709.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vynska Amalia Permadi, Xingwei Tan, Nafise Sadat Moosavi, Nikos Aletras</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Understanding culture requires reasoning across context, tradition, and implicit social knowledge, far beyond recalling isolated facts. Yet most culturally focused question answering (QA) benchmarks rely on single-hop questions, which may allow models to exploit shallow cues rather than demonstrate genuine cultural reasoning. In this work, we introduce ID-MoCQA, the first large-scale multi-hop QA dataset for assessing the cultural understanding of large language models (LLMs), grounded in Indonesian traditions and available in both English and Indonesian. We present a new framework that systematically transforms single-hop cultural questions into multi-hop reasoning chains spanning six clue types (e.g., commonsense, temporal, geographical). Our multi-stage validation pipeline, combining expert review and LLM-as-a-judge filtering, ensures high-quality question-answer pairs. Our evaluation across state-of-the-art models reveals substantial gaps in cultural reasoning, particularly in tasks requiring nuanced inference. ID-MoCQA provides a challenging and essential benchmark for advancing the cultural competency of LLMs.</p> + https://arxiv.org/abs/2602.03709 + Tue, 03 Feb 2026 16:32:00 +0000 - Internal Flow Signatures for Self-Checking and Refinement in LLMs - https://arxiv.org/abs/2602.01897 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sungheon Jeong, Sanggeon Yun, Ryozo Masukawa, Wenjun Haung, Hanning Chen, Mohsen Imani</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models can generate fluent answers that are unfaithful to the provided context, while many safeguards rely on external verification or a separate judge after generation. We introduce internal flow signatures that audit decision formation from depthwise dynamics at a fixed inter-block monitoring boundary. The method stabilizes token-wise motion via bias-centered monitoring, then summarizes trajectories in compact moving readout-aligned subspaces constructed from the top token and its close competitors within each depth window. Neighboring window frames are aligned by an orthogonal transport, yielding depth-comparable transported step lengths, turning angles, and subspace drift summaries that are invariant to within-window basis choices. A lightweight GRU validator trained on these signatures performs self-checking without modifying the base model. Beyond detection, the validator localizes a culprit depth event and enables a targeted refinement: the model rolls back to the culprit token and clamps an abnormal transported step at the identified block while preserving the orthogonal residual. The resulting pipeline provides actionable localization and low-overhead self-checking from internal decision dynamics. Code is available at github.com/EavnJeong/Internal-Flow-Signatures-for-Self-Checking-and-Refinement-in-LLMs.</p> - https://arxiv.org/abs/2602.01897 - Mon, 02 Feb 2026 10:05:54 +0000 + LIVE: Long-horizon Interactive Video World Modeling + https://arxiv.org/abs/2602.03747 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junchao Huang, Ziyang Ye, Xinting Hu, Tianyu He, Guiyu Zhang, Shaoshuai Shi, Jiang Bian, Li Jiang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Autoregressive video world models predict future visual observations conditioned on actions. While effective over short horizons, these models often struggle with long-horizon generation, as small prediction errors accumulate over time. Prior methods alleviate this by introducing pre-trained teacher models and sequence-level distribution matching, which incur additional computational cost and fail to prevent error propagation beyond the training horizon. In this work, we propose LIVE, a Long-horizon Interactive Video world modEl that enforces bounded error accumulation via a novel cycle-consistency objective, thereby eliminating the need for teacher-based distillation. Specifically, LIVE first performs a forward rollout from ground-truth frames and then applies a reverse generation process to reconstruct the initial state. The diffusion loss is subsequently computed on the reconstructed terminal state, providing an explicit constraint on long-horizon error propagation. Moreover, we provide an unified view that encompasses different approaches and introduce progressive training curriculum to stabilize training. Experiments demonstrate that LIVE achieves state-of-the-art performance on long-horizon benchmarks, generating stable, high-quality videos far beyond training rollout lengths.</p> + https://arxiv.org/abs/2602.03747 + Tue, 03 Feb 2026 17:10:03 +0000 - Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models - https://arxiv.org/abs/2602.01970 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01970.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yun Qu, Qi Wang, Yixiu Mao, Heming Zou, Yuhang Jiang, Weijie Liu, Clive Bai, Kai Yang, Yangkun Chen, Saiyong Yang, Xiangyang Ji</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-intensive optimization. Online prompt selection presents a plausible solution by prioritizing informative prompts to improve training efficiency. However, current methods either depend on costly, exact evaluations or construct prompt-specific predictive models lacking generalization across prompts. This study introduces Generalizable Predictive Prompt Selection (GPS), which performs Bayesian inference towards prompt difficulty using a lightweight generative model trained on the shared optimization history. Intermediate-difficulty prioritization and history-anchored diversity are incorporated into the batch acquisition principle to select informative prompt batches. The small predictive model also generalizes at test-time for efficient computational allocation. Experiments across varied reasoning benchmarks indicate GPS's substantial improvements in training efficiency, final performance, and test-time efficiency over superior baseline methods.</p> - https://arxiv.org/abs/2602.01970 - Mon, 02 Feb 2026 11:24:36 +0000 + AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration + https://arxiv.org/abs/2602.03786 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianhao Ruan, Zhihao Xu, Yiran Peng, Fashen Ren, Zhaoyang Yu, Xinbing Liang, Jinyu Xiang, Bang Liu, Chenglin Wu, Yuyu Luo, Jiayi Zhang</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs still lack a dynamic abstraction view of sub-agents, thereby hurting adaptability. We address this challenge with a unified, framework-agnostic agent abstraction that models any agent as a tuple Instruction, Context, Tools, Model. This tuple acts as a compositional recipe for capabilities, enabling the system to spawn specialized executors for each task on demand. Building on this abstraction, we introduce an agentic system AOrchestra, where the central orchestrator concretizes the tuple at each step: it curates task-relevant context, selects tools and models, and delegates execution via on-the-fly automatic agent creation. Such designs enable reducing human engineering efforts, and remain framework-agnostic with plug-and-play support for diverse agents as task executors. It also enables a controllable performance-cost trade-off, allowing the system to approach Pareto-efficient. Across three challenging benchmarks (GAIA, SWE-Bench, Terminal-Bench), AOrchestra achieves 16.28% relative improvement against the strongest baseline when paired with Gemini-3-Flash. The code is available at: https://github.com/FoundationAgents/AOrchestra</p> + https://arxiv.org/abs/2602.03786 + Tue, 03 Feb 2026 17:46:16 +0000 - Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning - https://arxiv.org/abs/2602.01983 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01983.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xintian Shen, Jiawei Chen, Lihao Zheng, Hao Ma, Tao Wei, Kun Zhan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Existing Tool-Integrated Reasoning (TIR) models have effectively extended the question-answering capabilities of LLMs by incorporating external tools. However, real-world scenarios present numerous open-ended problems where fixed tools often fail to meet task requirements. Furthermore, the lack of self-optimization mechanisms means that erroneous tool outputs can mislead the LLM's responses. Additionally, the construction of existing tools entails significant manual effort, which consequently constrains their applicability. Recognizing that the reasoning traces of LLMs encapsulate implicit problem-solving capabilities, we propose UCT, a novel training-free framework that transforms agents from tool users to tool creators. This approach harvests reasoning experiences and distills them into reusable assets. This method transforms the agent from a mere tool user into a tool creator, enabling adaptive tool creation and self-updating during the inference process. We also introduce a memory consolidation mechanism to maintain the tool library, ensuring high reusability of retained experiential memory for subsequent reasoning tasks. This novel automated tool construction paradigm continuously improves tool quality during reasoning, allowing the overall agent system to progress without additional training. Extensive experiments demonstrate that our method serves as a novel paradigm for enhancing the capabilities of TIR models. In particular, the significant performance gains achieved +20.86%uparrow and +23.04%uparrow on benchmarks across multi-domain mathematical and scientific reasoning tasks validate the self-evolving capability of the agent.</p> - https://arxiv.org/abs/2602.01983 - Mon, 02 Feb 2026 11:37:45 +0000 + 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation + https://arxiv.org/abs/2602.03796 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03796.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhixue Fang, Xu He, Songlin Tang, Haoxian Zhang, Qingfeng Li, Xiaoqiang Liu, Pengfei Wan, Kun Gai</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding novel-view synthesis. Explicit 3D models, though structurally informative, suffer from inherent inaccuracies (e.g., depth ambiguity and inaccurate dynamics) which, when used as a strong constraint, override the powerful intrinsic 3D awareness of large-scale video generators. In this work, we revisit motion control from a 3D-aware perspective, advocating for an implicit, view-agnostic motion representation that naturally aligns with the generator's spatial priors rather than depending on externally reconstructed constraints. We introduce 3DiMo, which jointly trains a motion encoder with a pretrained video generator to distill driving frames into compact, view-agnostic motion tokens, injected semantically via cross-attention. To foster 3D awareness, we train with view-rich supervision (i.e., single-view, multi-view, and moving-camera videos), forcing motion consistency across diverse viewpoints. Additionally, we use auxiliary geometric supervision that leverages SMPL only for early initialization and is annealed to zero, enabling the model to transition from external 3D guidance to learning genuine 3D spatial motion understanding from the data and the generator's priors. Experiments confirm that 3DiMo faithfully reproduces driving motions with flexible, text-driven camera control, significantly surpassing existing methods in both motion fidelity and visual quality.</p> + https://arxiv.org/abs/2602.03796 + Tue, 03 Feb 2026 17:59:09 +0000 - Enhancing Multi-Image Understanding through Delimiter Token Scaling - https://arxiv.org/abs/2602.01984 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minyoung Lee, Yeji Park, Dongjun Hwang, Yejin Kim, Seong Joon Oh, Junsuk Choe</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model struggles to distinguish information across different images. Existing LVLMs already employ delimiter tokens to mark the start and end of each image, yet our analysis reveals that these tokens fail to effectively block cross-image information leakage. To enhance their effectiveness, we propose a method that scales the hidden states of delimiter tokens. This enhances the model's ability to preserve image-specific information by reinforcing intra-image interaction and limiting undesired cross-image interactions. Consequently, the model is better able to distinguish between images and reason over them more accurately. Experiments show performance gains on multi-image benchmarks such as Mantis, MuirBench, MIRB, and QBench2. We further evaluate our method on text-only tasks that require clear distinction. The method improves performance on multi-document and multi-table understanding benchmarks, including TQABench, MultiNews, and WCEP-10. Notably, our method requires no additional training or inference cost.</p> - https://arxiv.org/abs/2602.01984 - Mon, 02 Feb 2026 11:38:01 +0000 + FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation + https://arxiv.org/abs/2602.03798 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03798.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zimu Lu, Houxing Ren, Yunqiao Yang, Ke Wang, Zhuofan Zong, Mingjie Zhan, Hongsheng Li</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data processing and storage with fancy visual effects. Notably, constructing production-level full-stack web applications is far more challenging than only generating frontend web pages, demanding careful control of data flow, comprehensive understanding of constantly updating packages and dependencies, and accurate localization of obscure bugs in the codebase. To address these difficulties, we introduce FullStack-Agent, a unified agent system for full-stack agentic coding that consists of three parts: (1) FullStack-Dev, a multi-agent framework with strong planning, code editing, codebase navigation, and bug localization abilities. (2) FullStack-Learn, an innovative data-scaling and self-improving method that back-translates crawled and synthesized website repositories to improve the backbone LLM of FullStack-Dev. (3) FullStack-Bench, a comprehensive benchmark that systematically tests the frontend, backend and database functionalities of the generated website. Our FullStack-Dev outperforms the previous state-of-the-art method by 8.7%, 38.2%, and 15.9% on the frontend, backend, and database test cases respectively. Additionally, FullStack-Learn raises the performance of a 30B model by 9.7%, 9.5%, and 2.8% on the three sets of test cases through self-improvement, demonstrating the effectiveness of our approach. The code is released at https://github.com/mnluzimu/FullStack-Agent.</p> + https://arxiv.org/abs/2602.03798 + Tue, 03 Feb 2026 18:01:34 +0000 - On the Limits of Layer Pruning for Generative Reasoning in LLMs - https://arxiv.org/abs/2602.01997 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.01997.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Safal Shrestha, Anubhav Shrestha, Aadim Nepal, Minwu Kim, Keith Ross</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent works have shown that layer pruning can compress large language models (LLMs) while retaining strong performance on classification benchmarks with little or no finetuning. However, existing pruning techniques often suffer severe degradation on generative reasoning tasks. Through a systematic study across multiple model families, we find that tasks requiring multi-step reasoning are particularly sensitive to depth reduction. Beyond surface-level text degeneration, we observe degradation of critical algorithmic capabilities, including arithmetic computation for mathematical reasoning and balanced parenthesis generation for code synthesis. Under realistic post-training constraints, without access to pretraining-scale data or compute, we evaluate a simple mitigation strategy based on supervised finetuning with Self-Generated Responses. This approach achieves strong recovery on classification tasks, retaining up to 90\% of baseline performance, and yields substantial gains of up to 20--30 percentage points on generative benchmarks compared to prior post-pruning techniques. Crucially, despite these gains, recovery for generative reasoning remains fundamentally limited relative to classification tasks and is viable primarily at lower pruning ratios. Overall, we characterize the practical limits of layer pruning for generative reasoning and provide guidance on when depth reduction can be applied effectively under constrained post-training regimes.</p> - https://arxiv.org/abs/2602.01997 - Mon, 02 Feb 2026 11:57:22 +0000 + Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation + https://arxiv.org/abs/2602.03806 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03806.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziru Chen, Dongdong Chen, Ruinan Jin, Yingbin Liang, Yujia Xie, Huan Sun</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recently, there have been significant research interests in training large language models (LLMs) with reinforcement learning (RL) on real-world tasks, such as multi-turn code generation. While online RL tends to perform better than offline RL, its higher training cost and instability hinders wide adoption. In this paper, we build on the observation that multi-turn code generation can be formulated as a one-step recoverable Markov decision process and propose contextual bandit learning with offline trajectories (Cobalt), a new method that combines the benefits of online and offline RL. Cobalt first collects code generation trajectories using a reference LLM and divides them into partial trajectories as contextual prompts. Then, during online bandit learning, the LLM is trained to complete each partial trajectory prompt through single-step code generation. Cobalt outperforms two multi-turn online RL baselines based on GRPO and VeRPO, and substantially improves R1-Distill 8B and Qwen3 8B by up to 9.0 and 6.2 absolute Pass@1 scores on LiveCodeBench. Also, we analyze LLMs' in-context reward hacking behaviors and augment Cobalt training with perturbed trajectories to mitigate this issue. Overall, our results demonstrate Cobalt as a promising solution for iterative decision-making tasks like multi-turn code generation. Our code and data are available at https://github.com/OSU-NLP-Group/cobalt.</p> + https://arxiv.org/abs/2602.03806 + Tue, 03 Feb 2026 18:08:41 +0000 - Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models - https://arxiv.org/abs/2602.02039 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02039.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Liu, Peijie Yu, Michele Orini, Yali Du, Yulan He</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks. Data Science provides a natural testbed, as real-world analysis starts from raw data rather than explicit queries, yet few benchmarks focus on it. To address this, we introduce Deep Data Research (DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-based benchmark that enables verifiable evaluation. Results show that while frontier models display emerging agency, long-horizon exploration remains challenging. Our analysis highlights that effective investigatory intelligence depends not only on agent scaffolding or merely scaling, but also on intrinsic strategies of agentic models.</p> - https://arxiv.org/abs/2602.02039 - Mon, 02 Feb 2026 12:36:57 +0000 + Adaptive Evidence Weighting for Audio-Spatiotemporal Fusion + https://arxiv.org/abs/2602.03817 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03817.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Oscar Ovanger, Levi Harris, Timothy H. Keitt</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Many machine learning systems have access to multiple sources of evidence for the same prediction target, yet these sources often differ in reliability and informativeness across inputs. In bioacoustic classification, species identity may be inferred both from the acoustic signal and from spatiotemporal context such as location and season; while Bayesian inference motivates multiplicative evidence combination, in practice we typically only have access to discriminative predictors rather than calibrated generative models. We introduce Fusion under INdependent Conditional Hypotheses (FINCH), an adaptive log-linear evidence fusion framework that integrates a pre-trained audio classifier with a structured spatiotemporal predictor. FINCH learns a per-sample gating function that estimates the reliability of contextual information from uncertainty and informativeness statistics. The resulting fusion family contains the audio-only classifier as a special case and explicitly bounds the influence of contextual evidence, yielding a risk-contained hypothesis class with an interpretable audio-only fallback. Across benchmarks, FINCH consistently outperforms fixed-weight fusion and audio-only baselines, improving robustness and error trade-offs even when contextual information is weak in isolation. We achieve state-of-the-art performance on CBI and competitive or improved performance on several subsets of BirdSet using a lightweight, interpretable, evidence-based approach. Code is available: \href{https://anonymous.4open.science/r/birdnoise-85CD/README.md{anonymous-repository}}</p> + https://arxiv.org/abs/2602.03817 + Tue, 03 Feb 2026 18:21:13 +0000 - WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora - https://arxiv.org/abs/2602.02053 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02053.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengyu Wang, Benfeng Xu, Licheng Zhang, Shaohan Wang, Mingxuan Du, Chiwei Zhu, Zhendong Mao</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Graph-based Retrieval-Augmented Generation (GraphRAG) organizes external knowledge as a hierarchical graph, enabling efficient retrieval and aggregation of scattered evidence across multiple documents. However, many existing benchmarks for GraphRAG rely on short, curated passages as external knowledge, failing to adequately evaluate systems in realistic settings involving long contexts and large-scale heterogeneous documents. To bridge this gap, we introduce WildGraphBench, a benchmark designed to assess GraphRAG performance in the wild. We leverage Wikipedia's unique structure, where cohesive narratives are grounded in long and heterogeneous external reference documents, to construct a benchmark reflecting real-word scenarios. Specifically, we sample articles across 12 top-level topics, using their external references as the retrieval corpus and citation-linked statements as ground truth, resulting in 1,100 questions spanning three levels of complexity: single-fact QA, multi-fact QA, and section-level summarization. Experiments across multiple baselines reveal that current GraphRAG pipelines help on multi-fact aggregation when evidence comes from a moderate number of sources, but this aggregation paradigm may overemphasize high-level statements at the expense of fine-grained details, leading to weaker performance on summarization tasks. Project page:https://github.com/BstWPY/WildGraphBench.</p> - https://arxiv.org/abs/2602.02053 - Mon, 02 Feb 2026 12:55:29 +0000 + Accelerating Scientific Research with Gemini: Case Studies and Common Techniques + https://arxiv.org/abs/2602.03837 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03837.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> David P. Woodruff, Vincent Cohen-Addad, Lalit Jain, Jieming Mao, Song Zuo, MohammadHossein Bateni, Simina Branzei, Michael P. Brenner, Lin Chen, Ying Feng, Lance Fortnow, Gang Fu, Ziyi Guan, Zahra Hadizadeh, Mohammad T. Hajiaghayi, Mahdi JafariRaviz, Adel Javanmard, Karthik C. S., Ken-ichi Kawarabayashi, Ravi Kumar, Silvio Lattanzi, Euiwoong Lee, Yi Li, Ioannis Panageas, Dimitris Paparas, Benjamin Przybocki, Bernardo Subercaseaux, Ola Svensson, Shayan Taherijam, Xuan Wu, Eylon Yogev, Morteza Zadimoghaddam, Samson Zhou, Vahab Mirrokni</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in large language models (LLMs) have opened new avenues for accelerating scientific research. While models are increasingly capable of assisting with routine tasks, their ability to contribute to novel, expert-level mathematical discovery is less understood. We present a collection of case studies demonstrating how researchers have successfully collaborated with advanced AI models, specifically Google's Gemini-based models (in particular Gemini Deep Think and its advanced variants), to solve open problems, refute conjectures, and generate new proofs across diverse areas in theoretical computer science, as well as other areas such as economics, optimization, and physics. Based on these experiences, we extract common techniques for effective human-AI collaboration in theoretical research, such as iterative refinement, problem decomposition, and cross-disciplinary knowledge transfer. While the majority of our results stem from this interactive, conversational methodology, we also highlight specific instances that push beyond standard chat interfaces. These include deploying the model as a rigorous adversarial reviewer to detect subtle flaws in existing proofs, and embedding it within a "neuro-symbolic" loop that autonomously writes and executes code to verify complex derivations. Together, these examples highlight the potential of AI not just as a tool for automation, but as a versatile, genuine partner in the creative process of scientific discovery.</p> + https://arxiv.org/abs/2602.03837 + Tue, 03 Feb 2026 18:56:17 +0000 - Closing the Loop: Universal Repository Representation with RPG-Encoder - https://arxiv.org/abs/2602.02084 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02084.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jane Luo, Chengyu Yin, Xin Zhang, Qingtao Li, Steven Liu, Yiming Huang, Jie Wu, Hao Liu, Yangyu Huang, Yu Kang, Fangkai Yang, Ying Xin, Scarlett Li</p><p><b>Upvotes:</b> 76</p><p><b>Summary:</b> Current repository agents encounter a reasoning disconnect due to fragmented representations, as existing methods rely on isolated API documentation or dependency graphs that lack semantic depth. We consider repository comprehension and generation to be inverse processes within a unified cycle: generation expands intent into implementation, while comprehension compresses implementation back into intent. To address this, we propose RPG-Encoder, a framework that generalizes the Repository Planning Graph (RPG) from a static generative blueprint into a unified, high-fidelity representation. RPG-Encoder closes the reasoning loop through three mechanisms: (1) Encoding raw code into the RPG that combines lifted semantic features with code dependencies; (2) Evolving the topology incrementally to decouple maintenance costs from repository scale, reducing overhead by 95.7%; and (3) Operating as a unified interface for structure-aware navigation. In evaluations, RPG-Encoder establishes state-of-the-art repository understanding on SWE-bench Verified with 93.7% Acc@5 and exceeds the best baseline by over 10% on SWE-bench Live Lite. These results highlight our superior fine-grained localization accuracy in complex codebases. Furthermore, it achieves 98.5% reconstruction coverage on RepoCraft, confirming RPG's high-fidelity capacity to mirror the original codebase and closing the loop between intent and implementation.</p> - https://arxiv.org/abs/2602.02084 - Mon, 02 Feb 2026 13:30:00 +0000 - - - FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space - https://arxiv.org/abs/2602.02092 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02092.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> FSVideo Team, Qingyu Chen, Zhiyuan Fang, Haibin Huang, Xinwei Huang, Tong Jin, Minxuan Lin, Bo Liu, Celong Liu, Chongyang Ma, Xing Mei, Xiaohui Shen, Yaojie Shen, Fuwen Tan, Angtian Wang, Xiao Yang, Yiding Yang, Jiamin Yuan, Lingxi Zhang, Yuxin Zhang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We introduce FSVideo, a fast speed transformer-based image-to-video (I2V) diffusion framework. We build our framework on the following key components: 1.) a new video autoencoder with highly-compressed latent space (64times64times4 spatial-temporal downsampling ratio), achieving competitive reconstruction quality; 2.) a diffusion transformer (DIT) architecture with a new layer memory design to enhance inter-layer information flow and context reuse within DIT, and 3.) a multi-resolution generation strategy via a few-step DIT upsampler to increase video fidelity. Our final model, which contains a 14B DIT base model and a 14B DIT upsampler, achieves competitive performance against other popular open-source models, while being an order of magnitude faster. We discuss our model design as well as training strategies in this report.</p> - https://arxiv.org/abs/2602.02092 - Mon, 02 Feb 2026 13:37:38 +0000 - - - An Empirical Study of World Model Quantization - https://arxiv.org/abs/2602.02110 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02110.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongqian Fu, Tianyi Zhao, Kai Han, Hang Zhou, Xinghao Chen, Yunhe Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> World models learn an internal representation of environment dynamics, enabling agents to simulate and reason about future states within a compact latent space for tasks such as planning, prediction, and inference. However, running world models rely on hevay computational cost and memory footprint, making model quantization essential for efficient deployment. To date, the effects of post-training quantization (PTQ) on world models remain largely unexamined. In this work, we present a systematic empirical study of world model quantization using DINO-WM as a representative case, evaluating diverse PTQ methods under both weight-only and joint weight-activation settings. We conduct extensive experiments on different visual planning tasks across a wide range of bit-widths, quantization granularities, and planning horizons up to 50 iterations. Our results show that quantization effects in world models extend beyond standard accuracy and bit-width trade-offs: group-wise weight quantization can stabilize low-bit rollouts, activation quantization granularity yields inconsistent benefits, and quantization sensitivity is highly asymmetric between encoder and predictor modules. Moreover, aggressive low-bit quantization significantly degrades the alignment between the planning objective and task success, leading to failures that cannot be remedied by additional optimization. These findings reveal distinct quantization-induced failure modes in world model-based planning and provide practical guidance for deploying quantized world models under strict computational constraints. The code will be available at https://github.com/huawei-noah/noah-research/tree/master/QuantWM.</p> - https://arxiv.org/abs/2602.02110 - Mon, 02 Feb 2026 13:54:03 +0000 - - - LoopViT: Scaling Visual ARC with Looped Transformers - https://arxiv.org/abs/2602.02156 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02156.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wen-Jie Shu, Xuerui Qiu, Rui-Jie Zhu, Harold Haodong Chen, Yexin Liu, Harry Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent advances in visual reasoning have leveraged vision transformers to tackle the ARC-AGI benchmark. However, we argue that the feed-forward architecture, where computational depth is strictly bound to parameter size, falls short of capturing the iterative, algorithmic nature of human induction. In this work, we propose a recursive architecture called Loop-ViT, which decouples reasoning depth from model capacity through weight-tied recurrence. Loop-ViT iterates a weight-tied Hybrid Block, combining local convolutions and global attention, to form a latent chain of thought. Crucially, we introduce a parameter-free Dynamic Exit mechanism based on predictive entropy: the model halts inference when its internal state ``crystallizes" into a low-uncertainty attractor. Empirical results on the ARC-AGI-1 benchmark validate this perspective: our 18M model achieves 65.8% accuracy, outperforming massive 73M-parameter ensembles. These findings demonstrate that adaptive iterative computation offers a far more efficient scaling axis for visual reasoning than simply increasing network width. The code is available at https://github.com/WenjieShu/LoopViT.</p> - https://arxiv.org/abs/2602.02156 - Mon, 02 Feb 2026 14:32:57 +0000 - - - Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models - https://arxiv.org/abs/2602.02185 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zeng, Wenxuan Huang, Zhen Fang, Shuang Chen, Yufan Shen, Yishuo Cai, Xiaoman Wang, Zhenfei Yin, Lin Chen, Zehui Chen, Shiting Huang, Yiming Zhao, Yao Hu, Philip Torr, Wanli Ouyang, Shaosheng Cao</p><p><b>Upvotes:</b> 107</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have advanced VQA and now support Vision-DeepResearch systems that use search engines for complex visual-textual fact-finding. However, evaluating these visual and textual search abilities is still difficult, and existing benchmarks have two major limitations. First, existing benchmarks are not visual search-centric: answers that should require visual search are often leaked through cross-textual cues in the text questions or can be inferred from the prior world knowledge in current MLLMs. Second, overly idealized evaluation scenario: On the image-search side, the required information can often be obtained via near-exact matching against the full image, while the text-search side is overly direct and insufficiently challenging. To address these issues, we construct the Vision-DeepResearch benchmark (VDR-Bench) comprising 2,000 VQA instances. All questions are created via a careful, multi-stage curation pipeline and rigorous expert review, designed to assess the behavior of Vision-DeepResearch systems under realistic real-world conditions. Moreover, to address the insufficient visual retrieval capabilities of current MLLMs, we propose a simple multi-round cropped-search workflow. This strategy is shown to effectively improve model performance in realistic visual retrieval scenarios. Overall, our results provide practical guidance for the design of future multimodal deep-research systems. The code will be released in https://github.com/Osilly/Vision-DeepResearch.</p> - https://arxiv.org/abs/2602.02185 - Mon, 02 Feb 2026 14:53:11 +0000 - - - Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation - https://arxiv.org/abs/2602.02214 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02214.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongzhou Zhu, Min Zhao, Guande He, Hang Su, Chongxuan Li, Jun Zhu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models, facing an architectural gap when full attention is replaced by causal attention. However, existing approaches do not bridge this gap theoretically. They initialize the AR student via ODE distillation, which requires frame-level injectivity, where each noisy frame must map to a unique clean frame under the PF-ODE of an AR teacher. Distilling an AR student from a bidirectional teacher violates this condition, preventing recovery of the teacher's flow map and instead inducing a conditional-expectation solution, which degrades performance. To address this issue, we propose Causal Forcing that uses an AR teacher for ODE initialization, thereby bridging the architectural gap. Empirical results show that our method outperforms all baselines across all metrics, surpassing the SOTA Self Forcing by 19.3\% in Dynamic Degree, 8.7\% in VisionReward, and 16.7\% in Instruction Following. Project page and the code: https://thu-ml.github.io/CausalForcing.github.io/{https://thu-ml.github.io/CausalForcing.github.io/}</p> - https://arxiv.org/abs/2602.02214 - Mon, 02 Feb 2026 15:19:22 +0000 - - - Show, Don't Tell: Morphing Latent Reasoning into Image Generation - https://arxiv.org/abs/2602.02227 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02227.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harold Haodong Chen, Xinxiang Yin, Wen-Jie Shu, Hongfei Zhang, Zixin Zhang, Chenfei Liao, Litao Guo, Qifeng Chen, Ying-Cong Chen</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation--a hallmark of human creativity. Current reasoning-augmented paradigms most rely on explicit thought processes, where intermediate reasoning is decoded into discrete text at fixed steps with frequent image decoding and re-encoding, leading to inefficiencies, information loss, and cognitive mismatches. To bridge this gap, we introduce LatentMorph, a novel framework that seamlessly integrates implicit latent reasoning into the T2I generation process. At its core, LatentMorph introduces four lightweight components: (i) a condenser for summarizing intermediate generation states into compact visual memory, (ii) a translator for converting latent thoughts into actionable guidance, (iii) a shaper for dynamically steering next image token predictions, and (iv) an RL-trained invoker for adaptively determining when to invoke reasoning. By performing reasoning entirely in continuous latent spaces, LatentMorph avoids the bottlenecks of explicit reasoning and enables more adaptive self-refinement. Extensive experiments demonstrate that LatentMorph (I) enhances the base model Janus-Pro by 16% on GenEval and 25% on T2I-CompBench; (II) outperforms explicit paradigms (e.g., TwiG) by 15% and 11% on abstract reasoning tasks like WISE and IPV-Txt, (III) while reducing inference time by 44% and token consumption by 51%; and (IV) exhibits 71% cognitive alignment with human intuition on reasoning invocation.</p> - https://arxiv.org/abs/2602.02227 - Mon, 02 Feb 2026 15:29:48 +0000 - - - Kimi K2.5: Visual Agentic Intelligence - https://arxiv.org/abs/2602.02276 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, S. H. Cai, Yuan Cao, Y. Charles, H. S. Che, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jiahao Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi Diao, Hao Ding, Mengfan Dong, Mengnan Dong, Yuxin Dong, Yuhao Dong, Angang Du, Chenzhuang Du, Dikang Du, Lingxiao Du, Yulun Du, Yu Fan, Shengjun Fang, Qiulin Feng, Yichen Feng, Garimugai Fu, Kelin Fu, Hongcheng Gao, Tong Gao, Yuyao Ge, Shangyi Geng, Chengyang Gong, Xiaochen Gong, Zhuoma Gongque, Qizheng Gu, Xinran Gu, Yicheng Gu, Longyu Guan, Yuanying Guo, Xiaoru Hao, Weiran He, Wenyang He, Yunjia He, Chao Hong, Hao Hu, Jiaxi Hu, Yangyang Hu, Zhenxing Hu, Ke Huang, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yu Jing, Guokun Lai, Aidi Li, C. Li, Cheng Li, Fang Li, Guanghe Li, Guanyu Li, Haitao Li, Haoyang Li, Jia Li, Jingwei Li, Junxiong Li, Lincan Li, Mo Li, Weihong Li, Wentao Li, Xinhang Li, Xinhao Li, Yang Li, Yanhao Li, Yiwei Li, Yuxiao Li, Zhaowei Li, Zheming Li, Weilong Liao, Jiawei Lin, Xiaohan Lin, Zhishan Lin, Zichao Lin, Cheng Liu, Chenyu Liu, Hongzhang Liu, Liang Liu, Shaowei Liu, Shudong Liu, Shuran Liu, Tianwei Liu, Tianyu Liu, Weizhou Liu, Xiangyan Liu, Yangyang Liu, Yanming Liu, Yibo Liu, Yuanxin Liu, Yue Liu, Zhengying Liu, Zhongnuo Liu, Enzhe Lu, Haoyu Lu, Zhiyuan Lu, Junyu Luo, Tongxu Luo, Yashuo Luo, Long Ma, Yingwei Ma, Shaoguang Mao, Yuan Mei, Xin Men, Fanqing Meng, Zhiyong Meng, Yibo Miao, Minqing Ni, Kun Ouyang, Siyuan Pan, Bo Pang, Yuchao Qian, Ruoyu Qin, Zeyu Qin, Jiezhong Qiu, Bowen Qu, Zeyu Shang, Youbo Shao, Tianxiao Shen, Zhennan Shen, Juanfeng Shi, Lidong Shi, Shengyuan Shi, Feifan Song, Pengwei Song, Tianhui Song, Xiaoxi Song, Hongjin Su, Jianlin Su, Zhaochen Su, Lin Sui, Jinsong Sun, Junyao Sun, Tongyu Sun, Flood Sung, Yunpeng Tai, Chuning Tang, Heyi Tang, Xiaojuan Tang, Zhengyang Tang, Jiawen Tao, Shiyuan Teng, Chaoran Tian, Pengfei Tian, Ao Wang, Bowen Wang, Chensi Wang, Chuang Wang, Congcong Wang, Dingkun Wang, Dinglu Wang, Dongliang Wang, Feng Wang, Hailong Wang, Haiming Wang, Hengzhi Wang, Huaqing Wang, Hui Wang, Jiahao Wang, Jinhong Wang, Jiuzheng Wang, Kaixin Wang, Linian Wang, Qibin Wang, Shengjie Wang, Shuyi Wang, Si Wang, Wei Wang, Xiaochen Wang, Xinyuan Wang, Yao Wang, Yejie Wang, Yipu Wang, Yiqin Wang, Yucheng Wang, Yuzhi Wang, Zhaoji Wang, Zhaowei Wang, Zhengtao Wang, Zhexu Wang, Zihan Wang, Zizhe Wang, Chu Wei, Ming Wei, Chuan Wen, Zichen Wen, Chengjie Wu, Haoning Wu, Junyan Wu, Rucong Wu, Wenhao Wu, Yuefeng Wu, Yuhao Wu, Yuxin Wu, Zijian Wu, Chenjun Xiao, Jin Xie, Xiaotong Xie, Yuchong Xie, Yifei Xin, Bowei Xing, Boyu Xu, Jianfan Xu, Jing Xu, Jinjing Xu, L. H. Xu, Lin Xu, Suting Xu, Weixin Xu, Xinbo Xu, Xinran Xu, Yangchuan Xu, Yichang Xu, Yuemeng Xu, Zelai Xu, Ziyao Xu, Junjie Yan, Yuzi Yan, Guangyao Yang, Hao Yang, Junwei Yang, Kai Yang, Ningyuan Yang, Ruihan Yang, Xiaofei Yang, Xinlong Yang, Ying Yang, Yi Yang, Yi Yang, Zhen Yang, Zhilin Yang, Zonghan Yang, Haotian Yao, Dan Ye, Wenjie Ye, Zhuorui Ye, Bohong Yin, Chengzhen Yu, Longhui Yu, Tao Yu, Tianxiang Yu, Enming Yuan, Mengjie Yuan, Xiaokun Yuan, Yang Yue, Weihao Zeng, Dunyuan Zha, Haobing Zhan, Dehao Zhang, Hao Zhang, Jin Zhang, Puqi Zhang, Qiao Zhang, Rui Zhang, Xiaobin Zhang, Y. Zhang, Yadong Zhang, Yangkun Zhang, Yichi Zhang, Yizhi Zhang, Yongting Zhang, Yu Zhang, Yushun Zhang, Yutao Zhang, Yutong Zhang, Zheng Zhang, Chenguang Zhao, Feifan Zhao, Jinxiang Zhao, Shuai Zhao, Xiangyu Zhao, Yikai Zhao, Zijia Zhao, Huabin Zheng, Ruihan Zheng, Shaojie Zheng, Tengyang Zheng, Junfeng Zhong, Longguang Zhong, Weiming Zhong, M. Zhou, Runjie Zhou, Xinyu Zhou, Zaida Zhou, Jinguo Zhu, Liya Zhu, Xinhao Zhu, Yuxuan Zhu, Zhen Zhu, Jingze Zhuang, Weiyu Zhuang, Ying Zou, Xinxing Zu</p><p><b>Upvotes:</b> 146</p><p><b>Summary:</b> We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to 4.5times over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.</p> - https://arxiv.org/abs/2602.02276 - Mon, 02 Feb 2026 16:17:38 +0000 - - - Cross-Lingual Stability of LLM Judges Under Controlled Generation: Evidence from Finno-Ugric Languages - https://arxiv.org/abs/2602.02287 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02287.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Isaac Chung, Linda Freienthal</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Cross-lingual evaluation of large language models (LLMs) typically conflates two sources of variance: genuine model performance differences and measurement instability. We investigate evaluation reliability by holding generation conditions constant while varying target language. Using synthetic customer-support dialogues generated with identical parameters across Estonian, Finnish, and Hungarian, we test whether automatic metrics and LLM-as-a-judge scoring produce stable model rankings across these morphologically rich, related Finno-Ugric languages. With a small set of Estonian native speaker annotations as a reference point, we find systematic ranking instabilities: surface-level metrics (lexical diversity, surface and semantic similarity) maintain cross-language stability, but pragmatic judgments (coherence, instruction-following) exhibit rank inversions and near-zero correlations. Because generation is controlled, these inconsistencies reflect how judge scoring behaves differently across languages rather than true model differences. This controlled design provides a diagnostic probe: evaluation methods that fail to maintain stability under identical generation conditions signal transfer failure before deployment. Our findings suggest that zero-shot judge transfer is unreliable for discourse-level assessment in morphologically rich languages, motivating language-specific calibration against targeted human baselines. We release our controlled generation protocol, synthetic data, and evaluation framework to enable replication across language families at https://github.com/isaac-chung/cross-lingual-stability-judges.</p> - https://arxiv.org/abs/2602.02287 - Mon, 02 Feb 2026 16:27:32 +0000 - - - Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs - https://arxiv.org/abs/2602.02338 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Liang, Zhongjin Zhang, Yuxuan Zhu, Kerui Zhang, Zhiluohan Guo, Wenhang Zhou, Zonqi Yang, Kangle Wu, Yabo Ni, Anxiang Zeng, Cong Fu, Jianxin Wang, Jiazhi Xia</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item embeddings are learned from foundation models and discretized using generic quantization schemes. This design is misaligned with generative recommendation objectives: semantic embeddings are weakly coupled with collaborative prediction, and generic quantization is inefficient at reducing sequential uncertainty for autoregressive modeling. To address these, we propose ReSID, a recommendation-native, principled SID framework that rethinks representation learning and quantization from the perspective of information preservation and sequential predictability, without relying on LLMs. ReSID consists of two components: (i) Field-Aware Masked Auto-Encoding (FAMAE), which learns predictive-sufficient item representations from structured features, and (ii) Globally Aligned Orthogonal Quantization (GAOQ), which produces compact and predictable SID sequences by jointly reducing semantic ambiguity and prefix-conditional uncertainty. Theoretical analysis and extensive experiments across ten datasets show the effectiveness of ReSID. ReSID consistently outperforms strong sequential and SID-based generative baselines by an average of over 10%, while reducing tokenization cost by up to 122x. Code is available at https://github.com/FuCongResearchSquad/ReSID.</p> - https://arxiv.org/abs/2602.02338 - Mon, 02 Feb 2026 17:00:04 +0000 - - - Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics - https://arxiv.org/abs/2602.02343 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02343.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziwen Xu, Chenyan Wu, Hengyu Sun, Haiwen Hong, Mengru Wang, Yunzhi Yao, Longtao Huang, Hui Xue, Shumin Deng, Zhixuan Chu, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison difficult. In this work, we present a unified view that frames these interventions as dynamic weight updates induced by a control signal, placing them within a single conceptual framework. Building on this view, we propose a unified preference-utility analysis that separates control effects into preference, defined as the tendency toward a target concept, and utility, defined as coherent and task-valid generation, and measures both on a shared log-odds scale using polarity-paired contrastive examples. Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility. We further explain this behavior through an activation manifold perspective, in which control shifts representations along target-concept directions to enhance preference, while utility declines primarily when interventions push representations off the model's valid-generation manifold. Finally, we introduce a new steering approach SPLIT guided by this analysis that improves preference while better preserving utility. Code is available at https://github.com/zjunlp/EasyEdit/blob/main/examples/SPLIT.md.</p> - https://arxiv.org/abs/2602.02343 - Mon, 02 Feb 2026 17:04:36 +0000 - - - Implicit neural representation of textures - https://arxiv.org/abs/2602.02354 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Albert Kwok, Zheyuan Hu, Dounia Hammou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Implicit neural representation (INR) has proven to be accurate and efficient in various domains. In this work, we explore how different neural networks can be designed as a new texture INR, which operates in a continuous manner rather than a discrete one over the input UV coordinate space. Through thorough experiments, we demonstrate that these INRs perform well in terms of image quality, with considerable memory usage and rendering inference time. We analyze the balance between these objectives. In addition, we investigate various related applications in real-time rendering and down-stream tasks, e.g. mipmap fitting and INR-space generation.</p> - https://arxiv.org/abs/2602.02354 - Mon, 02 Feb 2026 17:17:20 +0000 - - - SWE-Universe: Scale Real-World Verifiable Environments to Millions - https://arxiv.org/abs/2602.02361 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02361.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang, Wenting Zhao, Ruisheng Cao, Jiaxi Yang, Jiawei Chen, Mingze Li, Zeyao Ma, Hao Ge, Zongmeng Zhang, Zeyu Cui, Dayiheng Liu, Jingren Zhou, Jianling Sun, Junyang Lin, Binyuan Hui</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic building, such as low production yield, weak verifiers, and prohibitive cost, our framework utilizes a building agent powered by an efficient custom-trained model. This agent employs iterative self-verification and in-loop hacking detection to ensure the reliable generation of high-fidelity, verifiable tasks. Using this method, we scale the number of real-world multilingual SWE environments to a million scale (807,693). We demonstrate the profound value of our environments through large-scale agentic mid-training and reinforcement learning. Finally, we applied this technique to Qwen3-Max-Thinking and achieved a score of 75.3% on SWE-Bench Verified. Our work provides both a critical resource and a robust methodology to advance the next generation of coding agents.</p> - https://arxiv.org/abs/2602.02361 - Mon, 02 Feb 2026 17:20:30 +0000 - - - SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference Optimization - https://arxiv.org/abs/2602.02383 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02383.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maksim Afanasyev, Illarion Iov</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment process by deriving implicit reward functions, yet they often suffer from a critical objective mismatch: optimizing the relative margin between chosen and rejected responses does not guarantee the preservation of the chosen response's absolute likelihood. This can lead to ``unlearning'', where the model degrades the probability of high-quality outputs to satisfy margin constraints, and ``formatting collapse'' caused by the over-penalization of rejected sequences. In this work, we introduce SLIME (Stabilized Likelihood Implicit Margin Enforcement), a reference-free alignment objective designed to decouple preference learning from generation quality. SLIME incorporates a three-pronged objective: (1) an anchoring term to maximize the likelihood of preferred responses; (2) a stabilizing penalty that prevents the probabilities of rejected tokens from collapsing to zero; and (3) a dual-margin mechanism that combines hard and soft constraints for precise boundary shaping. Our results demonstrate that SLIME achieves superior performance compared to state-of-the-art baselines while maintaining higher generation stability.</p> - https://arxiv.org/abs/2602.02383 - Mon, 02 Feb 2026 17:46:06 +0000 - - - UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing - https://arxiv.org/abs/2602.02437 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dianyi Wang, Chaofan Ma, Feng Han, Size Wu, Wei Song, Yibin Wang, Zhixiong Zhang, Tianhang Wang, Siyuan Wang, Zhongyu Wei, Jiaqi Wang</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through a dual reasoning paradigm. We formulate generation as world knowledge-enhanced planning to inject implicit constraints, and leverage editing capabilities for fine-grained visual refinement to further correct visual errors via self-reflection. This approach unifies generation and editing within a shared representation, mirroring the human cognitive process of planning followed by refinement. We support this framework by systematically constructing a large-scale reasoning-centric dataset (~300k samples) covering five major knowledge domains (e.g., cultural commonsense, physics, etc.) for planning, alongside an agent-generated corpus for visual self-correction. Extensive experiments demonstrate that UniReason achieves advanced performance on reasoning-intensive benchmarks such as WISE, KrisBench and UniREditBench, while maintaining superior general synthesis capabilities.</p> - https://arxiv.org/abs/2602.02437 - Mon, 02 Feb 2026 18:34:35 +0000 - - - Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling - https://arxiv.org/abs/2602.02453 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02453.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andong Chen, Wenxin Zhu, Qiuyu Ding, Yuchen Song, Muyun Yang, Tiejun Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Chain-of-Thought reasoning has driven large language models to extend from thinking with text to thinking with images and videos. However, different modalities still have clear limitations: static images struggle to represent temporal structure, while videos introduce substantial redundancy and computational cost. In this work, we propose Thinking with Comics, a visual reasoning paradigm that uses comics as a high information-density medium positioned between images and videos. Comics preserve temporal structure, embedded text, and narrative coherence while requiring significantly lower reasoning cost. We systematically study two reasoning paths based on comics and evaluate them on a range of reasoning tasks and long-context understanding tasks. Experimental results show that Thinking with Comics outperforms Thinking with Images on multi-step temporal and causal reasoning tasks, while remaining substantially more efficient than Thinking with Video. Further analysis indicates that different comic narrative structures and styles consistently affect performance across tasks, suggesting that comics serve as an effective intermediate visual representation for improving multimodal reasoning.</p> - https://arxiv.org/abs/2602.02453 - Mon, 02 Feb 2026 18:43:57 +0000 - - - SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning - https://arxiv.org/abs/2602.02472 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qifan Yu, Xinyu Ma, Zhijian Zhuo, Minrui Wang, Deyi Liu, Shiyi Zhan, Yiyuan Ma, Liang Xiang, Xingyan Bin, Di He</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expansion, width expansion remains significantly understudied, with the few existing methods limited to the early stages of training. However, expanding width during the mid-stage is essential for maximizing computational savings, yet it remains a formidable challenge due to severe training instabilities. Empirically, we show that naive initialization at this stage disrupts activation statistics, triggering loss spikes, while copy-based initialization introduces gradient symmetry that hinders feature diversity. To address these issues, we propose SPARKLING (balancing {S}ignal {P}reservation {A}nd symmet{R}y brea{K}ing for width-progressive {L}earn{ING}), a novel framework for mid-stage width expansion. Our method achieves signal preservation via RMS-scale consistency, stabilizing activation statistics during expansion. Symmetry breaking is ensured through asymmetric optimizer state resetting and learning rate re-warmup. Extensive experiments on Mixture-of-Experts (MoE) models demonstrate that, across multiple width axes and optimizer families, SPARKLING consistently outperforms training from scratch and reduces training cost by up to 35% under 2times width expansion.</p> - https://arxiv.org/abs/2602.02472 - Mon, 02 Feb 2026 18:52:52 +0000 - - - Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability - https://arxiv.org/abs/2602.02477 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02477.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Liang, Zhong-Zhi Li, Zhenghao Lin, Eric Hancheng Jiang, Hengyuan Zhang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Yeyun Gong, Weizhu Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning. Nevertheless, at the limits of model capability, CoT often proves insufficient, and its strictly sequential nature constrains test-time scalability. A potential alternative is divide-and-conquer (DAC) reasoning, which decomposes a complex problem into subproblems to facilitate more effective exploration of the solution. Although promising, our analysis reveals a fundamental misalignment between general-purpose post-training and DAC-style inference, which limits the model's capacity to fully leverage this potential. To bridge this gap and fully unlock LLMs' reasoning capabilities on the most challenging tasks, we propose an end-to-end reinforcement learning (RL) framework to enhance their DAC-style reasoning capacity. At each step, the policy decomposes a problem into a group of subproblems, solves them sequentially, and addresses the original one conditioned on the subproblem solutions, with both decomposition and solution integrated into RL training. Under comparable training, our DAC-style framework endows the model with a higher performance ceiling and stronger test-time scalability, surpassing CoT by 8.6% in Pass@1 and 6.3% in Pass@32 on competition-level benchmarks.</p> - https://arxiv.org/abs/2602.02477 - Mon, 02 Feb 2026 18:54:54 +0000 - - - RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents - https://arxiv.org/abs/2602.02486 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02486.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jialiang Zhu, Gongrui Zhang, Xiaolong Ma, Lin Xu, Miaosen Zhang, Ruiqi Yang, Song Wang, Kai Qiu, Zhirong Wu, Qi Dai, Ruichun Ma, Bei Liu, Yifan Yang, Chong Luo, Zhengyuan Yang, Linjie Li, Lijuan Wang, Weizhu Chen, Xin Geng, Baining Guo</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions, or maintain global awareness under long contexts, often leading to local optima, redundant exploration, and inefficient search. We propose Re-TRAC, an agentic framework that performs cross-trajectory exploration by generating a structured state representation after each trajectory to summarize evidence, uncertainties, failures, and future plans, and conditioning subsequent trajectories on this state representation. This enables iterative reflection and globally informed planning, reframing research as a progressive process. Empirical results show that Re-TRAC consistently outperforms ReAct by 15-20% on BrowseComp with frontier LLMs. For smaller models, we introduce Re-TRAC-aware supervised fine-tuning, achieving state-of-the-art performance at comparable scales. Notably, Re-TRAC shows a monotonic reduction in tool calls and token usage across rounds, indicating progressively targeted exploration driven by cross-trajectory reflection rather than redundant search.</p> - https://arxiv.org/abs/2602.02486 - Mon, 02 Feb 2026 18:58:07 +0000 - - - RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System - https://arxiv.org/abs/2602.02488 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02488.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinjie Wang, Tianbao Xie, Ke Shen, Mengdi Wang, Ling Yang</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> We propose RLAnything, a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, amplifying learning signals and strengthening the overall RL system for any LLM or agentic scenarios. Specifically, the policy is trained with integrated feedback from step-wise and outcome signals, while the reward model is jointly optimized via consistency feedback, which in turn further improves policy training. Moreover, our theory-motivated automatic environment adaptation improves training for both the reward and policy models by leveraging critic feedback from each, enabling learning from experience. Empirically, each added component consistently improves the overall system, and RLAnything yields substantial gains across various representative LLM and agentic tasks, boosting Qwen3-VL-8B-Thinking by 9.1% on OSWorld and Qwen2.5-7B-Instruct by 18.7% and 11.9% on AlfWorld and LiveBench, respectively. We also that optimized reward-model signals outperform outcomes that rely on human labels. Code: https://github.com/Gen-Verse/Open-AgentRL</p> - https://arxiv.org/abs/2602.02488 - Mon, 02 Feb 2026 18:59:04 +0000 - - - PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss - https://arxiv.org/abs/2602.02493 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.02493.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehong Ma, Ruihan Xu, Shiliang Zhang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Pixel diffusion generates images directly in pixel space in an end-to-end manner, avoiding the artifacts and bottlenecks introduced by VAEs in two-stage latent diffusion. However, it is challenging to optimize high-dimensional pixel manifolds that contain many perceptually irrelevant signals, leaving existing pixel diffusion methods lagging behind latent diffusion models. We propose PixelGen, a simple pixel diffusion framework with perceptual supervision. Instead of modeling the full image manifold, PixelGen introduces two complementary perceptual losses to guide diffusion model towards learning a more meaningful perceptual manifold. An LPIPS loss facilitates learning better local patterns, while a DINO-based perceptual loss strengthens global semantics. With perceptual supervision, PixelGen surpasses strong latent diffusion baselines. It achieves an FID of 5.11 on ImageNet-256 without classifier-free guidance using only 80 training epochs, and demonstrates favorable scaling performance on large-scale text-to-image generation with a GenEval score of 0.79. PixelGen requires no VAEs, no latent representations, and no auxiliary stages, providing a simpler yet more powerful generative paradigm. Codes are publicly available at https://github.com/Zehong-Ma/PixelGen.</p> - https://arxiv.org/abs/2602.02493 - Mon, 02 Feb 2026 18:59:42 +0000 + Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing + https://arxiv.org/abs/2602.03845 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.03845.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Zheng, Chengsong Huang, Runpeng Dai, Yun He, Rui Liu, Xin Ni, Huiwen Bao, Kaishen Wang, Hongtu Zhu, Jiaxin Huang, Furong Huang, Heng Huang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Parallel thinking has emerged as a promising paradigm for reasoning, yet it imposes significant computational burdens. Existing efficiency methods primarily rely on local, per-trajectory signals and lack principled mechanisms to exploit global dynamics across parallel branches. We introduce 2D probing, an interface that exposes the width-depth dynamics of parallel thinking by periodically eliciting intermediate answers from all branches. Our analysis reveals three key insights: non-monotonic scaling across width-depth allocations, heterogeneous reasoning branch lengths, and early stabilization of global consensus. Guided by these insights, we introduce Parallel-Probe, a training-free controller designed to optimize online parallel thinking. Parallel-Probe employs consensus-based early stopping to regulate reasoning depth and deviation-based branch pruning to dynamically adjust width. Extensive experiments across three benchmarks and multiple models demonstrate that Parallel-Probe establishes a superior Pareto frontier for test-time scaling. Compared to standard majority voting, it reduces sequential tokens by up to 35.8% and total token cost by over 25.8% while maintaining competitive accuracy.</p> + https://arxiv.org/abs/2602.03845 + Tue, 03 Feb 2026 18:59:41 +0000