From 5069627361a2cbe8693438b7cc8b92c1c45793c7 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Mon, 19 Jan 2026 00:13:23 +0000 Subject: [PATCH] bot: update weekly RSS feed --- feed_weekly.xml | 1052 +++++++++++++++++++++++------------------------ 1 file changed, 526 insertions(+), 526 deletions(-) diff --git a/feed_weekly.xml b/feed_weekly.xml index e9b0814..b5148da 100644 --- a/feed_weekly.xml +++ b/feed_weekly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 12 Jan 2026 00:13:35 +0000 + Mon, 19 Jan 2026 00:13:23 +0000 - Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits - https://arxiv.org/abs/2512.20578 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.20578.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirhosein Ghasemabadi, Di Niu</p><p><b>Upvotes:</b> 69</p><p><b>Summary:</b> Large language models (LLMs) generate fluent and complex outputs but often fail to recognize their own mistakes and hallucinations. Existing approaches typically rely on external judges, multi-sample consistency, or text-based self-critique, which incur additional compute or correlate weakly with true correctness. We ask: can LLMs predict their own failures by inspecting internal states during inference? We introduce Gnosis, a lightweight self-awareness mechanism that enables frozen LLMs to perform intrinsic self-verification by decoding signals from hidden states and attention patterns. Gnosis passively observes internal traces, compresses them into fixed-budget descriptors, and predicts correctness with negligible inference cost, adding only ~5M parameters and operating independently of sequence length. Across math reasoning, open-domain question answering, and academic knowledge benchmarks, and over frozen backbones ranging from 1.7B to 20B parameters, Gnosis consistently outperforms strong internal baselines and large external judges in both accuracy and calibration. Moreover, it generalizes zero-shot to partial generations, enabling early detection of failing trajectories and compute-aware control. These results show that reliable correctness cues are intrinsic to generation process and can be extracted efficiently without external supervision.</p> - https://arxiv.org/abs/2512.20578 - Tue, 23 Dec 2025 18:21:32 +0000 + ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands + https://arxiv.org/abs/2512.24965 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24965.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Hu, Kevin Qinghong Lin, Mike Zheng Shou</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Building intelligent agents capable of dexterous manipulation is essential for achieving human-like automation in both robotics and digital environments. However, existing GUI agents rely on discrete click predictions (x,y), which prohibits free-form, closed-loop trajectories (e.g. dragging a progress bar) that require continuous, on-the-fly perception and adjustment. In this work, we develop ShowUI-π, the first flow-based generative model as GUI dexterous hand, featuring the following designs: (i) Unified Discrete-Continuous Actions, integrating discrete clicks and continuous drags within a shared model, enabling flexible adaptation across diverse interaction modes; (ii) Flow-based Action Generation for drag modeling, which predicts incremental cursor adjustments from continuous visual observations via a lightweight action expert, ensuring smooth and stable trajectories; (iii) Drag Training data and Benchmark, where we manually collect and synthesize 20K drag trajectories across five domains (e.g. PowerPoint, Adobe Premiere Pro), and introduce ScreenDrag, a benchmark with comprehensive online and offline evaluation protocols for assessing GUI agents' drag capabilities. Our experiments show that proprietary GUI agents still struggle on ScreenDrag (e.g. Operator scores 13.27, and the best Gemini-2.5-CUA reaches 22.18). In contrast, ShowUI-π achieves 26.98 with only 450M parameters, underscoring both the difficulty of the task and the effectiveness of our approach. We hope this work advances GUI agents toward human-like dexterous control in digital world. The code is available at https://github.com/showlab/showui-pi.</p> + https://arxiv.org/abs/2512.24965 + Wed, 31 Dec 2025 16:51:14 +0000 - IMA++: ISIC Archive Multi-Annotator Dermoscopic Skin Lesion Segmentation Dataset - https://arxiv.org/abs/2512.21472 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kumar Abhishek, Jeremy Kawahara, Ghassan Hamarneh</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multi-annotator medical image segmentation is an important research problem, but requires annotated datasets that are expensive to collect. Dermoscopic skin lesion imaging allows human experts and AI systems to observe morphological structures otherwise not discernable from regular clinical photographs. However, currently there are no large-scale publicly available multi-annotator skin lesion segmentation (SLS) datasets with annotator-labels for dermoscopic skin lesion imaging. We introduce ISIC MultiAnnot++, a large public multi-annotator skin lesion segmentation dataset for images from the ISIC Archive. The final dataset contains 17,684 segmentation masks spanning 14,967 dermoscopic images, where 2,394 dermoscopic images have 2-5 segmentations per image, making it the largest publicly available SLS dataset. Further, metadata about the segmentation, including the annotators' skill level and segmentation tool, is included, enabling research on topics such as annotator-specific preference modeling for segmentation and annotator metadata analysis. We provide an analysis on the characteristics of this dataset, curated data partitions, and consensus segmentation masks.</p> - https://arxiv.org/abs/2512.21472 - Thu, 25 Dec 2025 02:21:55 +0000 + DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving + https://arxiv.org/abs/2601.01528 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Zhou, Hao Shao, Letian Wang, Zhuofan Zong, Hongsheng Li, Steven L. Waslander</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving, this vision gives rise to driving world models: generative simulators that imagine ego and agent futures, enabling scalable simulation, safe testing of corner cases, and rich synthetic data generation. Yet, despite fast-growing research activity, the field lacks a rigorous benchmark to measure progress and guide priorities. Existing evaluations remain limited: generic video metrics overlook safety-critical imaging factors; trajectory plausibility is rarely quantified; temporal and agent-level consistency is neglected; and controllability with respect to ego conditioning is ignored. Moreover, current datasets fail to cover the diversity of conditions required for real-world deployment. To address these gaps, we present DrivingGen, the first comprehensive benchmark for generative driving world models. DrivingGen combines a diverse evaluation dataset curated from both driving datasets and internet-scale video sources, spanning varied weather, time of day, geographic regions, and complex maneuvers, with a suite of new metrics that jointly assess visual realism, trajectory plausibility, temporal coherence, and controllability. Benchmarking 14 state-of-the-art models reveals clear trade-offs: general models look better but break physics, while driving-specific ones capture motion realistically but lag in visual quality. DrivingGen offers a unified evaluation framework to foster reliable, controllable, and deployable driving world models, enabling scalable simulation, planning, and data-driven decision-making.</p> + https://arxiv.org/abs/2601.01528 + Sun, 04 Jan 2026 13:36:21 +0000 - Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning - https://arxiv.org/abs/2601.00830 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00830.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Deep Pankajbhai Mehta</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> When AI systems explain their reasoning step-by-step, practitioners often assume these explanations reveal what actually influenced the AI's answer. We tested this assumption by embedding hints into questions and measuring whether models mentioned them. In a study of over 9,000 test cases across 11 leading AI models, we found a troubling pattern: models almost never mention hints spontaneously, yet when asked directly, they admit noticing them. This suggests models see influential information but choose not to report it. Telling models they are being watched does not help. Forcing models to report hints works, but causes them to report hints even when none exist and reduces their accuracy. We also found that hints appealing to user preferences are especially dangerous-models follow them most often while reporting them least. These findings suggest that simply watching AI reasoning is not enough to catch hidden influences.</p> - https://arxiv.org/abs/2601.00830 - Thu, 25 Dec 2025 05:29:53 +0000 + VIBE: Visual Instruction Based Editor + https://arxiv.org/abs/2601.02242 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Grigorii Alekseenko, Aleksandr Gordeev, Irina Tolstykh, Bulat Suleimanov, Vladimir Dokholyan, Georgii Fedorov, Sergey Yakubson, Aleksandra Tsybina, Mikhail Chernyshov, Maksim Kuprashevich</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Instruction-based image editing is among the fastest developing areas in generative AI. Over the past year, the field has reached a new level, with dozens of open-source models released alongside highly capable commercial systems. However, only a limited number of open-source approaches currently achieve real-world quality. In addition, diffusion backbones, the dominant choice for these pipelines, are often large and computationally expensive for many deployments and research settings, with widely used variants typically containing 6B to 20B parameters. This paper presents a compact, high-throughput instruction-based image editing pipeline that uses a modern 2B-parameter Qwen3-VL model to guide the editing process and the 1.6B-parameter diffusion model Sana1.5 for image generation. Our design decisions across architecture, data processing, training configuration, and evaluation target low-cost inference and strict source consistency while maintaining high quality across the major edit categories feasible at this scale. Evaluated on the ImgEdit and GEdit benchmarks, the proposed method matches or exceeds the performance of substantially heavier baselines, including models with several times as many parameters and higher inference cost, and is particularly strong on edits that require preserving the input image, such as an attribute adjustment, object removal, background edits, and targeted replacement. The model fits within 24 GB of GPU memory and generates edited images at up to 2K resolution in approximately 4 seconds on an NVIDIA H100 in BF16, without additional inference optimizations or distillation.</p> + https://arxiv.org/abs/2601.02242 + Mon, 05 Jan 2026 16:17:20 +0000 - Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models - https://arxiv.org/abs/2512.21815 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, a measure of model uncertainty, is strongly correlated with the reliability of VLM. Prior entropy-based attacks maximize uncertainty at all decoding steps, implicitly assuming that every token contributes equally to generation instability. We show instead that a small fraction (about 20%) of high-entropy tokens, i.e., critical decision points in autoregressive generation, disproportionately governs output trajectories. By concentrating adversarial perturbations on these positions, we achieve semantic degradation comparable to global methods while using substantially smaller budgets. More importantly, across multiple representative VLMs, such selective attacks convert 35-49% of benign outputs into harmful ones, exposing a more critical safety risk. Remarkably, these vulnerable high-entropy forks recur across architecturally diverse VLMs, enabling feasible transferability (17-26% harmful rates on unseen targets). Motivated by these findings, we propose Entropy-bank Guided Adversarial attacks (EGA), which achieves competitive attack success rates (93-95%) alongside high harmful conversion, thereby revealing new weaknesses in current VLM safety mechanisms.</p> - https://arxiv.org/abs/2512.21815 - Fri, 26 Dec 2025 01:01:25 +0000 + AnyDepth: Depth Estimation Made Easy + https://arxiv.org/abs/2601.02760 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyu Ren, Zeyu Zhang, Wukai Li, Qingxiang Liu, Hao Tang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Monocular depth estimation aims to recover the depth information of 3D scenes from 2D images. Recent work has made significant progress, but its reliance on large-scale datasets and complex decoders has limited its efficiency and generalization ability. In this paper, we propose a lightweight and data-centric framework for zero-shot monocular depth estimation. We first adopt DINOv3 as the visual encoder to obtain high-quality dense features. Secondly, to address the inherent drawbacks of the complex structure of the DPT, we design the Simple Depth Transformer (SDT), a compact transformer-based decoder. Compared to the DPT, it uses a single-path feature fusion and upsampling process to reduce the computational overhead of cross-scale feature fusion, achieving higher accuracy while reducing the number of parameters by approximately 85%-89%. Furthermore, we propose a quality-based filtering strategy to filter out harmful samples, thereby reducing dataset size while improving overall training quality. Extensive experiments on five benchmarks demonstrate that our framework surpasses the DPT in accuracy. This work highlights the importance of balancing model design and data quality for achieving efficient and generalizable zero-shot depth estimation. Code: https://github.com/AIGeeksGroup/AnyDepth. Website: https://aigeeksgroup.github.io/AnyDepth.</p> + https://arxiv.org/abs/2601.02760 + Tue, 06 Jan 2026 06:51:35 +0000 - SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence - https://arxiv.org/abs/2512.22334 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22334.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiheng Wang, Yixin Chen, Shuo Li, Yifan Zhou, Bo Liu, Hengjian Gao, Jiakang Yuan, Jia Bu, Wanghan Xu, Yuhao Zhou, Xiangyu Zhao, Zhiwang Zhou, Fengxiang Wang, Haodong Duan, Songyang Zhang, Jun Yao, Han Deng, Yizhou Wang, Jiabei Xiao, Jiaqi Liu, Encheng Su, Yujie Liu, Weida Wang, Junchi Yao, Shenghe Zheng, Haoran Sun, Runmin Ma, Xiangchao Yan, Bo Zhang, Dongzhan Zhou, Shufei Zhang, Peng Ye, Xiaosong Wang, Shixiang Tang, Wenlong Zhang, Lei Bai</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike general-purpose evaluation platforms, SciEvalKit focuses on the core competencies of scientific intelligence, including Scientific Multimodal Perception, Scientific Multimodal Reasoning, Scientific Multimodal Understanding, Scientific Symbolic Reasoning, Scientific Code Generation, Science Hypothesis Generation and Scientific Knowledge Understanding. It supports six major scientific domains, spanning from physics and chemistry to astronomy and materials science. SciEvalKit builds a foundation of expert-grade scientific benchmarks, curated from real-world, domain-specific datasets, ensuring that tasks reflect authentic scientific challenges. The toolkit features a flexible, extensible evaluation pipeline that enables batch evaluation across models and datasets, supports custom model and dataset integration, and provides transparent, reproducible, and comparable results. By bridging capability-based evaluation and disciplinary diversity, SciEvalKit offers a standardized yet customizable infrastructure to benchmark the next generation of scientific foundation models and intelligent agents. The toolkit is open-sourced and actively maintained to foster community-driven development and progress in AI4Science.</p> - https://arxiv.org/abs/2512.22334 - Fri, 26 Dec 2025 17:36:02 +0000 + MMFormalizer: Multimodal Autoformalization in the Wild + https://arxiv.org/abs/2601.03017 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03017.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Xiong, Qi Han, Yunta Hsieh, Hui Shen, Huajian Xin, Chaofan Tao, Chenyang Zhao, Hengyuan Zhang, Taiqiang Wu, Zhen Zhang, Haochen Wang, Zhongwei Wan, Lingpeng Kong, Ngai Wong</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> Autoformalization, which translates natural language mathematics into formal statements to enable machine reasoning, faces fundamental challenges in the wild due to the multimodal nature of the physical world, where physics requires inferring hidden constraints (e.g., mass or energy) from visual elements. To address this, we propose MMFormalizer, which extends autoformalization beyond text by integrating adaptive grounding with entities from real-world mathematical and physical domains. MMFormalizer recursively constructs formal propositions from perceptually grounded primitives through recursive grounding and axiom composition, with adaptive recursive termination ensuring that every abstraction is supported by visual evidence and anchored in dimensional or axiomatic grounding. We evaluate MMFormalizer on a new benchmark, PhyX-AF, comprising 115 curated samples from MathVerse, PhyX, Synthetic Geometry, and Analytic Geometry, covering diverse multimodal autoformalization tasks. Results show that frontier models such as GPT-5 and Gemini-3-Pro achieve the highest compile and semantic accuracy, with GPT-5 excelling in physical reasoning, while geometry remains the most challenging domain. Overall, MMFormalizer provides a scalable framework for unified multimodal autoformalization, bridging perception and formal reasoning. To the best of our knowledge, this is the first multimodal autoformalization method capable of handling classical mechanics (derived from the Hamiltonian), as well as relativity, quantum mechanics, and thermodynamics. More details are available on our project page: MMFormalizer.github.io</p> + https://arxiv.org/abs/2601.03017 + Tue, 06 Jan 2026 13:42:51 +0000 - RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization - https://arxiv.org/abs/2601.00705 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00705.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei-Tse Cheng, Yen-Jen Chiou, Yuan-Fu Yang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce RGS-SLAM, a robust Gaussian-splatting SLAM framework that replaces the residual-driven densification stage of GS-SLAM with a training-free correspondence-to-Gaussian initialization. Instead of progressively adding Gaussians as residuals reveal missing geometry, RGS-SLAM performs a one-shot triangulation of dense multi-view correspondences derived from DINOv3 descriptors refined through a confidence-aware inlier classifier, generating a well-distributed and structure-aware Gaussian seed prior to optimization. This initialization stabilizes early mapping and accelerates convergence by roughly 20\%, yielding higher rendering fidelity in texture-rich and cluttered scenes while remaining fully compatible with existing GS-SLAM pipelines. Evaluated on the TUM RGB-D and Replica datasets, RGS-SLAM achieves competitive or superior localization and reconstruction accuracy compared with state-of-the-art Gaussian and point-based SLAM systems, sustaining real-time mapping performance at up to 925 FPS.</p> - https://arxiv.org/abs/2601.00705 - Sun, 28 Dec 2025 03:45:57 +0000 + CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature + https://arxiv.org/abs/2601.03319 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03319.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eldad Matmon, Amit Bracha, Noam Rotstein, Ron Kimmel</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> A photorealistic and controllable 3D caricaturization framework for faces is introduced. We start with an intrinsic Gaussian curvature-based surface exaggeration technique, which, when coupled with texture, tends to produce over-smoothed renders. To address this, we resort to 3D Gaussian Splatting (3DGS), which has recently been shown to produce realistic free-viewpoint avatars. Given a multiview sequence, we extract a FLAME mesh, solve a curvature-weighted Poisson equation, and obtain its exaggerated form. However, directly deforming the Gaussians yields poor results, necessitating the synthesis of pseudo-ground-truth caricature images by warping each frame to its exaggerated 2D representation using local affine transformations. We then devise a training scheme that alternates real and synthesized supervision, enabling a single Gaussian collection to represent both natural and exaggerated avatars. This scheme improves fidelity, supports local edits, and allows continuous control over the intensity of the caricature. In order to achieve real-time deformations, an efficient interpolation between the original and exaggerated surfaces is introduced. We further analyze and show that it has a bounded deviation from closed-form solutions. In both quantitative and qualitative evaluations, our results outperform prior work, delivering photorealistic, geometry-controlled caricature avatars.</p> + https://arxiv.org/abs/2601.03319 + Tue, 06 Jan 2026 13:56:28 +0000 - Diversity or Precision? A Deep Dive into Next Token Prediction - https://arxiv.org/abs/2512.22955 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyuan Wu, Hai Wang, Jiajia Wu, Jinxiang Ou, Keyao Wang, Weile Chen, Zihao Zheng, Bei Yu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space defined by the pre-trained model's token-output distribution. In this paper, we revisit the standard cross-entropy loss, interpreting it as a specific instance of policy gradient optimization applied within a single-step episode. To systematically study how the pre-trained distribution shapes the exploration potential for subsequent RL, we propose a generalized pre-training objective that adapts on-policy RL principles to supervised learning. By framing next-token prediction as a stochastic decision process, we introduce a reward-shaping strategy that explicitly balances diversity and precision. Our method employs a positive reward scaling factor to control probability concentration on ground-truth tokens and a rank-aware mechanism that treats high-ranking and low-ranking negative tokens asymmetrically. This allows us to reshape the pre-trained token-output distribution and investigate how to provide a more favorable exploration space for RL, ultimately enhancing end-to-end reasoning performance. Contrary to the intuition that higher distribution entropy facilitates effective exploration, we find that imposing a precision-oriented prior yields a superior exploration space for RL.</p> - https://arxiv.org/abs/2512.22955 - Sun, 28 Dec 2025 14:53:24 +0000 + What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models + https://arxiv.org/abs/2601.06165 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06165.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dasol Choi, Guijin Son, Hanwool Lee, Minhyuk Kim, Hyunwoo Ko, Teabin Lim, Ahn Eungyeol, Jungwhan Kim, Seunghyeok Hong, Youngsook Song</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Current vision-language benchmarks predominantly feature well-structured questions with clear, explicit prompts. However, real user queries are often informal and underspecified. Users naturally leave much unsaid, relying on images to convey context. We introduce HAERAE-Vision, a benchmark of 653 real-world visual questions from Korean online communities (0.76% survival from 86K candidates), each paired with an explicit rewrite, yielding 1,306 query variants in total. Evaluating 39 VLMs, we find that even state-of-the-art models (GPT-5, Gemini 2.5 Pro) achieve under 50% on the original queries. Crucially, query explicitation alone yields 8 to 22 point improvements, with smaller models benefiting most. We further show that even with web search, under-specified queries underperform explicit queries without search, revealing that current retrieval cannot compensate for what users leave unsaid. Our findings demonstrate that a substantial portion of VLM difficulty stem from natural query under-specification instead of model capability, highlighting a critical gap between benchmark evaluation and real-world deployment.</p> + https://arxiv.org/abs/2601.06165 + Wed, 07 Jan 2026 02:33:03 +0000 - Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion - https://arxiv.org/abs/2512.23035 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23035.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Zhou, Xuechao Zou, Shun Zhang, Kai Li, Shiying Wang, Jingming Chen, Congyan Lang, Tengfei Cao, Pin Tao, Yuanchun Shi</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Semi-supervised remote sensing (RS) image semantic segmentation offers a promising solution to alleviate the burden of exhaustive annotation, yet it fundamentally struggles with pseudo-label drift, a phenomenon where confirmation bias leads to the accumulation of errors during training. In this work, we propose Co2S, a stable semi-supervised RS segmentation framework that synergistically fuses priors from vision-language models and self-supervised models. Specifically, we construct a heterogeneous dual-student architecture comprising two distinct ViT-based vision foundation models initialized with pretrained CLIP and DINOv3 to mitigate error accumulation and pseudo-label drift. To effectively incorporate these distinct priors, an explicit-implicit semantic co-guidance mechanism is introduced that utilizes text embeddings and learnable queries to provide explicit and implicit class-level guidance, respectively, thereby jointly enhancing semantic consistency. Furthermore, a global-local feature collaborative fusion strategy is developed to effectively fuse the global contextual information captured by CLIP with the local details produced by DINOv3, enabling the model to generate highly precise segmentation results. Extensive experiments on six popular datasets demonstrate the superiority of the proposed method, which consistently achieves leading performance across various partition protocols and diverse scenarios. Project page is available at https://xavierjiezou.github.io/Co2S/.</p> - https://arxiv.org/abs/2512.23035 - Sun, 28 Dec 2025 18:24:19 +0000 + FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection + https://arxiv.org/abs/2601.03928 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03928.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyu Ouyang, Kevin Qinghong Lin, Mike Zheng Shou, Hwee Tou Ng</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Vision-Language Models (VLMs) have shown remarkable performance in User Interface (UI) grounding tasks, driven by their ability to process increasingly high-resolution screenshots. However, screenshots are tokenized into thousands of visual tokens (e.g., about 4700 for 2K resolution), incurring significant computational overhead and diluting attention. In contrast, humans typically focus on regions of interest when interacting with UI. In this work, we pioneer the task of efficient UI grounding. Guided by practical analysis of the task's characteristics and challenges, we propose FocusUI, an efficient UI grounding framework that selects patches most relevant to the instruction while preserving positional continuity for precise grounding. FocusUI addresses two key challenges: (1) Eliminating redundant tokens in visual encoding. We construct patch-level supervision by fusing an instruction-conditioned score with a rule-based UI-graph score that down-weights large homogeneous regions to select distinct and instruction-relevant visual tokens. (2) Preserving positional continuity during visual token selection. We find that general visual token pruning methods suffer from severe accuracy degradation on UI grounding tasks due to broken positional information. We introduce a novel PosPad strategy, which compresses each contiguous sequence of dropped visual tokens into a single special marker placed at the sequence's last index to preserve positional continuity. Comprehensive experiments on four grounding benchmarks demonstrate that FocusUI surpasses GUI-specific baselines. On the ScreenSpot-Pro benchmark, FocusUI-7B achieves a performance improvement of 3.7% over GUI-Actor-7B. Even with only 30% visual token retention, FocusUI-7B drops by only 3.2% while achieving up to 1.44x faster inference and 17% lower peak GPU memory.</p> + https://arxiv.org/abs/2601.03928 + Wed, 07 Jan 2026 13:48:12 +0000 - MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning - https://arxiv.org/abs/2512.23412 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23412.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Chen, Xintian Shen, Lihao Zheng, Zhenwei Shao, Hongyuan Zhang, Pengfei Yu, Xudong Rao, Ning Mao, Xiaobo Liu, Lian Wen, Chaoqun Du, Feng Gu, Wei He, Qizhen Li, Shanshan Li, Zide Liu, Jing Luo, Lifu Mu, Xuhao Pan, Chang Ren, Haoyi Sun, Qian Wang, Wei Wang, Hongfu Yang, Jiqing Zhan, Chunpeng Zhou, Zheng Zhou, Hao Ma, Tao Wei, Pan Zhou, Wei Chen</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of autonomous reasoning and tool invocation are rapidly emerging as a powerful approach for complex decision-making tasks involving multi-step interactions with external environments. In this work, we introduce MindWatcher, a TIR agent integrating interleaved thinking and multimodal chain-of-thought (CoT) reasoning. MindWatcher can autonomously decide whether and how to invoke diverse tools and coordinate their use, without relying on human prompts or workflows. The interleaved thinking paradigm enables the model to switch between thinking and tool calling at any intermediate stage, while its multimodal CoT capability allows manipulation of images during reasoning to yield more precise search results. We implement automated data auditing and evaluation pipelines, complemented by manually curated high-quality datasets for training, and we construct a benchmark, called MindWatcher-Evaluate Bench (MWE-Bench), to evaluate its performance. MindWatcher is equipped with a comprehensive suite of auxiliary reasoning tools, enabling it to address broad-domain multimodal problems. A large-scale, high-quality local image retrieval database, covering eight categories including cars, animals, and plants, endows model with robust object recognition despite its small size. Finally, we design a more efficient training infrastructure for MindWatcher, enhancing training speed and hardware utilization. Experiments not only demonstrate that MindWatcher matches or exceeds the performance of larger or more recent models through superior tool invocation, but also uncover critical insights for agent training, such as the genetic inheritance phenomenon in agentic RL.</p> - https://arxiv.org/abs/2512.23412 - Mon, 29 Dec 2025 12:16:12 +0000 + Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization + https://arxiv.org/abs/2601.04582 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04582.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mizanur Rahman, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Shafiq Joty, Enamul Hoque</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Text-to-Visualization (Text2Vis) systems translate natural language queries over tabular data into concise answers and executable visualizations. While closed-source LLMs generate functional code, the resulting charts often lack semantic alignment and clarity, qualities that can only be assessed post-execution. Open-source models struggle even more, frequently producing non-executable or visually poor outputs. Although supervised fine-tuning can improve code executability, it fails to enhance overall visualization quality, as traditional SFT loss cannot capture post-execution feedback. To address this gap, we propose RL-Text2Vis, the first reinforcement learning framework for Text2Vis generation. Built on Group Relative Policy Optimization (GRPO), our method uses a novel multi-objective reward that jointly optimizes textual accuracy, code validity, and visualization quality using post-execution feedback. By training Qwen2.5 models (7B and 14B), RL-Text2Vis achieves a 22% relative improvement in chart quality over GPT-4o on the Text2Vis benchmark and boosts code execution success from 78% to 97% relative to its zero-shot baseline. Our models significantly outperform strong zero-shot and supervised baselines and also demonstrate robust generalization to out-of-domain datasets like VIS-Eval and NVBench. These results establish GRPO as an effective strategy for structured, multimodal reasoning in visualization generation. We release our code at https://github.com/vis-nlp/RL-Text2Vis.</p> + https://arxiv.org/abs/2601.04582 + Thu, 08 Jan 2026 04:29:07 +0000 - Memorization in 3D Shape Generation: An Empirical Study - https://arxiv.org/abs/2512.23628 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23628.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shu Pu, Boya Zeng, Kaichen Zhou, Mengyu Wang, Zhuang Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Generative models are increasingly used in 3D vision to synthesize novel shapes, yet it remains unclear whether their generation relies on memorizing training shapes. Understanding their memorization could help prevent training data leakage and improve the diversity of generated results. In this paper, we design an evaluation framework to quantify memorization in 3D generative models and study the influence of different data and modeling designs on memorization. We first apply our framework to quantify memorization in existing methods. Next, through controlled experiments with a latent vector-set (Vecset) diffusion model, we find that, on the data side, memorization depends on data modality, and increases with data diversity and finer-grained conditioning; on the modeling side, it peaks at a moderate guidance scale and can be mitigated by longer Vecsets and simple rotation augmentation. Together, our framework and analysis provide an empirical understanding of memorization in 3D generative models and suggest simple yet effective strategies to reduce it without degrading generation quality. Our code is available at https://github.com/zlab-princeton/3d_mem.</p> - https://arxiv.org/abs/2512.23628 - Mon, 29 Dec 2025 17:39:21 +0000 + TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning + https://arxiv.org/abs/2601.04698 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04698.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinuo Wang, Mining Tan, Wenxiang Jiao, Xiaoxi Li, Hao Wang, Xuanyu Zhang, Yuan Lu, Weiming Dong</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Travel planning is a sophisticated decision-making process that requires synthesizing multifaceted information to construct itineraries. However, existing travel planning approaches face several challenges: (1) Pruning candidate points of interest (POIs) while maintaining a high recall rate; (2) A single reasoning path restricts the exploration capability within the feasible solution space for travel planning; (3) Simultaneously optimizing hard constraints and soft constraints remains a significant difficulty. To address these challenges, we propose TourPlanner, a comprehensive framework featuring multi-path reasoning and constraint-gated reinforcement learning. Specifically, we first introduce a Personalized Recall and Spatial Optimization (PReSO) workflow to construct spatially-aware candidate POIs' set. Subsequently, we propose Competitive consensus Chain-of-Thought (CCoT), a multi-path reasoning paradigm that improves the ability of exploring the feasible solution space. To further refine the plan, we integrate a sigmoid-based gating mechanism into the reinforcement learning stage, which dynamically prioritizes soft-constraint satisfaction only after hard constraints are met. Experimental results on travel planning benchmarks demonstrate that TourPlanner achieves state-of-the-art performance, significantly surpassing existing methods in both feasibility and user-preference alignment.</p> + https://arxiv.org/abs/2601.04698 + Thu, 08 Jan 2026 08:08:35 +0000 - GARDO: Reinforcing Diffusion Models without Reward Hacking - https://arxiv.org/abs/2512.24138 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24138.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran He, Yuxiao Ye, Jie Liu, Jiajun Liang, Zhiyong Wang, Ziyang Yuan, Xintao Wang, Hangyu Mao, Pengfei Wan, Ling Pan</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment. However, since precisely specifying a ground-truth objective for visual tasks remains challenging, the models are often optimized using a proxy reward that only partially captures the true goal. This mismatch often leads to reward hacking, where proxy scores increase while real image quality deteriorates and generation diversity collapses. While common solutions add regularization against the reference policy to prevent reward hacking, they compromise sample efficiency and impede the exploration of novel, high-reward regions, as the reference policy is usually sub-optimal. To address the competing demands of sample efficiency, effective exploration, and mitigation of reward hacking, we propose Gated and Adaptive Regularization with Diversity-aware Optimization (GARDO), a versatile framework compatible with various RL algorithms. Our key insight is that regularization need not be applied universally; instead, it is highly effective to selectively penalize a subset of samples that exhibit high uncertainty. To address the exploration challenge, GARDO introduces an adaptive regularization mechanism wherein the reference model is periodically updated to match the capabilities of the online policy, ensuring a relevant regularization target. To address the mode collapse issue in RL, GARDO amplifies the rewards for high-quality samples that also exhibit high diversity, encouraging mode coverage without destabilizing the optimization process. Extensive experiments across diverse proxy rewards and hold-out unseen metrics consistently show that GARDO mitigates reward hacking and enhances generation diversity without sacrificing sample efficiency or exploration, highlighting its effectiveness and robustness.</p> - https://arxiv.org/abs/2512.24138 - Tue, 30 Dec 2025 10:55:45 +0000 + Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking + https://arxiv.org/abs/2601.04720 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04720.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingxin Li, Yanzhao Zhang, Dingkun Long, Keqin Chen, Sibo Song, Shuai Bai, Zhibo Yang, Pengjun Xie, An Yang, Dayiheng Liu, Jingren Zhou, Junyang Lin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> In this report, we introduce the Qwen3-VL-Embedding and Qwen3-VL-Reranker model series, the latest extensions of the Qwen family built on the Qwen3-VL foundation model. Together, they provide an end-to-end pipeline for high-precision multimodal search by mapping diverse modalities, including text, images, document images, and video, into a unified representation space. The Qwen3-VL-Embedding model employs a multi-stage training paradigm, progressing from large-scale contrastive pre-training to reranking model distillation, to generate semantically rich high-dimensional vectors. It supports Matryoshka Representation Learning, enabling flexible embedding dimensions, and handles inputs up to 32k tokens. Complementing this, Qwen3-VL-Reranker performs fine-grained relevance estimation for query-document pairs using a cross-encoder architecture with cross-attention mechanisms. Both model series inherit the multilingual capabilities of Qwen3-VL, supporting more than 30 languages, and are released in 2B and 8B parameter sizes to accommodate diverse deployment requirements. Empirical evaluations demonstrate that the Qwen3-VL-Embedding series achieves state-of-the-art results across diverse multimodal embedding evaluation benchmarks. Specifically, Qwen3-VL-Embedding-8B attains an overall score of 77.8 on MMEB-V2, ranking first among all models (as of January 8, 2025). This report presents the architecture, training methodology, and practical capabilities of the series, demonstrating their effectiveness on various multimodal retrieval tasks, including image-text retrieval, visual question answering, and video-text matching.</p> + https://arxiv.org/abs/2601.04720 + Thu, 08 Jan 2026 08:36:06 +0000 - Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning - https://arxiv.org/abs/2512.24146 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24146.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chubin Chen, Sujie Hu, Jiashu Zhu, Meiqi Wu, Jintao Chen, Yanxun Li, Nisha Huang, Chengyu Fang, Jiahong Wu, Xiangxiang Chu, Xiu Li</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, while existing methods achieve high scores on automated reward metrics, they often lead to Preference Mode Collapse (PMC)-a specific form of reward hacking where models converge on narrow, high-scoring outputs (e.g., images with monolithic styles or pervasive overexposure), severely degrading generative diversity. In this work, we introduce and quantify this phenomenon, proposing DivGenBench, a novel benchmark designed to measure the extent of PMC. We posit that this collapse is driven by over-optimization along the reward model's inherent biases. Building on this analysis, we propose Directional Decoupling Alignment (D^2-Align), a novel framework that mitigates PMC by directionally correcting the reward signal. Specifically, our method first learns a directional correction within the reward model's embedding space while keeping the model frozen. This correction is then applied to the reward signal during the optimization process, preventing the model from collapsing into specific modes and thereby maintaining diversity. Our comprehensive evaluation, combining qualitative analysis with quantitative metrics for both quality and diversity, reveals that D^2-Align achieves superior alignment with human preference.</p> - https://arxiv.org/abs/2512.24146 - Tue, 30 Dec 2025 11:17:52 +0000 + KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions + https://arxiv.org/abs/2601.04745 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tingyu Wu, Zhisheng Chen, Ziyan Weng, Shuhe Wang, Chenglong Li, Shuo Zhang, Sen Hu, Silin Wu, Qizhen Lan, Huacan Wang, Ronghao Chen</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding. We present \BenchName, a publicly releasable benchmark built from long-form autobiographical narratives, where actions, context, and inner thoughts provide dense evidence for inferring stable motivations and decision principles. \BenchName~reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning. Across diverse narrative sources, retrieval-augmented systems mainly improve factual accuracy, while errors persist on temporally grounded explanations and higher-level inferences, highlighting the need for memory mechanisms beyond retrieval. Our data is in KnowMeBench{https://github.com/QuantaAlpha/KnowMeBench}.</p> + https://arxiv.org/abs/2601.04745 + Thu, 08 Jan 2026 09:11:33 +0000 - Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset - https://arxiv.org/abs/2512.24160 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> TsaiChing Ni, ZhenQi Chen, YuanFu Yang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We present IMDD-1M, the first large-scale Industrial Multimodal Defect Dataset comprising 1,000,000 aligned image-text pairs, designed to advance multimodal learning for manufacturing and quality inspection. IMDD-1M contains high-resolution real-world defects spanning over 60 material categories and more than 400 defect types, each accompanied by expert-verified annotations and fine-grained textual descriptions detailing defect location, severity, and contextual attributes. This dataset enables a wide spectrum of applications, including classification, segmentation, retrieval, captioning, and generative modeling. Building upon IMDD-1M, we train a diffusion-based vision-language foundation model from scratch, specifically tailored for industrial scenarios. The model serves as a generalizable foundation that can be efficiently adapted to specialized domains through lightweight fine-tuning. With less than 5% of the task-specific data required by dedicated expert models, it achieves comparable performance, highlighting the potential of data-efficient foundation model adaptation for industrial inspection and generation, paving the way for scalable, domain-adaptive, and knowledge-grounded manufacturing intelligence.</p> - https://arxiv.org/abs/2512.24160 - Tue, 30 Dec 2025 11:45:22 +0000 + AgentOCR: Reimagining Agent History via Optical Self-Compression + https://arxiv.org/abs/2601.04786 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lang Feng, Fuchao Yang, Feng Chen, Xin Cheng, Haiyang Xu, Zhenglin Wan, Ming Yan, Bo An</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction trajectories, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token budgets and memory usage. We introduce AgentOCR, a framework that exploits the superior information density of visual tokens by representing the accumulated observation-action history as a compact rendered image. To make multi-turn rollouts scalable, AgentOCR proposes segment optical caching. By decomposing history into hashable segments and maintaining a visual cache, this mechanism eliminates redundant re-rendering. Beyond fixed rendering, AgentOCR introduces agentic self-compression, where the agent actively emits a compression rate and is trained with compression-aware reward to adaptively balance task success and token efficiency. We conduct extensive experiments on challenging agentic benchmarks, ALFWorld and search-based QA. Remarkably, results demonstrate that AgentOCR preserves over 95\% of text-based agent performance while substantially reducing token consumption (>50\%), yielding consistent token and memory efficiency. Our further analysis validates a 20x rendering speedup from segment optical caching and the effective strategic balancing of self-compression.</p> + https://arxiv.org/abs/2601.04786 + Thu, 08 Jan 2026 10:10:20 +0000 - Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation - https://arxiv.org/abs/2512.24271 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24271.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhe Huang, Hao Wen, Aiming Hao, Bingze Song, Meiqi Wu, Jiahong Wu, Xiangxiang Chu, Sheng Lu, Haoqian Wang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have made remarkable progress in video understanding. However, they suffer from a critical vulnerability: an over-reliance on language priors, which can lead to visual ungrounded hallucinations, especially when processing counterfactual videos that defy common sense. This limitation, stemming from the intrinsic data imbalance between text and video, is challenging to address due to the substantial cost of collecting and annotating counterfactual data. To address this, we introduce DualityForge, a novel counterfactual data synthesis framework that employs controllable, diffusion-based video editing to transform real-world videos into counterfactual scenarios. By embedding structured contextual information into the video editing and QA generation processes, the framework automatically produces high-quality QA pairs together with original-edited video pairs for contrastive training. Based on this, we build DualityVidQA, a large-scale video dataset designed to reduce MLLM hallucinations. In addition, to fully exploit the contrastive nature of our paired data, we propose Duality-Normalized Advantage Training (DNA-Train), a two-stage SFT-RL training regime where the RL phase applies pair-wise ell_1 advantage normalization, thereby enabling a more stable and efficient policy optimization. Experiments on DualityVidQA-Test demonstrate that our method substantially reduces model hallucinations on counterfactual videos, yielding a relative improvement of 24.0% over the Qwen2.5-VL-7B baseline. Moreover, our approach achieves significant gains across both hallucination and general-purpose benchmarks, indicating strong generalization capability. We will open-source our dataset and code.</p> - https://arxiv.org/abs/2512.24271 - Tue, 30 Dec 2025 14:53:33 +0000 + SmartSearch: Process Reward-Guided Query Refinement for Search Agents + https://arxiv.org/abs/2601.04888 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04888.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tongyu Wen, Guanting Dong, Zhicheng Dou</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of search agents, yet the quality of intermediate search queries during reasoning remains overlooked. As a result, the generated queries often remain inaccurate, leading to unexpected retrieval results and ultimately limiting search agents' overall effectiveness. To mitigate this issue, we introduce SmartSearch, a framework built upon two key mechanisms: (1) Process rewards, which provide fine-grained supervision for the quality of each intermediate search query through Dual-Level Credit Assessment. (2) Query refinement, which promotes the optimization of query generation by selectively refining low-quality search queries and regenerating subsequent search rounds based on these refinements. To enable the search agent to progressively internalize the ability to improve query quality under the guidance of process rewards, we design a three-stage curriculum learning framework. This framework guides the agent through a progression from imitation, to alignment, and ultimately to generalization. Experimental results show that SmartSearch consistently surpasses existing baselines, and additional quantitative analyses further confirm its significant gains in both search efficiency and query quality. The code is available at https://github.com/MYVAE/SmartSearch.</p> + https://arxiv.org/abs/2601.04888 + Thu, 08 Jan 2026 12:39:05 +0000 - SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning - https://arxiv.org/abs/2512.24330 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yong Xien Chng, Tao Hu, Wenwen Tong, Xueheng Li, Jiandong Chen, Haojia Yu, Jiefan Lu, Hewei Guo, Hanming Deng, Chengjun Xie, Gao Huang, Dahua Lin, Lewei Lu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> While Vision-Language Models (VLMs) can solve complex tasks through agentic reasoning, their capabilities remain largely constrained to text-oriented chain-of-thought or isolated tool invocation. They fail to exhibit the human-like proficiency required to seamlessly interleave dynamic tool manipulation with continuous reasoning, particularly in knowledge-intensive and visually complex scenarios that demand coordinated external tools such as search and image cropping. In this work, we introduce SenseNova-MARS, a novel Multimodal Agentic Reasoning and Search framework that empowers VLMs with interleaved visual reasoning and tool-use capabilities via reinforcement learning (RL). Specifically, SenseNova-MARS dynamically integrates the image search, text search, and image crop tools to tackle fine-grained and knowledge-intensive visual understanding challenges. In the RL stage, we propose the Batch-Normalized Group Sequence Policy Optimization (BN-GSPO) algorithm to improve the training stability and advance the model's ability to invoke tools and reason effectively. To comprehensively evaluate the agentic VLMs on complex visual tasks, we introduce the HR-MMSearch benchmark, the first search-oriented benchmark composed of high-resolution images with knowledge-intensive and search-driven questions. Experiments demonstrate that SenseNova-MARS achieves state-of-the-art performance on open-source search and fine-grained image understanding benchmarks. Specifically, on search-oriented benchmarks, SenseNova-MARS-8B scores 67.84 on MMSearch and 41.64 on HR-MMSearch, surpassing proprietary models such as Gemini-3-Flash and GPT-5. SenseNova-MARS represents a promising step toward agentic VLMs by providing effective and robust tool-use capabilities. To facilitate further research in this field, we will release all code, models, and datasets.</p> - https://arxiv.org/abs/2512.24330 - Tue, 30 Dec 2025 16:31:45 +0000 + Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction + https://arxiv.org/abs/2601.05107 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05107.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muzhao Tian, Zisu Huang, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Yuanzhe Shen, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to memory usage: incorporating all relevant past information can lead to Memory Anchoring, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose Steerable Memory Agent, SteeM, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.</p> + https://arxiv.org/abs/2601.05107 + Thu, 08 Jan 2026 16:54:30 +0000 - Recursive Language Models - https://arxiv.org/abs/2512.24601 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24601.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alex L. Zhang, Tim Kraska, Omar Khattab</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference strategy that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs successfully handle inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of base LLMs and common long-context scaffolds across four diverse long-context tasks, while having comparable (or cheaper) cost per query.</p> - https://arxiv.org/abs/2512.24601 - Wed, 31 Dec 2025 03:43:41 +0000 + GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts + https://arxiv.org/abs/2601.05110 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05110.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhao Zeng, Xuteng Zhang, Yuling Shi, Chao Hu, Yuting Chen, Beijun Shen, Xiaodong Gu</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and computational cost. Collaborative inference offers a promising solution by selectively allocating work between lightweight and large models, yet a fundamental challenge remains: determining when a reasoning step requires the capacity of a large model or the efficiency of a small model. Existing routing strategies either rely on local token probabilities or post-hoc verification, introducing significant inference overhead. In this work, we propose a novel perspective on step-wise collaboration: the difficulty of a reasoning step can be inferred from its very first token. Inspired by the "Aha Moment" phenomenon in LRMs, we show that the entropy of the initial token serves as a strong predictor of step difficulty. Building on this insight, we introduce GlimpRouter, a training-free step-wise collaboration framework. GlimpRouter employs a lightweight model to generate only the first token of each reasoning step and routes the step to a larger model only when the initial token entropy exceeds a threshold. Experiments on multiple benchmarks demonstrate that our approach significantly reduces inference latency while preserving accuracy. For instance, GlimpRouter attains a substantial 10.7% improvement in accuracy while reducing inference latency by 25.9% compared to a standalone large model on AIME25. These results suggest a simple yet effective mechanism for reasoning: allocating computation based on a glimpse of thought rather than full-step evaluation.</p> + https://arxiv.org/abs/2601.05110 + Thu, 08 Jan 2026 16:58:07 +0000 - Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization - https://arxiv.org/abs/2512.24615 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24615.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Shi, Yuzheng Cai, Siqi Cai, Zihan Xu, Lichao Chen, Yulei Qin, Zhijian Zhou, Xiang Fei, Chaofan Qiu, Xiaoyu Tan, Gang Li, Zongyi Li, Haojia Lin, Guocan Cai, Yong Mao, Yunsheng Wu, Ke Li, Xing Sun</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> Existing Large Language Model (LLM) agent frameworks face two significant challenges: high configuration costs and static capabilities. Building a high-quality agent often requires extensive manual effort in tool integration and prompt engineering, while deployed agents struggle to adapt to dynamic environments without expensive fine-tuning. To address these issues, we propose Youtu-Agent, a modular framework designed for the automated generation and continuous evolution of LLM agents. Youtu-Agent features a structured configuration system that decouples execution environments, toolkits, and context management, enabling flexible reuse and automated synthesis. We introduce two generation paradigms: a Workflow mode for standard tasks and a Meta-Agent mode for complex, non-standard requirements, capable of automatically generating tool code, prompts, and configurations. Furthermore, Youtu-Agent establishes a hybrid policy optimization system: (1) an Agent Practice module that enables agents to accumulate experience and improve performance through in-context optimization without parameter updates; and (2) an Agent RL module that integrates with distributed training frameworks to enable scalable and stable reinforcement learning of any Youtu-Agents in an end-to-end, large-scale manner. Experiments demonstrate that Youtu-Agent achieves state-of-the-art performance on WebWalkerQA (71.47\%) and GAIA (72.8\%) using open-weight models. Our automated generation pipeline achieves over 81\% tool synthesis success rate, while the Practice module improves performance on AIME 2024/2025 by +2.7\% and +5.4\% respectively. Moreover, our Agent RL training achieves 40\% speedup with steady performance improvement on 7B LLMs, enhancing coding/reasoning and searching capabilities respectively up to 35\% and 21\% on Maths and general/multi-hop QA benchmarks.</p> - https://arxiv.org/abs/2512.24615 - Wed, 31 Dec 2025 04:17:36 +0000 + Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection + https://arxiv.org/abs/2601.05403 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05403.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiwei Liu, Yupen Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Tariquzzaman Faisal, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Mingbin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large language models (LLMs) have been widely applied across various domains of finance. Since their training data are largely derived from human-authored corpora, LLMs may inherit a range of human biases. Behavioral biases can lead to instability and uncertainty in decision-making, particularly when processing financial information. However, existing research on LLM bias has mainly focused on direct questioning or simplified, general-purpose settings, with limited consideration of the complex real-world financial environments and high-risk, context-sensitive, multilingual financial misinformation detection tasks (\mfmd). In this work, we propose \mfmdscen, a comprehensive benchmark for evaluating behavioral biases of LLMs in \mfmd across diverse economic scenarios. In collaboration with financial experts, we construct three types of complex financial scenarios: (i) role- and personality-based, (ii) role- and region-based, and (iii) role-based scenarios incorporating ethnicity and religious beliefs. We further develop a multilingual financial misinformation dataset covering English, Chinese, Greek, and Bengali. By integrating these scenarios with misinformation claims, \mfmdscen enables a systematic evaluation of 22 mainstream LLMs. Our findings reveal that pronounced behavioral biases persist across both commercial and open-source models. This project will be available at https://github.com/lzw108/FMD.</p> + https://arxiv.org/abs/2601.05403 + Thu, 08 Jan 2026 22:00:32 +0000 - Nested Learning: The Illusion of Deep Learning Architectures - https://arxiv.org/abs/2512.24695 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24695.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Behrouz, Meisam Razaviyayn, Peilin Zhong, Vahab Mirrokni</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Despite the recent progresses, particularly in developing Language Models, there are fundamental challenges and unanswered questions about how such models can continually learn/memorize, self-improve, and find effective solutions. In this paper, we present a new learning paradigm, called Nested Learning (NL), that coherently represents a machine learning model with a set of nested, multi-level, and/or parallel optimization problems, each of which with its own context flow. Through the lenses of NL, existing deep learning methods learns from data through compressing their own context flow, and in-context learning naturally emerges in large models. NL suggests a philosophy to design more expressive learning algorithms with more levels, resulting in higher-order in-context learning and potentially unlocking effective continual learning capabilities. We advocate for NL by presenting three core contributions: (1) Expressive Optimizers: We show that known gradient-based optimizers, such as Adam, SGD with Momentum, etc., are in fact associative memory modules that aim to compress the gradients' information (by gradient descent). Building on this insight, we present other more expressive optimizers with deep memory and/or more powerful learning rules; (2) Self-Modifying Learning Module: Taking advantage of NL's insights on learning algorithms, we present a sequence model that learns how to modify itself by learning its own update algorithm; and (3) Continuum Memory System: We present a new formulation for memory system that generalizes the traditional viewpoint of long/short-term memory. Combining our self-modifying sequence model with the continuum memory system, we present a continual learning module, called Hope, showing promising results in language modeling, knowledge incorporation, and few-shot generalization tasks, continual learning, and long-context reasoning tasks.</p> - https://arxiv.org/abs/2512.24695 - Wed, 31 Dec 2025 07:59:43 +0000 + Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization + https://arxiv.org/abs/2601.05432 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05432.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Ji, Yong Wang, Ziyu Ma, Yiming Hu, Hailang Huang, Xuecai Hu, Guanhua Chen, Liaoni Wu, Xiangxiang Chu</p><p><b>Upvotes:</b> 159</p><p><b>Summary:</b> The image geolocalization task aims to predict the location where an image was taken anywhere on Earth using visual clues. Existing large vision-language model (LVLM) approaches leverage world knowledge, chain-of-thought reasoning, and agentic capabilities, but overlook a common strategy used by humans -- using maps. In this work, we first equip the model Thinking with Map ability and formulate it as an agent-in-the-map loop. We develop a two-stage optimization scheme for it, including agentic reinforcement learning (RL) followed by parallel test-time scaling (TTS). The RL strengthens the agentic capability of model to improve sampling efficiency, and the parallel TTS enables the model to explore multiple candidate paths before making the final prediction, which is crucial for geolocalization. To evaluate our method on up-to-date and in-the-wild images, we further present MAPBench, a comprehensive geolocalization training and evaluation benchmark composed entirely of real-world images. Experimental results show that our method outperforms existing open- and closed-source models on most metrics, specifically improving Acc@500m from 8.0\% to 22.1\% compared to Gemini-3-Pro with Google Search/Map grounded mode.</p> + https://arxiv.org/abs/2601.05432 + Thu, 08 Jan 2026 23:47:30 +0000 - MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing - https://arxiv.org/abs/2601.00204 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaokun Sun, Zeyu Cai, Hao Tang, Ying Tai, Jian Yang, Zhenyu Zhang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> 3D morphing remains challenging due to the difficulty of generating semantically consistent and temporally smooth deformations, especially across categories. We present MorphAny3D, a training-free framework that leverages Structured Latent (SLAT) representations for high-quality 3D morphing. Our key insight is that intelligently blending source and target SLAT features within the attention mechanisms of 3D generators naturally produces plausible morphing sequences. To this end, we introduce Morphing Cross-Attention (MCA), which fuses source and target information for structural coherence, and Temporal-Fused Self-Attention (TFSA), which enhances temporal consistency by incorporating features from preceding frames. An orientation correction strategy further mitigates the pose ambiguity within the morphing steps. Extensive experiments show that our method generates state-of-the-art morphing sequences, even for challenging cross-category cases. MorphAny3D further supports advanced applications such as decoupled morphing and 3D style transfer, and can be generalized to other SLAT-based generative models. Project page: https://xiaokunsun.github.io/MorphAny3D.github.io/.</p> - https://arxiv.org/abs/2601.00204 - Thu, 01 Jan 2026 04:42:59 +0000 + Orient Anything V2: Unifying Orientation and Rotation Understanding + https://arxiv.org/abs/2601.05573 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05573.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehan Wang, Ziang Zhang, Jiayang Xu, Jialei Wang, Tianyu Pang, Chao Du, HengShuang Zhao, Zhou Zhao</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> This work presents Orient Anything V2, an enhanced foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Building upon Orient Anything V1, which defines orientation via a single unique front face, V2 extends this capability to handle objects with diverse rotational symmetries and directly estimate relative rotations. These improvements are enabled by four key innovations: 1) Scalable 3D assets synthesized by generative models, ensuring broad category coverage and balanced data distribution; 2) An efficient, model-in-the-loop annotation system that robustly identifies 0 to N valid front faces for each object; 3) A symmetry-aware, periodic distribution fitting objective that captures all plausible front-facing orientations, effectively modeling object rotational symmetry; 4) A multi-frame architecture that directly predicts relative object rotations. Extensive experiments show that Orient Anything V2 achieves state-of-the-art zero-shot performance on orientation estimation, 6DoF pose estimation, and object symmetry recognition across 11 widely used benchmarks. The model demonstrates strong generalization, significantly broadening the applicability of orientation estimation in diverse downstream tasks.</p> + https://arxiv.org/abs/2601.05573 + Fri, 09 Jan 2026 06:43:59 +0000 - NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos - https://arxiv.org/abs/2601.00393 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00393.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxue Yang, Lue Fan, Ziqi Shi, Junran Peng, Feng Wang, Zhaoxiang Zhang</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> In this paper, we propose NeoVerse, a versatile 4D world model that is capable of 4D reconstruction, novel-trajectory video generation, and rich downstream applications. We first identify a common limitation of scalability in current 4D world modeling methods, caused either by expensive and specialized multi-view 4D data or by cumbersome training pre-processing. In contrast, our NeoVerse is built upon a core philosophy that makes the full pipeline scalable to diverse in-the-wild monocular videos. Specifically, NeoVerse features pose-free feed-forward 4D reconstruction, online monocular degradation pattern simulation, and other well-aligned techniques. These designs empower NeoVerse with versatility and generalization to various domains. Meanwhile, NeoVerse achieves state-of-the-art performance in standard reconstruction and generation benchmarks. Our project page is available at https://neoverse-4d.github.io</p> - https://arxiv.org/abs/2601.00393 - Thu, 01 Jan 2026 17:07:30 +0000 + PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning + https://arxiv.org/abs/2601.05593 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05593.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Daxin Jiang, Xiangyu Zhang, Heung-Yeung Shum</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> We introduce Parallel Coordinated Reasoning (PaCoRe), a training-and-inference framework designed to overcome a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. PaCoRe departs from the traditional sequential paradigm by driving TTC through massive parallel exploration coordinated via a message-passing architecture in multiple rounds. Each round launches many parallel reasoning trajectories, compacts their findings into context-bounded messages, and synthesizes these messages to guide the next round and ultimately produce the final answer. Trained end-to-end with large-scale, outcome-based reinforcement learning, the model masters the synthesis abilities required by PaCoRe and scales to multi-million-token effective TTC without exceeding context limits. The approach yields strong improvements across diverse domains, and notably pushes reasoning beyond frontier systems in mathematics: an 8B model reaches 94.5% on HMMT 2025, surpassing GPT-5's 93.2% by scaling effective TTC to roughly two million tokens. We open-source model checkpoints, training data, and the full inference pipeline to accelerate follow-up work.</p> + https://arxiv.org/abs/2601.05593 + Fri, 09 Jan 2026 07:24:43 +0000 - Deep Delta Learning - https://arxiv.org/abs/2601.00417 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00417.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Zhang, Yifeng Liu, Mengdi Wang, Quanquan Gu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The efficacy of deep residual networks is fundamentally predicated on the identity shortcut connection. While this mechanism effectively mitigates the vanishing gradient problem, it imposes a strictly additive inductive bias on feature transformations, thereby limiting the network's capacity to model complex state transitions. In this paper, we introduce Deep Delta Learning (DDL), a novel architecture that generalizes the standard residual connection by modulating the identity shortcut with a learnable, data-dependent geometric transformation. This transformation, termed the Delta Operator, constitutes a rank-1 perturbation of the identity matrix, parameterized by a reflection direction vector k(X) and a gating scalar β(X). We provide a spectral analysis of this operator, demonstrating that the gate β(X) enables dynamic interpolation between identity mapping, orthogonal projection, and geometric reflection. Furthermore, we restructure the residual update as a synchronous rank-1 injection, where the gate acts as a dynamic step size governing both the erasure of old information and the writing of new features. This unification empowers the network to explicitly control the spectrum of its layer-wise transition operator, enabling the modeling of complex, non-monotonic dynamics while preserving the stable training characteristics of gated residual architectures.</p> - https://arxiv.org/abs/2601.00417 - Thu, 01 Jan 2026 18:11:38 +0000 + EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis + https://arxiv.org/abs/2601.05808 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05808.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoshuai Song, Haofei Chang, Guanting Dong, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but this process relies on rich and varied tool-interaction sandboxes. However, access to real systems is often restricted; LLM-simulated environments are prone to hallucinations and inconsistencies; and manually built sandboxes are hard to scale. In this paper, we propose EnvScaler, an automated framework for scalable tool-interaction environments via programmatic synthesis. EnvScaler comprises two components. First, SkelBuilder constructs diverse environment skeletons through topic mining, logic modeling, and quality evaluation. Then, ScenGenerator generates multiple task scenarios and rule-based trajectory validation functions for each environment. With EnvScaler, we synthesize 191 environments and about 7K scenarios, and apply them to Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) for Qwen3 series models. Results on three benchmarks show that EnvScaler significantly improves LLMs' ability to solve tasks in complex environments involving multi-turn, multi-tool interactions. We release our code and data at https://github.com/RUC-NLPIR/EnvScaler.</p> + https://arxiv.org/abs/2601.05808 + Fri, 09 Jan 2026 14:32:06 +0000 - E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models - https://arxiv.org/abs/2601.00423 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00423.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengjun Zhang, Zhang Zhang, Chensheng Dai, Yueqi Duan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent reinforcement learning has enhanced the flow matching models on human preference alignment. While stochastic sampling enables the exploration of denoising directions, existing methods which optimize over multiple denoising steps suffer from sparse and ambiguous reward signals. We observe that the high entropy steps enable more efficient and effective exploration while the low entropy steps result in undistinguished roll-outs. To this end, we propose E-GRPO, an entropy aware Group Relative Policy Optimization to increase the entropy of SDE sampling steps. Since the integration of stochastic differential equations suffer from ambiguous reward signals due to stochasticity from multiple steps, we specifically merge consecutive low entropy steps to formulate one high entropy step for SDE sampling, while applying ODE sampling on other steps. Building upon this, we introduce multi-step group normalized advantage, which computes group-relative advantages within samples sharing the same consolidated SDE denoising step. Experimental results on different reward settings have demonstrated the effectiveness of our methods.</p> - https://arxiv.org/abs/2601.00423 - Thu, 01 Jan 2026 18:27:32 +0000 + Boosting Latent Diffusion Models via Disentangled Representation Alignment + https://arxiv.org/abs/2601.05823 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05823.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> John Page, Xuesong Niu, Kai Wu, Kun Gai</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Latent Diffusion Models (LDMs) generate high-quality images by operating in a compressed latent space, typically obtained through image tokenizers such as Variational Autoencoders (VAEs). In pursuit of a generation-friendly VAE, recent studies have explored leveraging Vision Foundation Models (VFMs) as representation alignment targets for VAEs, mirroring the approach commonly adopted for LDMs. Although this yields certain performance gains, using the same alignment target for both VAEs and LDMs overlooks their fundamentally different representational requirements. We advocate that while LDMs benefit from latents retaining high-level semantic concepts, VAEs should excel in semantic disentanglement, enabling encoding of attribute-level information in a structured way. To address this, we propose the Semantic disentangled VAE (Send-VAE), explicitly optimized for disentangled representation learning through aligning its latent space with the semantic hierarchy of pre-trained VFMs. Our approach employs a non-linear mapper network to transform VAE latents, aligning them with VFMs to bridge the gap between attribute-level disentanglement and high-level semantics, facilitating effective guidance for VAE learning. We evaluate semantic disentanglement via linear probing on attribute prediction tasks, showing strong correlation with improved generation performance. Finally, using Send-VAE, we train flow-based transformers SiTs; experiments show Send-VAE significantly speeds up training and achieves a state-of-the-art FID of 1.21 and 1.75 with and without classifier-free guidance on ImageNet 256x256.</p> + https://arxiv.org/abs/2601.05823 + Fri, 09 Jan 2026 14:54:30 +0000 - CPPO: Contrastive Perception for Vision Language Policy Optimization - https://arxiv.org/abs/2601.00501 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahmad Rezaei, Mohsen Gholami, Saeed Ranjbar Alvar, Kevin Cannons, Mohammad Asiful Hossain, Zhou Weimin, Shunbo Zhou, Yong Zhang, Mohammad Akbari</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce CPPO, a Contrastive Perception Policy Optimization method for finetuning vision-language models (VLMs). While reinforcement learning (RL) has advanced reasoning in language models, extending it to multimodal reasoning requires improving both the perception and reasoning aspects. Prior works tackle this challenge mainly with explicit perception rewards, but disentangling perception tokens from reasoning tokens is difficult, requiring extra LLMs, ground-truth data, forced separation of perception from reasoning by policy model, or applying rewards indiscriminately to all output tokens. CPPO addresses this problem by detecting perception tokens via entropy shifts in the model outputs under perturbed input images. CPPO then extends the RL objective function with a Contrastive Perception Loss (CPL) that enforces consistency under information-preserving perturbations and sensitivity under information-removing ones. Experiments show that CPPO surpasses previous perception-rewarding methods, while avoiding extra models, making training more efficient and scalable.</p> - https://arxiv.org/abs/2601.00501 - Thu, 01 Jan 2026 22:48:26 +0000 + Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals + https://arxiv.org/abs/2601.05848 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nate Gillman, Yinghua Zhou, Zitian Tang, Evan Luo, Arjan Chakravarthy, Daksh Aggarwal, Michael Freeman, Charles Herrmann, Chen Sun</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.</p> + https://arxiv.org/abs/2601.05848 + Fri, 09 Jan 2026 15:23:36 +0000 - InfoSynth: Information-Guided Benchmark Synthesis for LLMs - https://arxiv.org/abs/2601.00575 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ishir Garg, Neel Kolhe, Xuandong Zhao, Dawn Song</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation. However, efficiently creating new benchmarks to evaluate these capabilities remains a challenge. Traditional benchmark creation relies on manual human effort, a process that is both expensive and time-consuming. Furthermore, existing benchmarks often contaminate LLM training data, necessitating novel and diverse benchmarks to accurately assess their genuine capabilities. This work introduces InfoSynth, a novel framework for automatically generating and evaluating reasoning benchmarks guided by information-theoretic principles. We propose metrics based on KL-divergence and entropy to quantify benchmark novelty and diversity without relying on costly model evaluations. Building on this framework, we develop an end-to-end pipeline that synthesizes robust Python coding problems from seed datasets using genetic algorithms and iterative code feedback. Our method generates accurate test cases and solutions to new problems 97% of the time, and the synthesized benchmarks consistently exhibit higher novelty and diversity compared to their seed datasets. Moreover, our algorithm provides a method for controlling the novelty/diversity and difficulty of generated problems. InfoSynth offers a scalable, self-verifying pipeline for constructing high-quality, novel and diverse benchmarks for LLMs. Project Page: https://ishirgarg.github.io/infosynth_web/</p> - https://arxiv.org/abs/2601.00575 - Fri, 02 Jan 2026 05:26:27 +0000 + An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift + https://arxiv.org/abs/2601.05882 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference-tuning degrades performance and reduces helpfulness when evaluated outside the training domain. However, the extent to which adaptation strategies mitigate this domain shift remains unexplored. We address this challenge by conducting a comprehensive and systematic study of alignment generalization under domain shift. We compare five popular alignment objectives and various adaptation strategies from source to target, including target-domain supervised fine-tuning and pseudo-labeling, across summarization and question-answering helpfulness tasks. Our findings reveal systematic differences in generalization across alignment objectives under domain shift. We show that adaptation strategies based on pseudo-labeling can substantially reduce domain-shift degradation</p> + https://arxiv.org/abs/2601.05882 + Fri, 09 Jan 2026 15:56:55 +0000 - Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation - https://arxiv.org/abs/2601.00664 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taekyung Ki, Sangwon Jang, Jaehyeong Jo, Jaehong Yoon, Sung Ju Hwang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation. However, current models do not yet convey the feeling of truly interactive communication, often generating one-way responses that lack emotional engagement. We identify two key challenges toward truly interactive avatars: generating motion in real-time under causal constraints and learning expressive, vibrant reactions without additional labeled data. To address these challenges, we propose Avatar Forcing, a new framework for interactive head avatar generation that models real-time user-avatar interactions through diffusion forcing. This design allows the avatar to process real-time multimodal inputs, including the user's audio and motion, with low latency for instant reactions to both verbal and non-verbal cues such as speech, nods, and laughter. Furthermore, we introduce a direct preference optimization method that leverages synthetic losing samples constructed by dropping user conditions, enabling label-free learning of expressive interaction. Experimental results demonstrate that our framework enables real-time interaction with low latency (approximately 500ms), achieving 6.8X speedup compared to the baseline, and produces reactive and expressive avatar motion, which is preferred over 80% against the baseline.</p> - https://arxiv.org/abs/2601.00664 - Fri, 02 Jan 2026 11:58:48 +0000 + Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency + https://arxiv.org/abs/2601.05905 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05905.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely on point-wise confidence like Self-Consistency, which can mask brittle belief. We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference. To address this gap, we propose Neighbor-Consistency Belief (NCB), a structural measure of belief robustness that evaluates response coherence across a conceptual neighborhood. To validate the efficiency of NCB, we introduce a new cognitive stress-testing protocol that probes outputs stability under contextual interference. Experiments across multiple LLMs show that the performance of high-NCB data is relatively more resistant to interference. Finally, we present Structure-Aware Training (SAT), which optimizes context-invariant belief structure and reduces long-tail knowledge brittleness by approximately 30%. Code will be available at https://github.com/zjunlp/belief.</p> + https://arxiv.org/abs/2601.05905 + Fri, 09 Jan 2026 16:23:21 +0000 - Fast-weight Product Key Memory - https://arxiv.org/abs/2601.00671 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00671.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Zhao, Llion Jones</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Sequence modeling layers in modern language models typically face a trade-off between storage capacity and computational efficiency. While Softmax attention offers unbounded storage at prohibitive quadratic costs, linear variants provide efficiency but suffer from limited, fixed-size storage. We propose Fast-weight Product Key Memory (FwPKM), a novel architecture that resolves this tension by transforming the sparse Product Key Memory (PKM) from a static module into a dynamic, "fast-weight" episodic memory. Unlike PKM, FwPKM updates its parameters dynamically at both training and inference time via local chunk-level gradient descent, allowing the model to rapidly memorize and retrieve new key-value pairs from input sequences. Experiments reveal that FwPKM functions as an effective episodic memory that complements the semantic memory of standard modules, yielding significant perplexity reductions on long-context datasets. Notably, in Needle in a Haystack evaluations, FwPKM generalizes to 128K-token contexts despite being trained on only 4K-token sequences.</p> - https://arxiv.org/abs/2601.00671 - Fri, 02 Jan 2026 12:37:53 +0000 + Can We Predict Before Executing Machine Learning Agents? + https://arxiv.org/abs/2601.05930 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05930.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingsheng Zheng, Jintian Zhang, Yujie Luo, Yuren Mao, Yunjun Gao, Lun Du, Huajun Chen, Ningyu Zhang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass these physical constraints, we internalize execution priors to substitute costly runtime checks with instantaneous predictive reasoning, drawing inspiration from World Models. In this work, we formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons. We demonstrate that LLMs exhibit significant predictive capabilities when primed with a Verified Data Analysis Report, achieving 61.5% accuracy and robust confidence calibration. Finally, we instantiate this framework in FOREAGENT, an agent that employs a Predict-then-Verify loop, achieving a 6x acceleration in convergence while surpassing execution-based baselines by +6%. Our code and dataset will be publicly available soon at https://github.com/zjunlp/predict-before-execute.</p> + https://arxiv.org/abs/2601.05930 + Fri, 09 Jan 2026 16:44:17 +0000 - The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving - https://arxiv.org/abs/2601.00747 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Max Ruiz Luyten, Mihaela van der Schaar</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> State-of-the-art large language model (LLM) pipelines rely on bootstrapped reasoning loops: sampling diverse chains of thought and reinforcing the highest-scoring ones, mainly optimizing correctness. We analyze how this design choice is sensitive to the collapse of the model's distribution over reasoning paths, slashing semantic entropy and undermining creative problem-solving. To analyze this failure, we introduce Distributional Creative Reasoning (DCR), a unified variational objective that casts training as gradient flow through probability measures on solution traces. STaR, GRPO, and DPO, as well as entropy bonuses, and other methods, all constitute special cases of the same loss. The framework delivers three core results: (i) the diversity decay theorem, describing how correctness-based objectives lead to distinct modes of diversity decay for STaR, GRPO, and DPO; (ii) designs that ensure convergence to a stable and diverse policy, effectively preventing collapse; and (iii) simple, actionable recipes to achieve this in practice. DCR thus offers the first principled recipe for LLMs that remain both correct and creative.</p> - https://arxiv.org/abs/2601.00747 - Fri, 02 Jan 2026 17:10:31 +0000 + VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction + https://arxiv.org/abs/2601.05966 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Longbin Ji, Xiaoxiong Liu, Junyuan Shang, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first large-scale Visual Autoregressive (VAR) framework for video generation that combines multi-scale next-frame prediction with autoregressive modeling. VideoAR disentangles spatial and temporal dependencies by integrating intra-frame VAR modeling with causal next-frame prediction, supported by a 3D multi-scale tokenizer that efficiently encodes spatio-temporal dynamics. To improve long-term consistency, we propose Multi-scale Temporal RoPE, Cross-Frame Error Correction, and Random Frame Mask, which collectively mitigate error propagation and stabilize temporal coherence. Our multi-stage pretraining pipeline progressively aligns spatial and temporal learning across increasing resolutions and durations. Empirically, VideoAR achieves new state-of-the-art results among autoregressive models, improving FVD on UCF-101 from 99.5 to 88.6 while reducing inference steps by over 10x, and reaching a VBench score of 81.74-competitive with diffusion-based models an order of magnitude larger. These results demonstrate that VideoAR narrows the performance gap between autoregressive and diffusion paradigms, offering a scalable, efficient, and temporally consistent foundation for future video generation research.</p> + https://arxiv.org/abs/2601.05966 + Fri, 09 Jan 2026 17:34:59 +0000 - AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction - https://arxiv.org/abs/2601.00796 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.00796.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiewen Chan, Zhenjun Zhao, Yu-Lun Liu</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Reconstructing dynamic 3D scenes from monocular videos requires simultaneously capturing high-frequency appearance details and temporally continuous motion. Existing methods using single Gaussian primitives are limited by their low-pass filtering nature, while standard Gabor functions introduce energy instability. Moreover, lack of temporal continuity constraints often leads to motion artifacts during interpolation. We propose AdaGaR, a unified framework addressing both frequency adaptivity and temporal continuity in explicit dynamic scene modeling. We introduce Adaptive Gabor Representation, extending Gaussians through learnable frequency weights and adaptive energy compensation to balance detail capture and stability. For temporal continuity, we employ Cubic Hermite Splines with Temporal Curvature Regularization to ensure smooth motion evolution. An Adaptive Initialization mechanism combining depth estimation, point tracking, and foreground masks establishes stable point cloud distributions in early training. Experiments on Tap-Vid DAVIS demonstrate state-of-the-art performance (PSNR 35.49, SSIM 0.9433, LPIPS 0.0723) and strong generalization across frame interpolation, depth consistency, video editing, and stereo view synthesis. Project page: https://jiewenchan.github.io/AdaGaR/</p> - https://arxiv.org/abs/2601.00796 - Fri, 02 Jan 2026 18:59:55 +0000 + The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning + https://arxiv.org/abs/2601.06002 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiguang Chen, Yantao Du, Ziniu Li, Jinhao Liu, Songyao Duan, Jiarui Guo, Minghao Liu, Jiaheng Liu, Tong Yang, Ge Zhang, Libo Qin, Wanxiang Che, Wenhao Huang</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajectories feature stable molecular-like structures in unified view, which are formed by three interaction types: Deep-Reasoning (covalent-like), Self-Reflection (hydrogen-bond-like), and Self-Exploration (van der Waals-like). Analysis of distilled trajectories reveals these structures emerge from Long CoT fine-tuning, not keyword imitation. We introduce Effective Semantic Isomers and show that only bonds promoting fast entropy convergence support stable Long CoT learning, while structural competition impairs training. Drawing on these findings, we present Mole-Syn, a distribution-transfer-graph method that guides synthesis of effective Long CoT structures, boosting performance and RL stability across benchmarks.</p> + https://arxiv.org/abs/2601.06002 + Fri, 09 Jan 2026 18:39:01 +0000 - KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs - https://arxiv.org/abs/2601.01046 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01046.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixuan Tang, Yi Yang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> While LLMs are powerful embedding backbones, their application in training-free settings faces two structural challenges: causal attention restricts early tokens from accessing subsequent context, and the next-token prediction objective biases representations toward generation rather than semantic compression. To address these limitations, we propose KV-Embedding, a framework that activates the latent representation power of frozen LLMs. Our method leverages the observation that the key-value (KV) states of the final token at each layer encode a compressed view of the sequence. By re-routing these states as a prepended prefix, we enable all tokens to access sequence-level context within a single forward pass. To ensure model-agnostic applicability, we introduce an automated layer selection strategy based on intrinsic dimensionality. Evaluations on MTEB across Qwen, Mistral, and Llama backbones show that KV-Embedding outperforms existing training-free baselines by up to 10%, while maintaining robust performance on sequences up to 4,096 tokens. These results demonstrate that internal state manipulation offers an efficient alternative to input modification, and we hope this work encourages further exploration of LLM internals for representation learning.</p> - https://arxiv.org/abs/2601.01046 - Sat, 03 Jan 2026 02:55:43 +0000 + Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards + https://arxiv.org/abs/2601.06021 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06021.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajie Zhang, Xin Lv, Ling Feng, Lei Hou, Juanzi Li</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of agents' reasoning process, and often lead to undesirable behaviors such as shortcut exploitation and hallucinations. To address these limitations, we propose Citation-aware Rubric Rewards (CaRR), a fine-grained reward framework for deep search agents that emphasizes reasoning comprehensiveness, factual grounding, and evidence connectivity. CaRR decomposes complex questions into verifiable single-hop rubrics and requires agents to satisfy these rubrics by explicitly identifying hidden entities, supporting them with correct citations, and constructing complete evidence chains that link to the predicted answer. We further introduce Citation-aware Group Relative Policy Optimization (C-GRPO), which combines CaRR and outcome rewards for training robust deep search agents. Experiments show that C-GRPO consistently outperforms standard outcome-based RL baselines across multiple deep search benchmarks. Our analysis also validates that C-GRPO effectively discourages shortcut exploitation, promotes comprehensive, evidence-grounded reasoning, and exhibits strong generalization to open-ended deep research tasks. Our code and data are available at https://github.com/THUDM/CaRR.</p> + https://arxiv.org/abs/2601.06021 + Fri, 09 Jan 2026 18:57:53 +0000 - Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models - https://arxiv.org/abs/2601.01321 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01321.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rong Zhou, Dongping Chen, Zihan Jia, Yao Su, Yixin Liu, Yiwen Lu, Dongwei Shi, Yue Huang, Tianyang Xu, Yi Pan, Xinliang Li, Yohannes Abate, Qingyu Chen, Zhengzhong Tu, Yu Yang, Yu Zhang, Qingsong Wen, Gengchen Mai, Sunyang Fu, Jiachen Li, Xuyu Wang, Ziran Wang, Jing Huang, Tianming Liu, Yong Chen, Lichao Sun, Lifang He</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Digital twins, as precise digital representations of physical systems, have evolved from passive simulation tools into intelligent and autonomous entities through the integration of artificial intelligence technologies. This paper presents a unified four-stage framework that systematically characterizes AI integration across the digital twin lifecycle, spanning modeling, mirroring, intervention, and autonomous management. By synthesizing existing technologies and practices, we distill a unified four-stage framework that systematically characterizes how AI methodologies are embedded across the digital twin lifecycle: (1) modeling the physical twin through physics-based and physics-informed AI approaches, (2) mirroring the physical system into a digital twin with real-time synchronization, (3) intervening in the physical twin through predictive modeling, anomaly detection, and optimization strategies, and (4) achieving autonomous management through large language models, foundation models, and intelligent agents. We analyze the synergy between physics-based modeling and data-driven learning, highlighting the shift from traditional numerical solvers to physics-informed and foundation models for physical systems. Furthermore, we examine how generative AI technologies, including large language models and generative world models, transform digital twins into proactive and self-improving cognitive systems capable of reasoning, communication, and creative scenario generation. Through a cross-domain review spanning eleven application domains, including healthcare, aerospace, smart manufacturing, robotics, and smart cities, we identify common challenges related to scalability, explainability, and trustworthiness, and outline directions for responsible AI-driven digital twin systems.</p> - https://arxiv.org/abs/2601.01321 - Sun, 04 Jan 2026 01:17:09 +0000 + RigMo: Unifying Rig and Motion Learning for Generative Animation + https://arxiv.org/abs/2601.06378 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06378.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Despite significant progress in 4D generation, rig and motion, the core structural and dynamic components of animation are typically modeled as separate problems. Existing pipelines rely on ground-truth skeletons and skinning weights for motion generation and treat auto-rigging as an independent process, undermining scalability and interpretability. We present RigMo, a unified generative framework that jointly learns rig and motion directly from raw mesh sequences, without any human-provided rig annotations. RigMo encodes per-vertex deformations into two compact latent spaces: a rig latent that decodes into explicit Gaussian bones and skinning weights, and a motion latent that produces time-varying SE(3) transformations. Together, these outputs define an animatable mesh with explicit structure and coherent motion, enabling feed-forward rig and motion inference for deformable objects. Beyond unified rig-motion discovery, we introduce a Motion-DiT model operating in RigMo's latent space and demonstrate that these structure-aware latents can naturally support downstream motion generation tasks. Experiments on DeformingThings4D, Objaverse-XL, and TrueBones demonstrate that RigMo learns smooth, interpretable, and physically plausible rigs, while achieving superior reconstruction and category-level generalization compared to existing auto-rigging and deformation baselines. RigMo establishes a new paradigm for unified, structure-aware, and scalable dynamic 3D modeling.</p> + https://arxiv.org/abs/2601.06378 + Sat, 10 Jan 2026 01:26:28 +0000 - LEMAS: Large A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models - https://arxiv.org/abs/2601.04233 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Zhao, Lijian Lin, Ye Zhu, Kai Xie, Yunfei Liu, Yu Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present the LEMAS-Dataset, which, to our knowledge, is currently the largest open-source multilingual speech corpus with word-level timestamps. Covering over 150,000 hours across 10 major languages, LEMAS-Dataset is constructed via a efficient data processing pipeline that ensures high-quality data and annotations. To validate the effectiveness of LEMAS-Dataset across diverse generative paradigms, we train two benchmark models with distinct architectures and task specializations on this dataset. LEMAS-TTS, built upon a non-autoregressive flow-matching framework, leverages the dataset's massive scale and linguistic diversity to achieve robust zero-shot multilingual synthesis. Our proposed accent-adversarial training and CTC loss mitigate cross-lingual accent issues, enhancing synthesis stability. Complementarily, LEMAS-Edit employs an autoregressive decoder-only architecture that formulates speech editing as a masked token infilling task. By exploiting precise word-level alignments to construct training masks and adopting adaptive decoding strategies, it achieves seamless, smooth-boundary speech editing with natural transitions. Experimental results demonstrate that models trained on LEMAS-Dataset deliver high-quality synthesis and editing performance, confirming the dataset's quality. We envision that this richly timestamp-annotated, fine-grained multilingual corpus will drive future advances in prompt-based speech generation systems.</p> - https://arxiv.org/abs/2601.04233 - Sun, 04 Jan 2026 03:43:52 +0000 + BizFinBench.v2: A Unified Dual-Mode Bilingual Benchmark for Expert-Level Financial Capability Alignment + https://arxiv.org/abs/2601.06401 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06401.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Guo, Rongjunchen Zhang, Guilong Lu, Xuntao Guo, Shuai Jia, Zhi Yang, Liwen Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large language models have undergone rapid evolution, emerging as a pivotal technology for intelligence in financial operations. However, existing benchmarks are often constrained by pitfalls such as reliance on simulated or general-purpose samples and a focus on singular, offline static scenarios. Consequently, they fail to align with the requirements for authenticity and real-time responsiveness in financial services, leading to a significant discrepancy between benchmark performance and actual operational efficacy. To address this, we introduce BizFinBench.v2, the first large-scale evaluation benchmark grounded in authentic business data from both Chinese and U.S. equity markets, integrating online assessment. We performed clustering analysis on authentic user queries from financial platforms, resulting in eight fundamental tasks and two online tasks across four core business scenarios, totaling 29,578 expert-level Q&A pairs. Experimental results demonstrate that ChatGPT-5 achieves a prominent 61.5% accuracy in main tasks, though a substantial gap relative to financial experts persists; in online tasks, DeepSeek-R1 outperforms all other commercial LLMs. Error analysis further identifies the specific capability deficiencies of existing models within practical financial business contexts. BizFinBench.v2 transcends the limitations of current benchmarks, achieving a business-level deconstruction of LLM financial capabilities and providing a precise basis for evaluating efficacy in the widespread deployment of LLMs within the financial domain. The data and code are available at https://github.com/HiThink-Research/BizFinBench.v2.</p> + https://arxiv.org/abs/2601.06401 + Sat, 10 Jan 2026 02:51:53 +0000 - DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer - https://arxiv.org/abs/2601.01425 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01425.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Guo, Fulong Ye, Xinghui Li, Pengqi Tu, Pengze Zhang, Qichao Sun, Songtao Zhao, Xiangwang Hou, Qian He</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Video Face Swapping (VFS) requires seamlessly injecting a source identity into a target video while meticulously preserving the original pose, expression, lighting, background, and dynamic information. Existing methods struggle to maintain identity similarity and attribute preservation while preserving temporal consistency. To address the challenge, we propose a comprehensive framework to seamlessly transfer the superiority of Image Face Swapping (IFS) to the video domain. We first introduce a novel data pipeline SyncID-Pipe that pre-trains an Identity-Anchored Video Synthesizer and combines it with IFS models to construct bidirectional ID quadruplets for explicit supervision. Building upon paired data, we propose the first Diffusion Transformer-based framework DreamID-V, employing a core Modality-Aware Conditioning module to discriminatively inject multi-model conditions. Meanwhile, we propose a Synthetic-to-Real Curriculum mechanism and an Identity-Coherence Reinforcement Learning strategy to enhance visual realism and identity consistency under challenging scenarios. To address the issue of limited benchmarks, we introduce IDBench-V, a comprehensive benchmark encompassing diverse scenes. Extensive experiments demonstrate DreamID-V outperforms state-of-the-art methods and further exhibits exceptional versatility, which can be seamlessly adapted to various swap-related tasks.</p> - https://arxiv.org/abs/2601.01425 - Sun, 04 Jan 2026 08:07:11 +0000 + LSRIF: Logic-Structured Reinforcement Learning for Instruction Following + https://arxiv.org/abs/2601.06431 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06431.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Ren, Qianyu He, Jingwen Chang, Jie Zeng, Jiaqing Liang, Yanghua Xiao, Han Xia, Zeye Sun, Fei Yu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Instruction-following is critical for large language models, but real-world instructions often contain logical structures such as sequential dependencies and conditional branching. Existing methods typically construct datasets with parallel constraints and optimize average rewards, ignoring logical dependencies and yielding noisy signals. We propose a logic-structured training framework LSRIF that explicitly models instruction logic. We first construct a dataset LSRInstruct with constraint structures such as parallel, sequential, and conditional types, and then design structure-aware rewarding method LSRIF including average aggregation for parallel structures, failure-penalty propagation for sequential structures, and selective rewards for conditional branches. Experiments show LSRIF brings significant improvements in instruction-following (in-domain and out-of-domain) and general reasoning. Analysis reveals that learning with explicit logic structures brings parameter updates in attention layers and sharpens token-level attention to constraints and logical operators.</p> + https://arxiv.org/abs/2601.06431 + Sat, 10 Jan 2026 05:11:38 +0000 - SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving - https://arxiv.org/abs/2601.01426 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaofan Tao, Jierun Chen, Yuxin Jiang, Kaiqi Kou, Shaowei Wang, Ruoyu Wang, Xiaohui Li, Sidi Yang, Yiming Du, Jianbo Dai, Zhiming Mao, Xinyu Wang, Lifeng Shang, Haoli Bai</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g., mid-training, SFT, reinforcement learning, and their combinations), we explore how to push the limits of a lightweight SFT-only approach for SWE tasks. SWE-Lego comprises three core building blocks, with key findings summarized as follows: 1) the SWE-Lego dataset, a collection of 32k highquality task instances and 18k validated trajectories, combining real and synthetic data to complement each other in both quality and quantity; 2) a refined SFT procedure with error masking and a difficulty-based curriculum, which demonstrably improves action quality and overall performance. Empirical results show that with these two building bricks alone,the SFT can push SWE-Lego models to state-of-the-art performance among open-source models of comparable size on SWE-bench Verified: SWE-Lego-Qwen3-8B reaches 42.2%, and SWE-Lego-Qwen3-32B attains 52.6%. 3) We further evaluate and improve test-time scaling (TTS) built upon the SFT foundation. Based on a well-trained verifier, SWE-Lego models can be significantly boosted--for example, 42.2% to 49.6% and 52.6% to 58.8% under TTS@16 for the 8B and 32B models, respectively.</p> - https://arxiv.org/abs/2601.01426 - Sun, 04 Jan 2026 08:07:27 +0000 + ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking + https://arxiv.org/abs/2601.06487 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06487.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiang Zhang, Boli Chen, Fanrui Zhang, Ruixue Ding, Shihang Wang, Qiuchen Wang, Yinfeng Huang, Haonan Zhang, Rongxiang Zhu, Pengyong Wang, Ailin Ren, Xin Li, Pengjun Xie, Jiawei Liu, Ning Guo, Jingren Zhou, Zheng-Jun Zha</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., complex travel planning). Due to the absence of objective ground-truth for these tasks, current RL algorithms largely rely on reward models that assign scalar scores to individual responses. We contend that such pointwise scoring suffers from an inherent discrimination collapse: the reward model struggles to distinguish subtle advantages among different trajectories, resulting in scores within a group being compressed into a narrow range. Consequently, the effective reward signal becomes dominated by noise from the reward model, leading to optimization stagnation. To address this, we propose ArenaRL, a reinforcement learning paradigm that shifts from pointwise scalar scoring to intra-group relative ranking. ArenaRL introduces a process-aware pairwise evaluation mechanism, employing multi-level rubrics to assign fine-grained relative scores to trajectories. Additionally, we construct an intra-group adversarial arena and devise a tournament-based ranking scheme to obtain stable advantage signals. Empirical results confirm that the built seeded single-elimination scheme achieves nearly equivalent advantage estimation accuracy to full pairwise comparisons with O(N^2) complexity, while operating with only O(N) complexity, striking an optimal balance between efficiency and precision. Furthermore, to address the lack of full-cycle benchmarks for open-ended agents, we build Open-Travel and Open-DeepResearch, two high-quality benchmarks featuring a comprehensive pipeline covering SFT, RL training, and multi-dimensional evaluation. Extensive experiments show that ArenaRL substantially outperforms standard RL baselines, enabling LLM agents to generate more robust solutions for complex real-world tasks.</p> + https://arxiv.org/abs/2601.06487 + Sat, 10 Jan 2026 08:43:07 +0000 - MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization - https://arxiv.org/abs/2601.01554 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> MOSI. AI, Donghua Yu, Zhengyuan Lin, Chen Yang, Yiyang Zhang, Hanfu Chen, Jingqi Chen, Ke Chen, Liwei Fan, Yi Jiang, Jie Zhu, Muchen Li, Wenxuan Wang, Yang Wang, Zhe Xu, Yitian Gong, Yuqian Zhang, Wenbo Zhang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained on extensive real wild data and equipped with a 128k context window for up to 90-minute inputs, MOSS Transcribe Diarize scales well and generalizes robustly. Across comprehensive evaluations, it outperforms state-of-the-art commercial systems on multiple public and in-house benchmarks.</p> - https://arxiv.org/abs/2601.01554 - Sun, 04 Jan 2026 15:01:10 +0000 + BabyVision: Visual Reasoning Beyond Language + https://arxiv.org/abs/2601.06521 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li</p><p><b>Upvotes:</b> 182</p><p><b>Summary:</b> While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.</p> + https://arxiv.org/abs/2601.06521 + Sat, 10 Jan 2026 10:42:44 +0000 - OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment - https://arxiv.org/abs/2601.01576 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Zhang, Kexin Tan, Yueyuan Huang, Yujiong Shen, Chunchun Ma, Li Ju, Xinran Zhang, Yuhui Wang, Wenqing Jing, Jingyi Deng, Huayu Sha, Binze Hu, Jingqi Tong, Changhao Jiang, Yage Geng, Yuankai Ying, Yue Zhang, Zhangyue Yin, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Evaluating novelty is critical yet challenging in peer review, as reviewers must assess submissions against a vast, rapidly evolving literature. This report presents OpenNovelty, an LLM-powered agentic system for transparent, evidence-based novelty analysis. The system operates through four phases: (1) extracting the core task and contribution claims to generate retrieval queries; (2) retrieving relevant prior work based on extracted queries via semantic search engine; (3) constructing a hierarchical taxonomy of core-task-related work and performing contribution-level full-text comparisons against each contribution; and (4) synthesizing all analyses into a structured novelty report with explicit citations and evidence snippets. Unlike naive LLM-based approaches, OpenNovelty grounds all assessments in retrieved real papers, ensuring verifiable judgments. We deploy our system on 500+ ICLR 2026 submissions with all reports publicly available on our website, and preliminary analysis suggests it can identify relevant prior work, including closely related papers that authors may overlook. OpenNovelty aims to empower the research community with a scalable tool that promotes fair, consistent, and evidence-backed peer review.</p> - https://arxiv.org/abs/2601.01576 - Sun, 04 Jan 2026 15:48:51 +0000 + Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity + https://arxiv.org/abs/2601.06596 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06596.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongjun An, Yiliang Song, Jiangan Chen, Jiawei Shao, Chi Zhang, Xuelong Li</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can steer responses toward user-appeasing agreement and away from truth-oriented correction. In this work, we investigate whether aligned models are vulnerable to Preference-Undermining Attacks (PUA), a class of manipulative prompting strategies designed to exploit the model's desire to please user preferences at the expense of truthfulness. We propose a diagnostic methodology that provides a finer-grained and more directive analysis than aggregate benchmark scores, using a factorial evaluation framework to decompose prompt-induced shifts into interpretable effects of system objectives (truth- vs. preference-oriented) and PUA-style dialogue factors (directive control, personal derogation, conditional approval, reality denial) within a controlled 2 times 2^4 design. Surprisingly, more advanced models are sometimes more susceptible to manipulative prompts. Beyond the dominant reality-denial factor, we observe model-specific sign reversals and interactions with PUA-style factors, suggesting tailored defenses rather than uniform robustness. These findings offer a novel, reproducible factorial evaluation methodology that provides finer-grained diagnostics for post-training processes like RLHF, enabling better trade-offs in the product iteration of LLMs by offering a more nuanced understanding of preference alignment risks and the impact of manipulative prompts.</p> + https://arxiv.org/abs/2601.06596 + Sat, 10 Jan 2026 15:16:23 +0000 - NitroGen: An Open Foundation Model for Generalist Gaming Agents - https://arxiv.org/abs/2601.02427 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Loïc Magne, Anas Awadalla, Guanzhi Wang, Yinzhen Xu, Joshua Belofsky, Fengyuan Hu, Joohwan Kim, Ludwig Schmidt, Georgia Gkioxari, Jan Kautz, Yisong Yue, Yejin Choi, Yuke Zhu, Linxi "Jim" Fan</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> We introduce NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. We incorporate three key ingredients: 1) an internet-scale video-action dataset constructed by automatically extracting player actions from publicly available gameplay videos, 2) a multi-game benchmark environment that can measure cross-game generalization, and 3) a unified vision-action model trained with large-scale behavior cloning. NitroGen exhibits strong competence across diverse domains, including combat encounters in 3D action games, high-precision control in 2D platformers, and exploration in procedurally generated worlds. It transfers effectively to unseen games, achieving up to 52% relative improvement in task success rates over models trained from scratch. We release the dataset, evaluation suite, and model weights to advance research on generalist embodied agents.</p> - https://arxiv.org/abs/2601.02427 - Sun, 04 Jan 2026 16:24:50 +0000 + EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs + https://arxiv.org/abs/2601.06786 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Taesup Kim</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Improving the reasoning abilities of large language models (LLMs) has largely relied on iterative self-training with model-generated data. While effective at boosting accuracy, existing approaches primarily reinforce successful reasoning paths, incurring a substantial calibration cost: models become overconfident and lose the ability to represent uncertainty. This failure has been characterized as a form of model collapse in alignment, where predictive distributions degenerate toward low-variance point estimates. We address this issue by reframing reasoning training as an epistemic learning problem, in which models must learn not only how to reason, but also when their reasoning should be trusted. We propose epistemically-calibrated reasoning (EpiCaR) as a training objective that jointly optimizes reasoning performance and calibration, and instantiate it within an iterative supervised fine-tuning framework using explicit self-evaluation signals. Experiments on Llama-3 and Qwen-3 families demonstrate that our approach achieves Pareto-superiority over standard baselines in both accuracy and calibration, particularly in models with sufficient reasoning capacity (e.g., 3B+). This framework generalizes effectively to OOD mathematical reasoning (GSM8K) and code generation (MBPP). Ultimately, our approach enables a 3X reduction in inference compute, matching the K=30 performance of STaR with only K=10 samples in capable models.</p> + https://arxiv.org/abs/2601.06786 + Sun, 11 Jan 2026 06:21:13 +0000 - OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs - https://arxiv.org/abs/2601.01592 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Wang, Yunhao Chen, Juncheng Li, Yixu Wang, Yang Yao, Tianle Gu, Jie Li, Yan Teng, Xingjun Ma, Yingchun Wang, Xia Hu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to single-turn text interactions, and lack the scalability required for systematic evaluation. To address this, we introduce OpenRT, a unified, modular, and high-throughput red-teaming framework designed for comprehensive MLLM safety evaluation. At its core, OpenRT architects a paradigm shift in automated red-teaming by introducing an adversarial kernel that enables modular separation across five critical dimensions: model integration, dataset management, attack strategies, judging methods, and evaluation metrics. By standardizing attack interfaces, it decouples adversarial logic from a high-throughput asynchronous runtime, enabling systematic scaling across diverse models. Our framework integrates 37 diverse attack methodologies, spanning white-box gradients, multi-modal perturbations, and sophisticated multi-agent evolutionary strategies. Through an extensive empirical study on 20 advanced models (including GPT-5.2, Claude 4.5, and Gemini 3 Pro), we expose critical safety gaps: even frontier models fail to generalize across attack paradigms, with leading models exhibiting average Attack Success Rates as high as 49.14%. Notably, our findings reveal that reasoning models do not inherently possess superior robustness against complex, multi-turn jailbreaks. By open-sourcing OpenRT, we provide a sustainable, extensible, and continuously maintained infrastructure that accelerates the development and standardization of AI safety.</p> - https://arxiv.org/abs/2601.01592 - Sun, 04 Jan 2026 16:41:33 +0000 + MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences + https://arxiv.org/abs/2601.06789 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06789.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihao Wang, Ziming Cheng, Shuo Zhang, Fan Liu, Rui Xu, Heng Lian, Kunyi Wang, Xiaoming Yu, Jianghao Yin, Sen Hu, Yue Hu, Shaolei Zhang, Yanbing Liu, Ronghao Chen, Huacan Wang</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratch or solely using local context, ignoring the immense historical human experience available on platforms like GitHub. Accessing this open-world experience is hindered by the unstructured and fragmented nature of real-world issue-tracking data. In this paper, we introduce MemGovern, a framework designed to govern and transform raw GitHub data into actionable experiential memory for agents. MemGovern employs experience governance to convert human experience into agent-friendly experience cards and introduces an agentic experience search strategy that enables logic-driven retrieval of human expertise. By producing 135K governed experience cards, MemGovern achieves a significant performance boost, improving resolution rates on the SWE-bench Verified by 4.65%. As a plug-in approach, MemGovern provides a solution for agent-friendly memory infrastructure.</p> + https://arxiv.org/abs/2601.06789 + Sun, 11 Jan 2026 06:41:26 +0000 - FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing - https://arxiv.org/abs/2601.01720 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01720.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xijie Huang, Chengming Xu, Donghao Luo, Xiaobin Hu, Peng Tang, Xu Peng, Jiangning Zhang, Chengjie Wang, Yanwei Fu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> First-Frame Propagation (FFP) offers a promising paradigm for controllable video editing, but existing methods are hampered by a reliance on cumbersome run-time guidance. We identify the root cause of this limitation as the inadequacy of current training datasets, which are often too short, low-resolution, and lack the task diversity required to teach robust temporal priors. To address this foundational data gap, we first introduce FFP-300K, a new large-scale dataset comprising 300K high-fidelity video pairs at 720p resolution and 81 frames in length, constructed via a principled two-track pipeline for diverse local and global edits. Building on this dataset, we propose a novel framework designed for true guidance-free FFP that resolves the critical tension between maintaining first-frame appearance and preserving source video motion. Architecturally, we introduce Adaptive Spatio-Temporal RoPE (AST-RoPE), which dynamically remaps positional encodings to disentangle appearance and motion references. At the objective level, we employ a self-distillation strategy where an identity propagation task acts as a powerful regularizer, ensuring long-term temporal stability and preventing semantic drift. Comprehensive experiments on the EditVerseBench benchmark demonstrate that our method significantly outperforming existing academic and commercial models by receiving about 0.2 PickScore and 0.3 VLM score improvement against these competitors.</p> - https://arxiv.org/abs/2601.01720 - Mon, 05 Jan 2026 01:46:22 +0000 + Forest Before Trees: Latent Superposition for Efficient Visual Reasoning + https://arxiv.org/abs/2601.06803 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning (DWAL). Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains.</p> + https://arxiv.org/abs/2601.06803 + Sun, 11 Jan 2026 08:30:49 +0000 - K-EXAONE Technical Report - https://arxiv.org/abs/2601.01739 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01739.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eunbi Choi, Kibong Choi, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Hyunjik Jo, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Haeju Lee, Jinsik Lee, Kyungmin Lee, Sangha Park, Heuiyeen Yeen, Hwan Chang, Stanley Jungkyu Choi, Yejin Choi, Jiwon Ham, Kijeong Jeon, Geunyeong Jeong, Gerrard Jeongwon Jo, Yonghwan Jo, Jiyeon Jung, Naeun Kang, Dohoon Kim, Euisoon Kim, Hayeon Kim, Hyosang Kim, Hyunseo Kim, Jieun Kim, Minu Kim, Myoungshin Kim, Unsol Kim, Youchul Kim, YoungJin Kim, Chaeeun Lee, Chaeyoon Lee, Changhun Lee, Dahm Lee, Edward Hwayoung Lee, Honglak Lee, Jinsang Lee, Jiyoung Lee, Sangeun Lee, Seungwon Lim, Solji Lim, Woohyung Lim, Chanwoo Moon, Jaewoo Park, Jinho Park, Yongmin Park, Hyerin Seo, Wooseok Seo, Yongwoo Song, Sejong Yang, Sihoon Yang, Chang En Yea, Sihyuk Yi, Chansik Yoon, Dongkeun Yoon, Sangyeon Yoon, Hyeongu Yun</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> This technical report presents K-EXAONE, a large-scale multilingual language model developed by LG AI Research. K-EXAONE is built on a Mixture-of-Experts architecture with 236B total parameters, activating 23B parameters during inference. It supports a 256K-token context window and covers six languages: Korean, English, Spanish, German, Japanese, and Vietnamese. We evaluate K-EXAONE on a comprehensive benchmark suite spanning reasoning, agentic, general, Korean, and multilingual abilities. Across these evaluations, K-EXAONE demonstrates performance comparable to open-weight models of similar size. K-EXAONE, designed to advance AI for a better life, is positioned as a powerful proprietary AI foundation model for a wide range of industrial and research applications.</p> - https://arxiv.org/abs/2601.01739 - Mon, 05 Jan 2026 02:30:59 +0000 + ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration + https://arxiv.org/abs/2601.06860 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06860.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifei Chen, Guanting Dong, Zhicheng Dou</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large Language Models (LLMs) can extend their parameter knowledge limits by adopting the Tool-Integrated Reasoning (TIR) paradigm. However, existing LLM-based agent training framework often focuses on answers' accuracy, overlooking specific alignment for behavior patterns. Consequently, agent often exhibits ineffective actions during TIR tasks, such as redundant and insufficient tool calls. How to calibrate erroneous behavioral patterns when executing TIR tasks, thereby exploring effective trajectories, remains an open-ended problem. In this paper, we propose ET-Agent, a training framework for calibrating agent's tool-use behavior through two synergistic perspectives: Self-evolving Data Flywheel and Behavior Calibration Training. Specifically, we introduce a self-evolutionary data flywheel to generate enhanced data, used to fine-tune LLM to improve its exploration ability. Based on this, we implement an two-phases behavior-calibration training framework. It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors. Further in-depth experiments confirm the superiority of across multiple dimensions, including correctness, efficiency, reasoning conciseness, and tool execution accuracy. Our ET-Agent framework provides practical insights for research in the TIR field. Codes can be found in https://github.com/asilverlight/ET-Agent</p> + https://arxiv.org/abs/2601.06860 + Sun, 11 Jan 2026 11:05:26 +0000 - COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs - https://arxiv.org/abs/2601.01836 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01836.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dasol Choi, DongGeon Lee, Brigitta Jesica Kartono, Helena Berndt, Taeyoun Kwon, Joonwon Jang, Haon Park, Hwanjo Yu, Minsuk Kahng</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> As large language models are deployed in high-stakes enterprise applications, from healthcare to finance, ensuring adherence to organization-specific policies has become essential. Yet existing safety evaluations focus exclusively on universal harms. We present COMPASS (Company/Organization Policy Alignment Assessment), the first systematic framework for evaluating whether LLMs comply with organizational allowlist and denylist policies. We apply COMPASS to eight diverse industry scenarios, generating and validating 5,920 queries that test both routine compliance and adversarial robustness through strategically designed edge cases. Evaluating seven state-of-the-art models, we uncover a fundamental asymmetry: models reliably handle legitimate requests (>95% accuracy) but catastrophically fail at enforcing prohibitions, refusing only 13-40% of adversarial denylist violations. These results demonstrate that current LLMs lack the robustness required for policy-critical deployments, establishing COMPASS as an essential evaluation framework for organizational AI safety.</p> - https://arxiv.org/abs/2601.01836 - Mon, 05 Jan 2026 06:57:45 +0000 + Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning + https://arxiv.org/abs/2601.06943 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengwen Liu, Xiaomin Yu, Zhuoyue Chang, Zhe Huang, Shuo Zhang, Heng Lian, Kunyi Wang, Rui Xu, Sen Hu, Jianheng Hou, Hao Peng, Chengwei Qin, Xiaobin Hu, Hong Peng, Ronghao Chen, Huacan Wang</p><p><b>Upvotes:</b> 202</p><p><b>Summary:</b> In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.</p> + https://arxiv.org/abs/2601.06943 + Sun, 11 Jan 2026 15:07:37 +0000 - CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving - https://arxiv.org/abs/2601.01874 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.01874.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuhang Chen, Yunqiu Xu, Junjie Xie, Aojun Lu, Tao Feng, Zeying Huang, Ning Zhang, Yi Sun, Yi Yang, Hangjie Yuan</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reasoning, but their solutions are limited to improving the extraction and interpretation of visual inputs. Notably, they all ignore the key issue of whether the extracted visual cues are faithfully integrated and properly utilized in subsequent reasoning. Motivated by this, we present CogFlow, a novel cognitive-inspired three-stage framework that incorporates a knowledge internalization stage, explicitly simulating the hierarchical flow of human reasoning: perceptionRightarrowinternalizationRightarrowreasoning. Inline with this hierarchical flow, we holistically enhance all its stages. We devise Synergistic Visual Rewards to boost perception capabilities in parametric and semantic spaces, jointly improving visual information extraction from symbols and diagrams. To guarantee faithful integration of extracted visual cues into subsequent reasoning, we introduce a Knowledge Internalization Reward model in the internalization stage, bridging perception and reasoning. Moreover, we design a Visual-Gated Policy Optimization algorithm to further enforce the reasoning is grounded with the visual knowledge, preventing models seeking shortcuts that appear coherent but are visually ungrounded reasoning chains. Moreover, we contribute a new dataset MathCog for model training, which contains samples with over 120K high-quality perception-reasoning aligned annotations. Comprehensive experiments and analysis on commonly used visual mathematical reasoning benchmarks validate the superiority of the proposed CogFlow.</p> - https://arxiv.org/abs/2601.01874 - Mon, 05 Jan 2026 08:02:18 +0000 + X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests + https://arxiv.org/abs/2601.06953 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Wu, Haoling Li, Xin Zhang, Jiani Guo, Jane Luo, Steven Liu, Yangyu Huang, Ruihang Chu, Scarlett Li, Yujiu Yang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Competitive programming presents great challenges for Code LLMs due to its intensive reasoning demands and high logical complexity. However, current Code LLMs still rely heavily on real-world data, which limits their scalability. In this paper, we explore a fully synthetic approach: training Code LLMs with entirely generated tasks, solutions, and test cases, to empower code reasoning models without relying on real-world data. To support this, we leverage feature-based synthesis to propose a novel data synthesis pipeline called SynthSmith. SynthSmith shows strong potential in producing diverse and challenging tasks, along with verified solutions and tests, supporting both supervised fine-tuning and reinforcement learning. Based on the proposed synthetic SFT and RL datasets, we introduce the X-Coder model series, which achieves a notable pass rate of 62.9 avg@8 on LiveCodeBench v5 and 55.8 on v6, outperforming DeepCoder-14B-Preview and AReal-boba2-14B despite having only 7B parameters. In-depth analysis reveals that scaling laws hold on our synthetic dataset, and we explore which dimensions are more effective to scale. We further provide insights into code-centric reinforcement learning and highlight the key factors that shape performance through detailed ablations and analysis. Our findings demonstrate that scaling high-quality synthetic data and adopting staged training can greatly advance code reasoning, while mitigating reliance on real-world coding data.</p> + https://arxiv.org/abs/2601.06953 + Sun, 11 Jan 2026 15:22:33 +0000 - WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks - https://arxiv.org/abs/2601.02439 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02439.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Bai, Alexey Taymanov, Tong Zhang, Aviral Kumar, Spencer Whitehead</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning. WebGym contains nearly 300,000 tasks with rubric-based evaluations across diverse, real-world websites and difficulty levels. We train agents with a simple reinforcement learning (RL) recipe, which trains on the agent's own interaction traces (rollouts), using task rewards as feedback to guide learning. To enable scaling RL, we speed up sampling of trajectories in WebGym by developing a high-throughput asynchronous rollout system, designed specifically for web agents. Our system achieves a 4-5x rollout speedup compared to naive implementations. Second, we scale the task set breadth, depth, and size, which results in continued performance improvement. Fine-tuning a strong base vision-language model, Qwen-3-VL-8B-Instruct, on WebGym results in an improvement in success rate on an out-of-distribution test set from 26.2% to 42.9%, significantly outperforming agents based on proprietary models such as GPT-4o and GPT-5-Thinking that achieve 27.1% and 29.8%, respectively. This improvement is substantial because our test set consists only of tasks on websites never seen during training, unlike many other prior works on training visual web agents.</p> - https://arxiv.org/abs/2601.02439 - Mon, 05 Jan 2026 09:35:11 +0000 + RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction + https://arxiv.org/abs/2601.06966 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.06966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or task-oriented dialogue, failing to capture **"long-term project-oriented"** interactions where agents must track evolving goals. To bridge this gap, we introduce **RealMem**, the first benchmark grounded in realistic project scenarios. RealMem comprises over 2,000 cross-session dialogues across eleven scenarios, utilizing natural user queries for evaluation. We propose a synthesis pipeline that integrates Project Foundation Construction, Multi-Agent Dialogue Generation, and Memory and Schedule Management to simulate the dynamic evolution of memory. Experiments reveal that current memory systems face significant challenges in managing the long-term project states and dynamic context dependencies inherent in real-world projects. Our code and datasets are available at [https://github.com/AvatarMemory/RealMemBench](https://github.com/AvatarMemory/RealMemBench).</p> + https://arxiv.org/abs/2601.06966 + Sun, 11 Jan 2026 15:49:36 +0000 - MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics - https://arxiv.org/abs/2601.02075 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofan Shi, Hubao A, Yufei Shao, Mengyan Dai, Yadong Yu, Pan Xiang, Dongliang Huang, Hongxu An, Chunxiao Xin, Haiyang Shen, Zhenyu Wang, Yunshan Na, Gang Huang, Xiang Jing</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Molecular dynamics (MD) simulations are essential for understanding atomic-scale behaviors in materials science, yet writing LAMMPS scripts remains highly specialized and time-consuming tasks. Although LLMs show promise in code generation and domain-specific question answering, their performance in MD scenarios is limited by scarce domain data, the high deployment cost of state-of-the-art LLMs, and low code executability. Building upon our prior MDAgent, we present MDAgent2, the first end-to-end framework capable of performing both knowledge Q&A and code generation within the MD domain. We construct a domain-specific data-construction pipeline that yields three high-quality datasets spanning MD knowledge, question answering, and code generation. Based on these datasets, we adopt a three stage post-training strategy--continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL)--to train two domain-adapted models, MD-Instruct and MD-Code. Furthermore, we introduce MD-GRPO, a closed-loop RL method that leverages simulation outcomes as reward signals and recycles low-reward trajectories for continual refinement. We further build MDAgent2-RUNTIME, a deployable multi-agent system that integrates code generation, execution, evaluation, and self-correction. Together with MD-EvalBench proposed in this work, the first benchmark for LAMMPS code generation and question answering, our models and system achieve performance surpassing several strong baselines.This work systematically demonstrates the adaptability and generalization capability of large language models in industrial simulation tasks, laying a methodological foundation for automatic code generation in AI for Science and industrial-scale simulations. URL: https://github.com/FredericVAN/PKU_MDAgent2</p> - https://arxiv.org/abs/2601.02075 - Mon, 05 Jan 2026 12:56:51 +0000 + Solar Open Technical Report + https://arxiv.org/abs/2601.07022 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07022.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sungrae Park, Sanghoon Kim, Jungho Cho, Gyoungjin Gim, Dawoon Jung, Mikyoung Cha, Eunhae Choo, Taekgyu Hong, Minbyul Jeong, SeHwan Joo, Minsoo Khang, Eunwon Kim, Minjeong Kim, Sujeong Kim, Yunsu Kim, Hyeonju Lee, Seunghyun Lee, Sukyung Lee, Siyoung Park, Gyungin Shin, Inseo Song, Wonho Song, Seonghoon Yang, Seungyoun Yi, Sanghoon Yoon, Jeonghyun Ko, Seyoung Song, Keunwoo Choi, Hwalsuk Lee, Sunghun Kim, Du-Seong Chang, Kyunghyun Cho, Junsuk Choe, Hwaran Lee, Jae-Gil Lee, KyungTae Lim, Alice Oh</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> We introduce Solar Open, a 102B-parameter bilingual Mixture-of-Experts language model for underserved languages. Solar Open demonstrates a systematic methodology for building competitive LLMs by addressing three interconnected challenges. First, to train effectively despite data scarcity for underserved languages, we synthesize 4.5T tokens of high-quality, domain-specific, and RL-oriented data. Second, we coordinate this data through a progressive curriculum jointly optimizing composition, quality thresholds, and domain coverage across 20 trillion tokens. Third, to enable reasoning capabilities through scalable RL, we apply our proposed framework SnapPO for efficient optimization. Across benchmarks in English and Korean, Solar Open achieves competitive performance, demonstrating the effectiveness of this methodology for underserved language AI development.</p> + https://arxiv.org/abs/2601.07022 + Sun, 11 Jan 2026 18:33:09 +0000 - Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting - https://arxiv.org/abs/2601.02151 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02151.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muxi Diao, Lele Yang, Wuxuan Gong, Yutong Zhang, Zhonghao Yan, Yufei Han, Kongming Liang, Weiran Xu, Zhanyu Ma</p><p><b>Upvotes:</b> 87</p><p><b>Summary:</b> Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities. We investigate this discrepancy and identify a fundamental distributional gap: while RL aligns with the model's internal belief, SFT forces the model to fit external supervision. This mismatch often manifests as "Confident Conflicts" tokens characterized by low probability but low entropy. In these instances, the model is highly confident in its own prediction but is forced to learn a divergent ground truth, triggering destructive gradient updates. To address this, we propose Entropy-Adaptive Fine-Tuning (EAFT). Unlike methods relying solely on prediction probability, EAFT utilizes token-level entropy as a gating mechanism to distinguish between epistemic uncertainty and knowledge conflict. This allows the model to learn from uncertain samples while suppressing gradients on conflicting data. Extensive experiments on Qwen and GLM series (ranging from 4B to 32B parameters) across mathematical, medical, and agentic domains confirm our hypothesis. EAFT consistently matches the downstream performance of standard SFT while significantly mitigating the degradation of general capabilities.</p> - https://arxiv.org/abs/2601.02151 - Mon, 05 Jan 2026 14:28:17 +0000 + Dr. Zero: Self-Evolving Search Agents without Training Data + https://arxiv.org/abs/2601.07055 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenrui Yue, Kartikeya Upasani, Xianjun Yang, Suyu Ge, Shaoliang Nie, Yuning Mao, Zhe Liu, Dong Wang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> As high-quality data becomes increasingly difficult to obtain, data-free self-evolution has emerged as a promising paradigm. This approach allows large language models (LLMs) to autonomously generate and solve complex problems, thereby improving their reasoning capabilities. However, multi-turn search agents struggle in data-free self-evolution due to the limited question diversity and the substantial compute required for multi-step reasoning and tool using. In this work, we introduce Dr. Zero, a framework enabling search agents to effectively self-evolve without any training data. In particular, we design a self-evolution feedback loop where a proposer generates diverse questions to train a solver initialized from the same base model. As the solver evolves, it incentivizes the proposer to produce increasingly difficult yet solvable tasks, thus establishing an automated curriculum to refine both agents. To enhance training efficiency, we also introduce hop-grouped relative policy optimization (HRPO). This method clusters structurally similar questions to construct group-level baselines, effectively minimizing the sampling overhead in evaluating each query's individual difficulty and solvability. Consequently, HRPO significantly reduces the compute requirements for solver training without compromising performance or stability. Extensive experiment results demonstrate that the data-free Dr. Zero matches or surpasses fully supervised search agents, proving that complex reasoning and search capabilities can emerge solely through self-evolution.</p> + https://arxiv.org/abs/2601.07055 + Sun, 11 Jan 2026 20:27:55 +0000 - Confidence Estimation for LLMs in Multi-turn Interactions - https://arxiv.org/abs/2601.02179 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02179.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Caiqi Zhang, Ruihan Yang, Xiaochen Zhu, Chengzu Li, Tiancheng Hu, Yijiang River Dong, Deqing Yang, Nigel Collier</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research dominantly focuses on single-turn settings. The dynamics of model confidence in multi-turn conversations, where context accumulates and ambiguity is progressively resolved, remain largely unexplored. Reliable confidence estimation in multi-turn settings is critical for many downstream applications, such as autonomous agents and human-in-the-loop systems. This work presents the first systematic study of confidence estimation in multi-turn interactions, establishing a formal evaluation framework grounded in two key desiderata: per-turn calibration and monotonicity of confidence as more information becomes available. To facilitate this, we introduce novel metrics, including a length-normalized Expected Calibration Error (InfoECE), and a new "Hinter-Guesser" paradigm for generating controlled evaluation datasets. Our experiments reveal that widely-used confidence techniques struggle with calibration and monotonicity in multi-turn dialogues. We propose P(Sufficient), a logit-based probe that achieves comparatively better performance, although the task remains far from solved. Our work provides a foundational methodology for developing more reliable and trustworthy conversational agents.</p> - https://arxiv.org/abs/2601.02179 - Mon, 05 Jan 2026 14:58:04 +0000 + Lost in the Noise: How Reasoning Models Fail with Contextual Distractors + https://arxiv.org/abs/2601.07226 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07226.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongyun Lee, Yongrae Jo, Minju Seo, Moontae Lee, Minjoon Seo</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Recent advances in reasoning models and agentic AI systems have led to an increased reliance on diverse external information. However, this shift introduces input contexts that are inherently noisy, a reality that current sanitized benchmarks fail to capture. We introduce NoisyBench, a comprehensive benchmark that systematically evaluates model robustness across 11 datasets in RAG, reasoning, alignment, and tool-use tasks against diverse noise types, including random documents, irrelevant chat histories, and hard negative distractors. Our evaluation reveals a catastrophic performance drop of up to 80% in state-of-the-art models when faced with contextual distractors. Crucially, we find that agentic workflows often amplify these errors by over-trusting noisy tool outputs, and distractors can trigger emergent misalignment even without adversarial intent. We find that prompting, context engineering, SFT, and outcome-reward only RL fail to ensure robustness; in contrast, our proposed Rationale-Aware Reward (RARE) significantly strengthens resilience by incentivizing the identification of helpful information within noise. Finally, we uncover an inverse scaling trend where increased test-time computation leads to worse performance in noisy settings and demonstrate via attention visualization that models disproportionately focus on distractor tokens, providing vital insights for building the next generation of robust, reasoning-capable agents.</p> + https://arxiv.org/abs/2601.07226 + Mon, 12 Jan 2026 05:43:51 +0000 - NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation - https://arxiv.org/abs/2601.02204 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huichao Zhang, Liao Qu, Yiheng Liu, Hang Chen, Yangyang Song, Yongsheng Dong, Shikun Sun, Xian Li, Xu Wang, Yi Jiang, Hu Ye, Bo Chen, Yiming Gao, Peng Liu, Akide Liu, Zhipeng Yang, Qili Deng, Linjie Xing, Jiyang Liu, Zhao Wang, Yang Zhou, Mingcong Liu, Yi Zhang, Qian He, Xiwei Hu, Zhongqi Qi, Jie Shao, Zhiye Fu, Shuai Wang, Fangmin Chen, Xuezhi Chai, Zhihua Wu, Yitong Wang, Zehuan Yuan, Daniel K. Du, Xinglong Wu</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architecture, NextFlow natively activates multimodal understanding and generation capabilities, unlocking abilities of image editing, interleaved content and video generation. Motivated by the distinct nature of modalities - where text is strictly sequential and images are inherently hierarchical - we retain next-token prediction for text but adopt next-scale prediction for visual generation. This departs from traditional raster-scan methods, enabling the generation of 1024x1024 images in just 5 seconds - orders of magnitude faster than comparable AR models. We address the instabilities of multi-scale generation through a robust training recipe. Furthermore, we introduce a prefix-tuning strategy for reinforcement learning. Experiments demonstrate that NextFlow achieves state-of-the-art performance among unified models and rivals specialized diffusion baselines in visual quality.</p> - https://arxiv.org/abs/2601.02204 - Mon, 05 Jan 2026 15:27:04 +0000 + The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents + https://arxiv.org/abs/2601.07264 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weihao Xuan, Qingcheng Zeng, Heli Qi, Yunze Xiao, Junjue Wang, Naoto Yokoya</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Autonomous agents based on large language models (LLMs) are rapidly evolving to handle multi-turn tasks, but ensuring their trustworthiness remains a critical challenge. A fundamental pillar of this trustworthiness is calibration, which refers to an agent's ability to express confidence that reliably reflects its actual performance. While calibration is well-established for static models, its dynamics in tool-integrated agentic workflows remain underexplored. In this work, we systematically investigate verbalized calibration in tool-use agents, revealing a fundamental confidence dichotomy driven by tool type. Specifically, our pilot study identifies that evidence tools (e.g., web search) systematically induce severe overconfidence due to inherent noise in retrieved information, while verification tools (e.g., code interpreters) can ground reasoning through deterministic feedback and mitigate miscalibration. To robustly improve calibration across tool types, we propose a reinforcement learning (RL) fine-tuning framework that jointly optimizes task accuracy and calibration, supported by a holistic benchmark of reward designs. We demonstrate that our trained agents not only achieve superior calibration but also exhibit robust generalization from local training environments to noisy web settings and to distinct domains such as mathematical reasoning. Our results highlight the necessity of domain-specific calibration strategies for tool-use agents. More broadly, this work establishes a foundation for building self-aware agents that can reliably communicate uncertainty in high-stakes, real-world deployments.</p> + https://arxiv.org/abs/2601.07264 + Mon, 12 Jan 2026 07:10:35 +0000 - VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation - https://arxiv.org/abs/2601.02256 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02256.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shikun Sun, Liao Qu, Huichao Zhang, Yiheng Liu, Yangyang Song, Xian Li, Xu Wang, Yi Jiang, Daniel K. Du, Xinglong Wu, Jia Jia</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates severe asynchronous policy conflicts. This issue becomes particularly acute in reinforcement learning (RL) scenarios, leading to unstable training and suboptimal alignment. To resolve this, we propose a novel framework to enhance Group Relative Policy Optimization (GRPO) by explicitly managing these conflicts. Our method integrates three synergistic components: 1) a stabilizing intermediate reward to guide early-stage generation; 2) a dynamic time-step reweighting scheme for precise credit assignment; and 3) a novel mask propagation algorithm, derived from principles of Reward Feedback Learning (ReFL), designed to isolate optimization effects both spatially and temporally. Our approach demonstrates significant improvements in sample quality and objective alignment over the vanilla GRPO baseline, enabling robust and effective optimization for VAR models.</p> - https://arxiv.org/abs/2601.02256 - Mon, 05 Jan 2026 16:36:40 +0000 + Controlled Self-Evolution for Algorithmic Code Optimization + https://arxiv.org/abs/2601.07348 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07348.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tu Hu, Ronghao Chen, Shuo Zhang, Jianghao Yin, Mou Xiao Feng, Jingping Liu, Shaolei Zhang, Wenqi Jiang, Yuqi Fang, Sen Hu, Yi Xu, Huacan Wang</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets. This inefficiency stems from initialization bias trapping evolution in poor solution regions, uncontrolled stochastic operations lacking feedback guidance, and insufficient experience utilization across tasks. To address these bottlenecks, we propose Controlled Self-Evolution (CSE), which consists of three key components. Diversified Planning Initialization generates structurally distinct algorithmic strategies for broad solution space coverage. Genetic Evolution replaces stochastic operations with feedback-guided mechanisms, enabling targeted mutation and compositional crossover. Hierarchical Evolution Memory captures both successful and failed experiences at inter-task and intra-task levels. Experiments on EffiBench-X demonstrate that CSE consistently outperforms all baselines across various LLM backbones. Furthermore, CSE achieves higher efficiency from early generations and maintains continuous improvement throughout evolution. Our code is publicly available at https://github.com/QuantaAlpha/EvoControl.</p> + https://arxiv.org/abs/2601.07348 + Mon, 12 Jan 2026 09:23:13 +0000 - DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies - https://arxiv.org/abs/2601.02267 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02267.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Renke Wang, Zhenyu Zhang, Ying Tai, Jian Yang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Human mesh recovery from multi-view images faces a fundamental challenge: real-world datasets contain imperfect ground-truth annotations that bias the models' training, while synthetic data with precise supervision suffers from domain gap. In this paper, we propose DiffProxy, a novel framework that generates multi-view consistent human proxies for mesh recovery. Central to DiffProxy is leveraging the diffusion-based generative priors to bridge the synthetic training and real-world generalization. Its key innovations include: (1) a multi-conditional mechanism for generating multi-view consistent, pixel-aligned human proxies; (2) a hand refinement module that incorporates flexible visual prompts to enhance local details; and (3) an uncertainty-aware test-time scaling method that increases robustness to challenging cases during optimization. These designs ensure that the mesh recovery process effectively benefits from the precise synthetic ground truth and generative advantages of the diffusion-based pipeline. Trained entirely on synthetic data, DiffProxy achieves state-of-the-art performance across five real-world benchmarks, demonstrating strong zero-shot generalization particularly on challenging scenarios with occlusions and partial views. Project page: https://wrk226.github.io/DiffProxy.html</p> - https://arxiv.org/abs/2601.02267 - Mon, 05 Jan 2026 16:51:45 +0000 + Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models + https://arxiv.org/abs/2601.07351 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07351.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linhao Zhong, Linyu Wu, Bozhen Fang, Tianjian Feng, Chenchen Jing, Wen Wang, Jiaheng Zhang, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions and underutilize intermediate probabilistic representations. In this paper, we propose EvoToken-DLM, a novel diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions. EvoToken-DLM enables a progressive transition from masked states to discrete outputs, supporting revisable decoding. To effectively support this evolution, we introduce continuous trajectory supervision, which aligns training objectives with iterative probabilistic updates. Extensive experiments across multiple benchmarks show that EvoToken-DLM consistently achieves superior performance, outperforming strong diffusion-based and masked DLM baselines. Project webpage: https://aim-uofa.github.io/EvoTokenDLM.</p> + https://arxiv.org/abs/2601.07351 + Mon, 12 Jan 2026 09:25:14 +0000 - InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams - https://arxiv.org/abs/2601.02281 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Yuan, Yantai Yang, Xiaotian Yang, Xupeng Zhang, Zhonghao Zhao, Lingming Zhang, Zhipeng Zhang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offline models like VGGT achieve inspiring geometry capability, their batch-based nature renders them irrelevant for live systems. Streaming architectures, though the intended solution for live operation, have proven inadequate. Existing methods either fail to support truly infinite-horizon inputs or suffer from catastrophic drift over long sequences. We shatter this long-standing dilemma with InfiniteVGGT, a causal visual geometry transformer that operationalizes the concept of a rolling memory through a bounded yet adaptive and perpetually expressive KV cache. Capitalizing on this, we devise a training-free, attention-agnostic pruning strategy that intelligently discards obsolete information, effectively ``rolling'' the memory forward with each new frame. Fully compatible with FlashAttention, InfiniteVGGT finally alleviates the compromise, enabling infinite-horizon streaming while outperforming existing streaming methods in long-term stability. The ultimate test for such a system is its performance over a truly infinite horizon, a capability that has been impossible to rigorously validate due to the lack of extremely long-term, continuous benchmarks. To address this critical gap, we introduce the Long3D benchmark, which, for the first time, enables a rigorous evaluation of continuous 3D geometry estimation on sequences about 10,000 frames. This provides the definitive evaluation platform for future research in long-term 3D geometry understanding. Code is available at: https://github.com/AutoLab-SAI-SJTU/InfiniteVGGT</p> - https://arxiv.org/abs/2601.02281 - Mon, 05 Jan 2026 17:11:00 +0000 + MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era + https://arxiv.org/abs/2601.07526 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07526.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Zhang, Mouxiang Chen, Ruisheng Cao, Jiawei Chen, Fan Zhou, Yiheng Xu, Jiaxi Yang, Liang Chen, Changwei Luo, Kai Zhang, Fan Yan, KaShun Shum, Jiajun Zhang, Zeyu Cui, Hu Feng, Junyang Lin, Binyuan Hui, Min Yang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> The rapid development of interactive and autonomous AI systems signals our entry into the agentic era. Training and evaluating agents on complex agentic tasks such as software engineering and computer use requires not only efficient model computation but also sophisticated infrastructure capable of coordinating vast agent-environment interactions. However, no open-source infrastructure can effectively support large-scale training and evaluation on such complex agentic tasks. To address this challenge, we present MegaFlow, a large-scale distributed orchestration system that enables efficient scheduling, resource allocation, and fine-grained task management for agent-environment workloads. MegaFlow abstracts agent training infrastructure into three independent services (Model Service, Agent Service, and Environment Service) that interact through unified interfaces, enabling independent scaling and flexible resource allocation across diverse agent-environment configurations. In our agent training deployments, MegaFlow successfully orchestrates tens of thousands of concurrent agent tasks while maintaining high system stability and achieving efficient resource utilization. By enabling such large-scale agent training, MegaFlow addresses a critical infrastructure gap in the emerging agentic AI landscape.</p> + https://arxiv.org/abs/2601.07526 + Mon, 12 Jan 2026 13:25:33 +0000 - Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling - https://arxiv.org/abs/2601.02346 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02346.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Falcon LLM Team, Iheb Chaabane, Puneesh Khanna, Suhail Mohmad, Slim Frikha, Shi Hu, Abdalgader Abubaker, Reda Alami, Mikhail Lubinets, Mohamed El Amine Seddik, Hakim Hacid</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> This work introduces Falcon-H1R, a 7B-parameter reasoning-optimized model that establishes the feasibility of achieving competitive reasoning performance with small language models (SLMs). Falcon-H1R stands out for its parameter efficiency, consistently matching or outperforming SOTA reasoning models that are 2times to 7times larger across a variety of reasoning-intensive benchmarks. These results underscore the importance of careful data curation and targeted training strategies (via both efficient SFT and RL scaling) in delivering significant performance gains without increasing model size. Furthermore, Falcon-H1R advances the 3D limits of reasoning efficiency by combining faster inference (through its hybrid-parallel architecture design), token efficiency, and higher accuracy. This unique blend makes Falcon-H1R-7B a practical backbone for scaling advanced reasoning systems, particularly in scenarios requiring extensive chain-of-thoughts generation and parallel test-time scaling. Leveraging the recently introduced DeepConf approach, Falcon-H1R achieves state-of-the-art test-time scaling efficiency, offering substantial improvements in both accuracy and computational cost. As a result, Falcon-H1R demonstrates that compact models, through targeted model training and architectural choices, can deliver robust and scalable reasoning performance.</p> - https://arxiv.org/abs/2601.02346 - Mon, 05 Jan 2026 18:44:27 +0000 + TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts + https://arxiv.org/abs/2601.08881 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Xu, Hongbin Yan, Juan Cao, Yiji Cheng, Tiankai Hang, Runze He, Zijin Yin, Shiyi Zhang, Yuxin Zhang, Jintao Li, Chunyu Wang, Qinglin Lu, Tong-Yee Lee, Fan Tang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise between conflicting objectives (e.g., local editing v.s. subject-driven generation). While the sparse Mixture-of-Experts (MoE) paradigm is a promising solution, its gating networks remain task-agnostic, operating based on local features, unaware of global task intent. This task-agnostic nature prevents meaningful specialization and fails to resolve the underlying task interference. In this paper, we propose a novel framework to inject semantic intent into MoE routing. We introduce a Hierarchical Task Semantic Annotation scheme to create structured task descriptors (e.g., scope, type, preservation). We then design Predictive Alignment Regularization to align internal routing decisions with the task's high-level semantics. This regularization evolves the gating network from a task-agnostic executor to a dispatch center. Our model effectively mitigates task interference, outperforming dense baselines in fidelity and quality, and our analysis shows that experts naturally develop clear and semantically correlated specializations.</p> + https://arxiv.org/abs/2601.08881 + Mon, 12 Jan 2026 14:52:45 +0000 - Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes - https://arxiv.org/abs/2601.02356 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02356.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Tan, Zhaoyang Zhang, Yantao Shen, Jiarui Cai, Shuo Yang, Jiajun Wu, Wei Xia, Zhuowen Tu, Stefano Soatto</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for multimodal generation systems. While existing text-based manipulation methods can adjust appearance or style, they struggle to perform object-level geometric transformations-such as translating, rotating, or resizing objects-due to scarce paired supervision and pixel-level optimization limits. Talk2Move employs Group Relative Policy Optimization (GRPO) to explore geometric actions through diverse rollouts generated from input images and lightweight textual variations, removing the need for costly paired data. A spatial reward guided model aligns geometric transformations with linguistic description, while off-policy step evaluation and active step sampling improve learning efficiency by focusing on informative transformation stages. Furthermore, we design object-centric spatial rewards that evaluate displacement, rotation, and scaling behaviors directly, enabling interpretable and coherent transformations. Experiments on curated benchmarks demonstrate that Talk2Move achieves precise, consistent, and semantically faithful object transformations, outperforming existing text-guided editing approaches in both spatial accuracy and scene coherence.</p> - https://arxiv.org/abs/2601.02356 - Mon, 05 Jan 2026 18:55:32 +0000 + Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning + https://arxiv.org/abs/2601.07641 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07641.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxuan Lu, Ziyu Kong, Yemin Wang, Rong Fu, Haiyuan Wan, Cheng Yang, Wenjie Lou, Haoran Sun, Lilong Wang, Yankai Jiang, Xiaosong Wang, Xiao Sun, Dongzhan Zhou</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that fundamentally fails in scientific domains where tools are sparse, heterogeneous, and intrinsically incomplete. In this paper, we propose Test-Time Tool Evolution (TTE), a new paradigm that enables agents to synthesize, verify, and evolve executable tools during inference. By transforming tools from fixed resources into problem-driven artifacts, TTE overcomes the rigidity and long-tail limitations of static tool libraries. To facilitate rigorous evaluation, we introduce SciEvo, a benchmark comprising 1,590 scientific reasoning tasks supported by 925 automatically evolved tools. Extensive experiments show that TTE achieves state-of-the-art performance in both accuracy and tool efficiency, while enabling effective cross-domain adaptation of computational tools. The code and benchmark have been released at https://github.com/lujiaxuan0520/Test-Time-Tool-Evol.</p> + https://arxiv.org/abs/2601.07641 + Mon, 12 Jan 2026 15:22:51 +0000 - VINO: A Unified Visual Generator with Interleaved OmniModal Context - https://arxiv.org/abs/2601.02358 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02358.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyi Chen, Tong He, Zhoujie Fu, Pengfei Wan, Kun Gai, Weicai Ye</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> We present VINO, a unified visual generator that performs image and video generation and editing within a single framework. Instead of relying on task-specific models or independent modules for each modality, VINO uses a shared diffusion backbone that conditions on text, images and videos, enabling a broad range of visual creation and editing tasks under one model. Specifically, VINO couples a vision-language model (VLM) with a Multimodal Diffusion Transformer (MMDiT), where multimodal inputs are encoded as interleaved conditioning tokens, and then used to guide the diffusion process. This design supports multi-reference grounding, long-form instruction following, and coherent identity preservation across static and dynamic content, while avoiding modality-specific architectural components. To train such a unified system, we introduce a multi-stage training pipeline that progressively expands a video generation base model into a unified, multi-task generator capable of both image and video input and output. Across diverse generation and editing benchmarks, VINO demonstrates strong visual quality, faithful instruction following, improved reference and attribute preservation, and more controllable multi-identity edits. Our results highlight a practical path toward scalable unified visual generation, and the promise of interleaved, in-context computation as a foundation for general-purpose visual creation.</p> - https://arxiv.org/abs/2601.02358 - Mon, 05 Jan 2026 18:56:34 +0000 + OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent + https://arxiv.org/abs/2601.07779 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Qingyun Li, Yian Wang, Yu Qiao, Zun Wang, Zichen Ding</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalization in novel domains. These limitations stem from a lack of granular control over historical visual context curation and the absence of visual-aware tutorial retrieval. To bridge these gaps, we introduce OS-Symphony, a holistic framework that comprises an Orchestrator coordinating two key innovations for robust automation: (1) a Reflection-Memory Agent that utilizes milestone-driven long-term memory to enable trajectory-level self-correction, effectively mitigating visual context loss in long-horizon tasks; (2) Versatile Tool Agents featuring a Multimodal Searcher that adopts a SeeAct paradigm to navigate a browser-based sandbox to synthesize live, visually aligned tutorials, thereby resolving fidelity issues in unseen scenarios. Experimental results demonstrate that OS-Symphony delivers substantial performance gains across varying model scales, establishing new state-of-the-art results on three online benchmarks, notably achieving 65.84% on OSWorld.</p> + https://arxiv.org/abs/2601.07779 + Mon, 12 Jan 2026 17:55:51 +0000 - ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors - https://arxiv.org/abs/2601.02359 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02359.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaede Shiohara, Toshihiko Yamasaki, Vladislav Golyanik</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Detecting unknown deepfake manipulations remains one of the most challenging problems in face forgery detection. Current state-of-the-art approaches fail to generalize to unseen manipulations, as they primarily rely on supervised training with existing deepfakes or pseudo-fakes, which leads to overfitting to specific forgery patterns. In contrast, self-supervised methods offer greater potential for generalization, but existing work struggles to learn discriminative representations only from self-supervision. In this paper, we propose ExposeAnyone, a fully self-supervised approach based on a diffusion model that generates expression sequences from audio. The key idea is, once the model is personalized to specific subjects using reference sets, it can compute the identity distances between suspected videos and personalized subjects via diffusion reconstruction errors, enabling person-of-interest face forgery detection. Extensive experiments demonstrate that 1) our method outperforms the previous state-of-the-art method by 4.22 percentage points in the average AUC on DF-TIMIT, DFDCP, KoDF, and IDForge datasets, 2) our model is also capable of detecting Sora2-generated videos, where the previous approaches perform poorly, and 3) our method is highly robust to corruptions such as blur and compression, highlighting the applicability in real-world face forgery detection.</p> - https://arxiv.org/abs/2601.02359 - Mon, 05 Jan 2026 18:59:54 +0000 + MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head + https://arxiv.org/abs/2601.07832 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.07832.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kewei Zhang, Ye Huang, Yufan Deng, Jincheng Yu, Junsong Chen, Huan Ling, Enze Xie, Daquan Zhou</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades performance, with existing fixes typically re-introducing computational overhead through extra modules (e.g., depthwise separable convolution) that defeat the original purpose. In this work, we identify a key failure mode in these methods: global context collapse, where the model loses representational diversity. To address this, we propose Multi-Head Linear Attention (MHLA), which preserves this diversity by computing attention within divided heads along the token dimension. We prove that MHLA maintains linear complexity while recovering much of the expressive power of softmax attention, and verify its effectiveness across multiple domains, achieving a 3.6\% improvement on ImageNet classification, a 6.3\% gain on NLP, a 12.6\% improvement on image generation, and a 41\% enhancement on video generation under the same time complexity.</p> + https://arxiv.org/abs/2601.07832 + Mon, 12 Jan 2026 18:59:18 +0000 - SimpleMem: Efficient Lifelong Memory for LLM Agents - https://arxiv.org/abs/2601.02553 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02553.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Liu, Yaofeng Su, Peng Xia, Siwei Han, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> To support reliable long-term interaction in complex environments, LLM agents require memory systems that efficiently manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which applies entropy-aware filtering to distill unstructured interactions into compact, multi-view indexed memory units; (2) Recursive Memory Consolidation, an asynchronous process that integrates related units into higher-level abstract representations to reduce redundancy; and (3) Adaptive Query-Aware Retrieval, which dynamically adjusts retrieval scope based on query complexity to construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% while reducing inference-time token consumption by up to 30-fold, demonstrating a superior balance between performance and efficiency. Code is available at https://github.com/aiming-lab/SimpleMem.</p> - https://arxiv.org/abs/2601.02553 - Mon, 05 Jan 2026 21:02:49 +0000 + MemoBrain: Executive Memory as an Agentic Brain for Reasoning + https://arxiv.org/abs/2601.08079 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongjin Qian, Zhao Cao, Zheng Liu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory mechanisms, such accumulation disrupts logical continuity and undermines task alignment. This positions memory not as an auxiliary efficiency concern, but as a core component for sustaining coherent, goal-directed reasoning over long horizons. We propose MemoBrain, an executive memory model for tool-augmented agents that constructs a dependency-aware memory over reasoning steps, capturing salient intermediate states and their logical relations. Operating as a co-pilot alongside the reasoning agent, MemoBrain organizes reasoning progress without blocking execution and actively manages the working context. Specifically, it prunes invalid steps, folds completed sub-trajectories, and preserves a compact, high-salience reasoning backbone under a fixed context budget. Together, these mechanisms enable explicit cognitive control over reasoning trajectories rather than passive context accumulation. We evaluate MemoBrain on challenging long-horizon benchmarks, including GAIA, WebWalker, and BrowseComp-Plus, demonstrating consistent improvements over strong baselines.</p> + https://arxiv.org/abs/2601.08079 + Mon, 12 Jan 2026 23:44:59 +0000 - Learning User Preferences Through Interaction for Long-Term Collaboration - https://arxiv.org/abs/2601.02702 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02702.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuhaib Mehri, Priyanka Kargupta, Tal August, Dilek Hakkani-Tür</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> As conversational agents accumulate experience collaborating with users, adapting to user preferences is essential for fostering long-term relationships and improving collaboration quality over time. We introduce MultiSessionCollab, a benchmark that evaluates how well agents can learn user preferences and leverage them to improve collaboration quality throughout multiple sessions. To develop agents that succeed in this setting, we present long-term collaborative agents equipped with a memory that persists and refines user preference as interaction experience accumulates. Moreover, we demonstrate that learning signals can be derived from user simulator behavior in MultiSessionCollab to train agents to generate more comprehensive reflections and update their memory more effectively. Extensive experiments show that equipping agents with memory improves long-term collaboration, yielding higher task success rates, more efficient interactions, and reduced user effort. Finally, we conduct a human user study that demonstrates that memory helps improve user experience in real-world settings.</p> - https://arxiv.org/abs/2601.02702 - Tue, 06 Jan 2026 04:26:22 +0000 + The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios + https://arxiv.org/abs/2601.08173 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08173.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daocheng Fu, Jianbiao Mei, Rong Wu, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce , a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. Unlike traditional benchmarks, evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv</p> + https://arxiv.org/abs/2601.08173 + Tue, 13 Jan 2026 03:09:18 +0000 - MiMo-V2-Flash Technical Report - https://arxiv.org/abs/2601.02780 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02780.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bangjun Xiao, Bingquan Xia, Bo Yang, Bofei Gao, Bowen Shen, Chen Zhang, Chenhong He, Chiheng Lou, Fuli Luo, Gang Wang, Gang Xie, Hailin Zhang, Hanglong Lv, Hanyu Li, Heyu Chen, Hongshen Xu, Houbin Zhang, Huaqiu Liu, Jiangshan Duo, Jianyu Wei, Jiebao Xiao, Jinhao Dong, Jun Shi, Junhao Hu, Kainan Bao, Kang Zhou, Lei Li, Liang Zhao, Linghao Zhang, Peidian Li, Qianli Chen, Shaohui Liu, Shihua Yu, Shijie Cao, Shimao Chen, Shouqiu Yu, Shuo Liu, Tianling Zhou, Weijiang Su, Weikun Wang, Wenhan Ma, Xiangwei Deng, Bohan Mao, Bowen Ye, Can Cai, Chenghua Wang, Chengxuan Zhu, Chong Ma, Chun Chen, Chunan Li, Dawei Zhu, Deshan Xiao, Dong Zhang, Duo Zhang, Fangyue Liu, Feiyu Yang, Fengyuan Shi, Guoan Wang, Hao Tian, Hao Wu, Heng Qu, Hongfei Yi, Hongxu An, Hongyi Guan, Xing Zhang, Yifan Song, Yihan Yan, Yihao Zhao, Yingchun Lai, Yizhao Gao, Yu Cheng, Yuanyuan Tian, Yudong Wang, Zhen Tang, Zhengju Tang, Zhengtao Wen, Zhichao Song, Zhixian Zheng, Zihan Jiang, Jian Wen, Jiarui Sun, Jiawei Li, Jinlong Xue, Jun Xia, Kai Fang, Menghang Zhu, Nuo Chen, Qian Tu, Qihao Zhang, Qiying Wang, Rang Li, Rui Ma, Shaolei Zhang, Shengfan Wang, Shicheng Li, Shuhao Gu, Shuhuai Ren, Sirui Deng, Tao Guo, Tianyang Lu, Weiji Zhuang, Weikang Zhang, Weimin Xiong, Wenshan Huang, Wenyu Yang, Xin Zhang, Xing Yong, Xu Wang, Xueyang Xie, Yilin Jiang, Yixin Yang, Yongzhe He, Yu Tu, Yuanliang Dong, Yuchen Liu, Yue Ma, Yue Yu, Yuxing Xiang, Zhaojun Huang, Zhenru Lin, Zhipeng Xu, Zhiyang Chen, Zhonghua Deng, Zihan Zhang, Zihao Yue</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-V2-Flash adopts a hybrid attention architecture that interleaves Sliding Window Attention (SWA) with global attention, with a 128-token sliding window under a 5:1 hybrid ratio. The model is pre-trained on 27 trillion tokens with Multi-Token Prediction (MTP), employing a native 32k context length and subsequently extended to 256k. To efficiently scale post-training compute, MiMo-V2-Flash introduces a novel Multi-Teacher On-Policy Distillation (MOPD) paradigm. In this framework, domain-specialized teachers (e.g., trained via large-scale reinforcement learning) provide dense and token-level reward, enabling the student model to perfectly master teacher expertise. MiMo-V2-Flash rivals top-tier open-weight models such as DeepSeek-V3.2 and Kimi-K2, despite using only 1/2 and 1/3 of their total parameters, respectively. During inference, by repurposing MTP as a draft model for speculative decoding, MiMo-V2-Flash achieves up to 3.6 acceptance length and 2.6x decoding speedup with three MTP layers. We open-source both the model weights and the three-layer MTP weights to foster open research and community collaboration.</p> - https://arxiv.org/abs/2601.02780 - Tue, 06 Jan 2026 07:31:47 +0000 + User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale + https://arxiv.org/abs/2601.08225 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08225.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jungho Cho, Minbyul Jeong, Sungrae Park</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> The recent paradigm shift toward large reasoning models (LRMs) as autonomous agents has intensified the demand for sophisticated, multi-turn tool-use capabilities. Yet, existing datasets and data-generation approaches are limited by static, predefined toolsets that cannot scale to the complexity of open-ended human-agent collaboration. To address this, we initially developed a framework for automated task-oriented multi-turn dialogue generation at scale, utilizing an LRM-based simulator to dynamically generate high-value, domain-specific tools to solve specified tasks. However, we observe that a purely task-oriented design often results in "solely task-solving" trajectories, where the agent completes the objective with minimal interaction, failing to generate the high turn-count conversations seen in realistic scenarios. To bridge this gap, we shift toward a user-oriented simulation paradigm. By decoupling task generation from a dedicated user simulator that mimics human behavioral rules - such as incremental request-making and turn-by-turn feedback - we facilitate more authentic, extended multi-turn dialogues that reflect the iterative nature of real-world problem solving. Our generation pipeline operates as a versatile, plug-and-play module capable of initiating generation from any state, ensuring high scalability in producing extended tool-use data. Furthermore, by facilitating multiple task completions within a single trajectory, it yields a high-density dataset that reflects the multifaceted demands of real-world human-agent interaction.</p> + https://arxiv.org/abs/2601.08225 + Tue, 13 Jan 2026 05:14:09 +0000 - DreamStyle: A Unified Framework for Video Stylization - https://arxiv.org/abs/2601.02785 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02785.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengtian Li, Jinshu Chen, Songtao Zhao, Wanquan Feng, Pengqi Tu, Qian He</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Video stylization, an important downstream task of video generation models, has not yet been thoroughly explored. Its input style conditions typically include text, style image, and stylized first frame. Each condition has a characteristic advantage: text is more flexible, style image provides a more accurate visual anchor, and stylized first frame makes long-video stylization feasible. However, existing methods are largely confined to a single type of style condition, which limits their scope of application. Additionally, their lack of high-quality datasets leads to style inconsistency and temporal flicker. To address these limitations, we introduce DreamStyle, a unified framework for video stylization, supporting (1) text-guided, (2) style-image-guided, and (3) first-frame-guided video stylization, accompanied by a well-designed data curation pipeline to acquire high-quality paired video data. DreamStyle is built on a vanilla Image-to-Video (I2V) model and trained using a Low-Rank Adaptation (LoRA) with token-specific up matrices that reduces the confusion among different condition tokens. Both qualitative and quantitative evaluations demonstrate that DreamStyle is competent in all three video stylization tasks, and outperforms the competitors in style consistency and video quality.</p> - https://arxiv.org/abs/2601.02785 - Tue, 06 Jan 2026 07:42:12 +0000 + SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices + https://arxiv.org/abs/2601.08303 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08303.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongting Hu, Aarush Gupta, Magzhan Gabidolla, Arpit Sahni, Huseyin Coskun, Yanyu Li, Yerlan Idelbayev, Ahsan Mahmood, Aleksei Lebedev, Dishani Lahiri, Anujraaj Goyal, Ju Hu, Mingming Gong, Sergey Tulyakov, Anil Kag</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT framework tailored for mobile and edge devices that achieves transformer-level generation quality under strict resource constraints. Our design combines three key components. First, we propose a compact DiT architecture with an adaptive global-local sparse attention mechanism that balances global context modeling and local detail preservation. Second, we propose an elastic training framework that jointly optimizes sub-DiTs of varying capacities within a unified supernetwork, allowing a single model to dynamically adjust for efficient inference across different hardware. Finally, we develop Knowledge-Guided Distribution Matching Distillation, a step-distillation pipeline that integrates the DMD objective with knowledge transfer from few-step teacher models, producing high-fidelity and low-latency generation (e.g., 4-step) suitable for real-time on-device use. Together, these contributions enable scalable, efficient, and high-quality diffusion models for deployment on diverse hardware.</p> + https://arxiv.org/abs/2601.08303 + Tue, 13 Jan 2026 07:46:46 +0000 - Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy - https://arxiv.org/abs/2601.02989 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02989.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hosein Hasani, Mohammadali Banayeeanzade, Ali Nafisi, Sadegh Mohammadian, Fatemeh Askari, Mobin Bagherian, Amirmohammad Izadi, Mahdieh Soleymani Baghshah</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language models (LLMs), despite strong performance on complex mathematical problems, exhibit systematic limitations in counting tasks. This issue arises from architectural limits of transformers, where counting is performed across layers, leading to degraded precision for larger counting problems due to depth constraints. To address this limitation, we propose a simple test-time strategy inspired by System-2 cognitive processes that decomposes large counting tasks into smaller, independent sub-problems that the model can reliably solve. We evaluate this approach using observational and causal mediation analyses to understand the underlying mechanism of this System-2-like strategy. Our mechanistic analysis identifies key components: latent counts are computed and stored in the final item representations of each part, transferred to intermediate steps via dedicated attention heads, and aggregated in the final stage to produce the total count. Experimental results demonstrate that this strategy enables LLMs to surpass architectural limitations and achieve high accuracy on large-scale counting tasks. This work provides mechanistic insight into System-2 counting in LLMs and presents a generalizable approach for improving and understanding their reasoning behavior.</p> - https://arxiv.org/abs/2601.02989 - Tue, 06 Jan 2026 12:58:27 +0000 + UM-Text: A Unified Multimodal Model for Image Understanding + https://arxiv.org/abs/2601.08321 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08321.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lichen Ma, Xiaolong Fu, Gaojing Zhou, Zipeng Guo, Ting Zhu, Yichun Liu, Yu Shi, Jason Li, Junshi Huang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus generate visual text that is style-consistent with the image. Previous methods often involve complex steps of specifying the text content and attributes, such as font size, color, and layout, without considering the stylistic consistency with the reference image. To address this, we propose UM-Text, a unified multimodal model for context understanding and visual text editing by natural language instructions. Specifically, we introduce a Visual Language Model (VLM) to process the instruction and reference image, so that the text content and layout can be elaborately designed according to the context information. To generate an accurate and harmonious visual text image, we further propose the UM-Encoder to combine the embeddings of various condition information, where the combination is automatically configured by VLM according to the input instruction. During training, we propose a regional consistency loss to offer more effective supervision for glyph generation on both latent and RGB space, and design a tailored three-stage training strategy to further enhance model performance. In addition, we contribute the UM-DATA-200K, a large-scale visual text image dataset on diverse scenes for model training. Extensive qualitative and quantitative results on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance.</p> + https://arxiv.org/abs/2601.08321 + Tue, 13 Jan 2026 08:18:49 +0000 - Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners - https://arxiv.org/abs/2601.02996 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.02996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihong Liu, Raoyuan Zhao, Hinrich Schütze, Michael A. Hedderich</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large reasoning models (LRMs) achieve strong performance on mathematical reasoning tasks, often attributed to their capability to generate explicit chain-of-thought (CoT) explanations. However, recent work shows that LRMs often arrive at the correct answer before completing these textual reasoning steps, indicating the presence of latent reasoning -- internal, non-verbal computation encoded in hidden states. While this phenomenon has been explored in English, its multilingual behavior remains largely unknown. In this paper, we conduct a systematic investigation of multilingual latent reasoning in LRMs across 11 languages. Using a truncation-based strategy, we examine how the correct answer emerges as the model is given only partial reasoning traces, allowing us to measure stepwise latent prediction formation. Our results reveal clear evidence of multilingual latent reasoning, though unevenly: strong in resource-rich languages, weaker in low-resource ones, and broadly less observable on harder benchmarks. To understand whether these differences reflect distinct internal mechanisms, we further perform representational analyses. Despite surface-level disparities, we find that the internal evolution of predictions is highly consistent across languages and broadly aligns with English -- a pattern suggesting an English-centered latent reasoning pathway.</p> - https://arxiv.org/abs/2601.02996 - Tue, 06 Jan 2026 13:20:17 +0000 + JudgeRLVR: Judge First, Generate Second for Efficient Reasoning + https://arxiv.org/abs/2601.08468 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08468.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangshan Duo, Hanyu Li, Hailin Zhang, Yudong Wang, Sujian Li, Liang Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for reasoning in Large Language Models. However, optimizing solely for final-answer correctness often drives models into aimless, verbose exploration, where they rely on exhaustive trial-and-error tactics rather than structured planning to reach solutions. While heuristic constraints like length penalties can reduce verbosity, they often truncate essential reasoning steps, creating a difficult trade-off between efficiency and verification. In this paper, we argue that discriminative capability is a prerequisite for efficient generation: by learning to distinguish valid solutions, a model can internalize a guidance signal that prunes the search space. We propose JudgeRLVR, a two-stage judge-then-generate paradigm. In the first stage, we train the model to judge solution responses with verifiable answers. In the second stage, we fine-tune the same model with vanilla generating RLVR initialized from the judge. Compared to Vanilla RLVR using the same math-domain training data, JudgeRLVR achieves a better quality--efficiency trade-off for Qwen3-30B-A3B: on in-domain math, it delivers about +3.7 points average accuracy gain with -42\% average generation length; on out-of-domain benchmarks, it delivers about +4.5 points average accuracy improvement, demonstrating enhanced generalization.</p> + https://arxiv.org/abs/2601.08468 + Tue, 13 Jan 2026 11:47:42 +0000 - Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts - https://arxiv.org/abs/2601.03315 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03315.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dhruv Trehan, Paras Chopra</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We report a case study of four end-to-end attempts to autonomously generate ML research papers using a pipeline of six LLM agents mapped to stages of the scientific workflow. Of these four, three attempts failed during implementation or evaluation. One completed the pipeline and was accepted to Agents4Science 2025, an experimental inaugural venue that required AI systems as first authors, passing both human and multi-AI review. From these attempts, we document six recurring failure modes: bias toward training data defaults, implementation drift under execution pressure, memory and context degradation across long-horizon tasks, overexcitement that declares success despite obvious failures, insufficient domain intelligence, and weak scientific taste in experimental design. We conclude by discussing four design principles for more robust AI-scientist systems, implications for autonomous scientific discovery, and we release all prompts, artifacts, and outputs at https://github.com/Lossfunk/ai-scientist-artefacts-v1</p> - https://arxiv.org/abs/2601.03315 - Tue, 06 Jan 2026 13:20:54 +0000 + Ministral 3 + https://arxiv.org/abs/2601.08584 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08584.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian, Victor Jouault, Abhinav Rastogi, Adrien Sadé, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Amélie Héliou, Amos You, Andy Ehrenberg, Andy Lo, Anton Eliseev, Antonia Calvi, Avinash Sooriyarachchi, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Clémence Lanfranchi, Corentin Barreau, Cyprien Courtot, Daniele Grattarola, Darius Dabert, Diego de las Casas, Elliot Chane-Sane, Faruk Ahmed, Gabrielle Berrada, Gaëtan Ecrepont, Gauthier Guinet, Georgii Novikov, Guillaume Kunsch, Guillaume Lample, Guillaume Martin, Gunshi Gupta, Jan Ludziejewski, Jason Rute, Joachim Studnia, Jonas Amar, Joséphine Delas, Josselin Somerville Roberts, Karmesh Yadav, Khyathi Chandu, Kush Jain, Laurence Aitchison, Laurent Fainsin, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Margaret Jennings, Marie Pellat, Mark Prins, Mathieu Poirée, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mia Chiquier, Michel Schimpf, Nathan Grinsztajn, Neha Gupta, Nikhil Raghuraman, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Patrick von Platen, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Pavankumar Reddy Muddireddy, Philomène Chagniot, Pierre Stock, Pravesh Agrawal, Quentin Torroba, Romain Sauvestre, Roman Soletskyi, Rupert Menneer, Sagar Vaze, Samuel Barry, Sanchit Gandhi, Siddhant Waghjale, Siddharth Gandhi, Soham Ghosh, Srijan Mishra, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Théo Cachet, Theo Simon Sorg, Thibaut Lavril, Thiziri Nait Saada, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Bewley, Tom Edwards, Umar Jamil, Umberto Tomasini, Valeriia Nemychnikova, Van Phung, Vincent Maladière, Virgile Richard, Wassim Bouaziz, Wen-Ding Li, William Marshall, Xinghui Li, Xinyu Yang, Yassine El Ouahidi, Yihan Wang, Yunhao Tang, Zaccharie Ramzi</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> We introduce the Ministral 3 series, a family of parameter-efficient dense language models designed for compute and memory constrained applications, available in three model sizes: 3B, 8B, and 14B parameters. For each model size, we release three variants: a pretrained base model for general-purpose use, an instruction finetuned, and a reasoning model for complex problem-solving. In addition, we present our recipe to derive the Ministral 3 models through Cascade Distillation, an iterative pruning and continued training with distillation technique. Each model comes with image understanding capabilities, all under the Apache 2.0 license.</p> + https://arxiv.org/abs/2601.08584 + Tue, 13 Jan 2026 14:06:03 +0000 - SOP: A Scalable Online Post-Training System for Vision-Language-Action Models - https://arxiv.org/abs/2601.03044 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03044.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingjie Pan, Siyuan Feng, Qinglin Zhang, Xinchen Li, Jianheng Song, Chendi Qu, Yi Wang, Chuankang Li, Ziyu Xiong, Zhi Chen, Yi Liu, Jianlan Luo</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality. Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific, limiting effective on-policy adaptation and scalable learning from real-world interaction. We introduce a Scalable Online Post-training (SOP) system that enables online, distributed, multi-task post-training of generalist VLA models directly in the physical world. SOP tightly couples execution and learning through a closed-loop architecture in which a fleet of robots continuously streams on-policy experience and human intervention signals to a centralized cloud learner, and asynchronously receives updated policies. This design supports prompt on-policy correction, scales experience collection through parallel deployment, and preserves generality during adaptation. SOP is agnostic to the choice of post-training algorithm; we instantiate it with both interactive imitation learning (HG-DAgger) and reinforcement learning (RECAP). Across a range of real-world manipulation tasks including cloth folding, box assembly, and grocery restocking, we show that SOP substantially improves the performance of large pretrained VLA models while maintaining a single shared policy across tasks. Effective post-training can be achieved within hours of real-world interaction, and performance scales near-linearly with the number of robots in the fleet. These results suggest that tightly coupling online learning with fleet-scale deployment is instrumental to enabling efficient, reliable, and scalable post-training of generalist robot policies in the physical world.</p> - https://arxiv.org/abs/2601.03044 - Tue, 06 Jan 2026 14:25:11 +0000 + End-to-End Video Character Replacement without Structural Guidance + https://arxiv.org/abs/2601.08587 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08587.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengbo Xu, Jie Ma, Ziheng Wang, Zhan Peng, Jun Liang, Jing Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Controllable video character replacement with a user-provided identity remains a challenging problem due to the lack of paired video data. Prior works have predominantly relied on a reconstruction-based paradigm that requires per-frame segmentation masks and explicit structural guidance (e.g., skeleton, depth). This reliance, however, severely limits their generalizability in complex scenarios involving occlusions, character-object interactions, unusual poses, or challenging illumination, often leading to visual artifacts and temporal inconsistencies. In this paper, we propose MoCha, a pioneering framework that bypasses these limitations by requiring only a single arbitrary frame mask. To effectively adapt the multi-modal input condition and enhance facial identity, we introduce a condition-aware RoPE and employ an RL-based post-training stage. Furthermore, to overcome the scarcity of qualified paired-training data, we propose a comprehensive data construction pipeline. Specifically, we design three specialized datasets: a high-fidelity rendered dataset built with Unreal Engine 5 (UE5), an expression-driven dataset synthesized by current portrait animation techniques, and an augmented dataset derived from existing video-mask pairs. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches. We will release the code to facilitate further research. Please refer to our project page for more details: orange-3dv-team.github.io/MoCha</p> + https://arxiv.org/abs/2601.08587 + Tue, 13 Jan 2026 14:10:34 +0000 - One Sample to Rule Them All: Extreme Data Efficiency in RL Scaling - https://arxiv.org/abs/2601.03111 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03111.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiyuan Li, Zhen Huang, Yanan Wu, Weixun Wang, Xuefeng Li, Yijia Luo, Wenbo Su, Bo Zheng, Pengfei Liu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of existing RL attempts in LLMs usually relies on high-quality samples of thousands or beyond. In this paper, we challenge fundamental assumptions about data requirements in RL for LLMs by demonstrating the remarkable effectiveness of one-shot learning. Specifically, we introduce polymath learning, a framework for designing one training sample that elicits multidisciplinary impact. We present three key findings: (1) A single, strategically selected math reasoning sample can produce significant performance improvements across multiple domains, including physics, chemistry, and biology with RL; (2) The math skills salient to reasoning suggest the characteristics of the optimal polymath sample; and (3) An engineered synthetic sample that integrates multidiscipline elements outperforms training with individual samples that naturally occur. Our approach achieves superior performance to training with larger datasets across various reasoning benchmarks, demonstrating that sample quality and design, rather than quantity, may be the key to unlock enhanced reasoning capabilities in language models. Our results suggest a shift, dubbed as sample engineering, toward precision engineering of training samples rather than simply increasing data volume.</p> - https://arxiv.org/abs/2601.03111 - Tue, 06 Jan 2026 15:41:35 +0000 + ExpSeek: Self-Triggered Experience Seeking for Web Agents + https://arxiv.org/abs/2601.08605 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, Yongbin Li</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insights from accumulated experiences. However, existing methods predominantly inject experience passively as global context before task execution, struggling to adapt to dynamically changing contextual observations during agent-environment interaction. We propose ExpSeek, which shifts experience toward step-level proactive seeking: (1) estimating step-level entropy thresholds to determine intervention timing using the model's intrinsic signals; (2) designing step-level tailor-designed experience content. Experiments on Qwen3-8B and 32B models across four challenging web agent benchmarks demonstrate that ExpSeek achieves absolute improvements of 9.3% and 7.5%, respectively. Our experiments validate the feasibility and advantages of entropy as a self-triggering signal, reveal that even a 4B small-scale experience model can significantly boost the performance of larger agent models.</p> + https://arxiv.org/abs/2601.08605 + Tue, 13 Jan 2026 14:48:34 +0000 - Unified Thinker: A General Reasoning Modular Core for Image Generation - https://arxiv.org/abs/2601.03127 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03127.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Despite impressive progress in high-fidelity image synthesis, generative models still struggle with logic-intensive instruction following, exposing a persistent reasoning--execution gap. Meanwhile, closed-source systems (e.g., Nano Banana) have demonstrated strong reasoning-driven image generation, highlighting a substantial gap to current open-source models. We argue that closing this gap requires not merely better visual generators, but executable reasoning: decomposing high-level intents into grounded, verifiable plans that directly steer the generative process. To this end, we propose Unified Thinker, a task-agnostic reasoning architecture for general image generation, designed as a unified planning core that can plug into diverse generators and workflows. Unified Thinker decouples a dedicated Thinker from the image Generator, enabling modular upgrades of reasoning without retraining the entire generative model. We further introduce a two-stage training paradigm: we first build a structured planning interface for the Thinker, then apply reinforcement learning to ground its policy in pixel-level feedback, encouraging plans that optimize visual correctness over textual plausibility. Extensive experiments on text-to-image generation and image editing show that Unified Thinker substantially improves image reasoning and generation quality.</p> - https://arxiv.org/abs/2601.03127 - Tue, 06 Jan 2026 15:59:33 +0000 + ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios + https://arxiv.org/abs/2601.08620 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> António Loison, Quentin Macé, Antoine Edy, Victor Xing, Tom Balough, Gabriel Moreira, Bo Liu, Manuel Faysse, Céline Hudelot, Gautier Viaud</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) pipelines must address challenges beyond simple single-document retrieval, such as interpreting visual elements (tables, charts, images), synthesizing information across documents, and providing accurate source grounding. Existing benchmarks fail to capture this complexity, often focusing on textual data, single-document comprehension, or evaluating retrieval and generation in isolation. We introduce ViDoRe v3, a comprehensive multimodal RAG benchmark featuring multi-type queries over visually rich document corpora. It covers 10 datasets across diverse professional domains, comprising ~26,000 document pages paired with 3,099 human-verified queries, each available in 6 languages. Through 12,000 hours of human annotation effort, we provide high-quality annotations for retrieval relevance, bounding box localization, and verified reference answers. Our evaluation of state-of-the-art RAG pipelines reveals that visual retrievers outperform textual ones, late-interaction models and textual reranking substantially improve performance, and hybrid or purely visual contexts enhance answer generation quality. However, current models still struggle with non-textual elements, open-ended queries, and fine-grained visual grounding. To encourage progress in addressing these challenges, the benchmark is released under a commercially permissive license at https://hf.co/vidore.</p> + https://arxiv.org/abs/2601.08620 + Tue, 13 Jan 2026 15:00:33 +0000 - Parallel Latent Reasoning for Sequential Recommendation - https://arxiv.org/abs/2601.03153 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03153.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiakai Tang, Xu Chen, Wen Chen, Jian Wu, Yuning Jiang, Bo Zheng</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Capturing complex user preferences from sparse behavioral sequences remains a fundamental challenge in sequential recommendation. Recent latent reasoning methods have shown promise by extending test-time computation through multi-step reasoning, yet they exclusively rely on depth-level scaling along a single trajectory, suffering from diminishing returns as reasoning depth increases. To address this limitation, we propose Parallel Latent Reasoning (PLR), a novel framework that pioneers width-level computational scaling by exploring multiple diverse reasoning trajectories simultaneously. PLR constructs parallel reasoning streams through learnable trigger tokens in continuous latent space, preserves diversity across streams via global reasoning regularization, and adaptively synthesizes multi-stream outputs through mixture-of-reasoning-streams aggregation. Extensive experiments on three real-world datasets demonstrate that PLR substantially outperforms state-of-the-art baselines while maintaining real-time inference efficiency. Theoretical analysis further validates the effectiveness of parallel reasoning in improving generalization capability. Our work opens new avenues for enhancing reasoning capacity in sequential recommendation beyond existing depth scaling.</p> - https://arxiv.org/abs/2601.03153 - Tue, 06 Jan 2026 16:25:48 +0000 + VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory + https://arxiv.org/abs/2601.08665 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08665.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaoan Wang, Yuanfei Luo, Xingyu Chen, Aocheng Luo, Dongyue Li, Chang Liu, Sheng Chen, Yangang Zhang, Junzhi Yu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> VLA models have shown promising potential in embodied navigation by unifying perception and planning while inheriting the strong generalization abilities of large VLMs. However, most existing VLA models rely on reactive mappings directly from observations to actions, lacking the explicit reasoning capabilities and persistent memory required for complex, long-horizon navigation tasks. To address these challenges, we propose VLingNav, a VLA model for embodied navigation grounded in linguistic-driven cognition. First, inspired by the dual-process theory of human cognition, we introduce an adaptive chain-of-thought mechanism, which dynamically triggers explicit reasoning only when necessary, enabling the agent to fluidly switch between fast, intuitive execution and slow, deliberate planning. Second, to handle long-horizon spatial dependencies, we develop a visual-assisted linguistic memory module that constructs a persistent, cross-modal semantic memory, enabling the agent to recall past observations to prevent repetitive exploration and infer movement trends for dynamic environments. For the training recipe, we construct Nav-AdaCoT-2.9M, the largest embodied navigation dataset with reasoning annotations to date, enriched with adaptive CoT annotations that induce a reasoning paradigm capable of adjusting both when to think and what to think about. Moreover, we incorporate an online expert-guided reinforcement learning stage, enabling the model to surpass pure imitation learning and to acquire more robust, self-explored navigation behaviors. Extensive experiments demonstrate that VLingNav achieves state-of-the-art performance across a wide range of embodied navigation benchmarks. Notably, VLingNav transfers to real-world robotic platforms in a zero-shot manner, executing various navigation tasks and demonstrating strong cross-domain and cross-task generalization.</p> + https://arxiv.org/abs/2601.08665 + Tue, 13 Jan 2026 15:43:43 +0000 - UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision - https://arxiv.org/abs/2601.03193 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruiyan Han, Zhen Fang, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage such internal knowledge for high-quality generation. We formalize this discrepancy as Conduction Aphasia, a phenomenon where models accurately interpret multimodal inputs but struggle to translate that understanding into faithful and controllable synthesis. To address this, we propose UniCorn, a simple yet elegant self-improvement framework that eliminates the need for external data or teacher supervision. By partitioning a single UMM into three collaborative roles: Proposer, Solver, and Judge, UniCorn generates high-quality interactions via self-play and employs cognitive pattern reconstruction to distill latent understanding into explicit generative signals. To validate the restoration of multimodal coherence, we introduce UniCycle, a cycle-consistency benchmark based on a Text to Image to Text reconstruction loop. Extensive experiments demonstrate that UniCorn achieves comprehensive and substantial improvements over the base model across six general image generation benchmarks. Notably, it achieves SOTA performance on TIIF(73.8), DPG(86.8), CompBench(88.5), and UniCycle while further delivering substantial gains of +5.0 on WISE and +6.5 on OneIG. These results highlight that our method significantly enhances T2I generation while maintaining robust comprehension, demonstrating the scalability of fully self-supervised refinement for unified multimodal intelligence.</p> - https://arxiv.org/abs/2601.03193 - Tue, 06 Jan 2026 17:15:50 +0000 + Parallel Context-of-Experts Decoding for Retrieval Augmented Generation + https://arxiv.org/abs/2601.08670 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08670.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Giulio Corallo, Paolo Papotti</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Retrieval Augmented Generation faces a trade-off: concatenating documents in a long prompt enables multi-document reasoning but creates prefill bottlenecks, while encoding document KV caches separately offers speed but breaks cross-document interaction. We propose Parallel Context-of-Experts Decoding (Pced), a training-free framework that shifts evidence aggregation from the attention mechanism to the decoding. Pced treats retrieved documents as isolated "experts", synchronizing their predictions via a novel retrieval-aware contrastive decoding rule that weighs expert logits against the model prior. This approach recovers cross-document reasoning capabilities without constructing a shared attention across documents.</p> + https://arxiv.org/abs/2601.08670 + Tue, 13 Jan 2026 15:46:59 +0000 - LTX-2: Efficient Joint Audio-Visual Foundation Model - https://arxiv.org/abs/2601.03233 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoav HaCohen, Benny Brazowski, Nisan Chiprut, Yaki Bitterman, Andrew Kvochko, Avishai Berkowitz, Daniel Shalem, Daphna Lifschitz, Dudu Moshe, Eitan Porat, Eitan Richardson, Guy Shiran, Itay Chachy, Jonathan Chetboun, Michael Finkelson, Michael Kupchick, Nir Zabari, Nitzan Guetta, Noa Kotler, Ofir Bibi, Ori Gordon, Poriya Panet, Roi Benita, Shahar Armon, Victor Kulikov, Yaron Inger, Yonatan Shiftan, Zeev Melumian, Zeev Farbman</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Recent text-to-video diffusion models can generate compelling video sequences, yet they remain silent -- missing the semantic, emotional, and atmospheric cues that audio provides. We introduce LTX-2, an open-source foundational model capable of generating high-quality, temporally synchronized audiovisual content in a unified manner. LTX-2 consists of an asymmetric dual-stream transformer with a 14B-parameter video stream and a 5B-parameter audio stream, coupled through bidirectional audio-video cross-attention layers with temporal positional embeddings and cross-modality AdaLN for shared timestep conditioning. This architecture enables efficient training and inference of a unified audiovisual model while allocating more capacity for video generation than audio generation. We employ a multilingual text encoder for broader prompt understanding and introduce a modality-aware classifier-free guidance (modality-CFG) mechanism for improved audiovisual alignment and controllability. Beyond generating speech, LTX-2 produces rich, coherent audio tracks that follow the characters, environment, style, and emotion of each scene -- complete with natural background and foley elements. In our evaluations, the model achieves state-of-the-art audiovisual quality and prompt adherence among open-source systems, while delivering results comparable to proprietary models at a fraction of their computational cost and inference time. All model weights and code are publicly released.</p> - https://arxiv.org/abs/2601.03233 - Tue, 06 Jan 2026 18:24:41 +0000 + Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs + https://arxiv.org/abs/2601.08763 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Hu, Yucheng Wang, Yufei He, Jiaying Wu, Yilun Zhao, See-Kiong Ng, Cynthia Breazeal, Anh Tuan Luu, Hae Won Park, Bryan Hooi</p><p><b>Upvotes:</b> 125</p><p><b>Summary:</b> Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from exploration collapse: policies prematurely concentrate on a small set of dominant reasoning patterns, improving pass@1 while limiting rollout-level diversity and gains in pass@k. We argue that this failure stems from regularizing local token behavior rather than diversity over sets of solutions. To address this, we propose Uniqueness-Aware Reinforcement Learning, a rollout-level objective that explicitly rewards correct solutions that exhibit rare high-level strategies. Our method uses an LLM-based judge to cluster rollouts for the same problem according to their high-level solution strategies, ignoring superficial variations, and reweights policy advantages inversely with cluster size. As a result, correct but novel strategies receive higher rewards than redundant ones. Across mathematics, physics, and medical reasoning benchmarks, our approach consistently improves pass@k across large sampling budgets and increases the area under the pass@k curve (AUC@K) without sacrificing pass@1, while sustaining exploration and uncovering more diverse solution strategies at scale.</p> + https://arxiv.org/abs/2601.08763 + Tue, 13 Jan 2026 17:48:43 +0000 - MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents - https://arxiv.org/abs/2601.03236 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03236.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongming Jiang, Yi Li, Guanpeng Li, Bingzhe Li</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretability and alignment between query intent and retrieved evidence, leading to suboptimal reasoning accuracy. In this paper, we propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across orthogonal semantic, temporal, causal, and entity graphs. MAGMA formulates retrieval as policy-guided traversal over these relational views, enabling query-adaptive selection and structured context construction. By decoupling memory representation from retrieval logic, MAGMA provides transparent reasoning paths and fine-grained control over retrieval. Experiments on LoCoMo and LongMemEval demonstrate that MAGMA consistently outperforms state-of-the-art agentic memory systems in long-horizon reasoning tasks.</p> - https://arxiv.org/abs/2601.03236 - Tue, 06 Jan 2026 18:29:43 +0000 + Motion Attribution for Video Generation + https://arxiv.org/abs/2601.08828 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08828.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xindi Wu, Despoina Paschalidou, Jun Gao, Antonio Torralba, Laura Leal-Taixé, Olga Russakovsky, Sanja Fidler, Jonathan Lorraine</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework that scales to modern, large, high-quality video datasets and models. We use this to study which fine-tuning clips improve or degrade temporal dynamics. Motive isolates temporal dynamics from static appearance via motion-weighted loss masks, yielding efficient and scalable motion-specific influence computation. On text-to-video models, Motive identifies clips that strongly affect motion and guides data curation that improves temporal consistency and physical plausibility. With Motive-selected high-influence data, our method improves both motion smoothness and dynamic degree on VBench, achieving a 74.1% human preference win rate compared with the pretrained base model. To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models and to use it to curate fine-tuning data.</p> + https://arxiv.org/abs/2601.08828 + Tue, 13 Jan 2026 18:59:09 +0000 - InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields - https://arxiv.org/abs/2601.03252 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03252.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Yu, Haotong Lin, Jiawei Wang, Jiaxin Li, Yida Wang, Xueyang Zhang, Yue Wang, Xiaowei Zhou, Ruizhen Hu, Sida Peng</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> Existing depth estimation methods are fundamentally limited to predicting depth on discrete image grids. Such representations restrict their scalability to arbitrary output resolutions and hinder the geometric detail recovery. This paper introduces InfiniDepth, which represents depth as neural implicit fields. Through a simple yet effective local implicit decoder, we can query depth at continuous 2D coordinates, enabling arbitrary-resolution and fine-grained depth estimation. To better assess our method's capabilities, we curate a high-quality 4K synthetic benchmark from five different games, spanning diverse scenes with rich geometric and appearance details. Extensive experiments demonstrate that InfiniDepth achieves state-of-the-art performance on both synthetic and real-world benchmarks across relative and metric depth estimation tasks, particularly excelling in fine-detail regions. It also benefits the task of novel view synthesis under large viewpoint shifts, producing high-quality results with fewer holes and artifacts.</p> - https://arxiv.org/abs/2601.03252 - Tue, 06 Jan 2026 18:57:06 +0000 + 3AM: Segment Anything with Geometric Consistency in Videos + https://arxiv.org/abs/2601.08831 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08831.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang-Che Sun, Cheng Sun, Chin-Yang Lin, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional 3D instance segmentation methods address viewpoint consistency but require camera poses, depth maps, and expensive preprocessing. We introduce 3AM, a training-time enhancement that integrates 3D-aware features from MUSt3R into SAM2. Our lightweight Feature Merger fuses multi-level MUSt3R features that encode implicit geometric correspondence. Combined with SAM2's appearance features, the model achieves geometry-consistent recognition grounded in both spatial position and visual similarity. We propose a field-of-view aware sampling strategy ensuring frames observe spatially consistent object regions for reliable 3D correspondence learning. Critically, our method requires only RGB input at inference, with no camera poses or preprocessing. On challenging datasets with wide-baseline motion (ScanNet++, Replica), 3AM substantially outperforms SAM2 and extensions, achieving 90.6% IoU and 71.7% Positive IoU on ScanNet++'s Selected Subset, improving over state-of-the-art VOS methods by +15.9 and +30.4 points. Project page: https://jayisaking.github.io/3AM-Page/</p> + https://arxiv.org/abs/2601.08831 + Tue, 13 Jan 2026 18:59:54 +0000 - Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training - https://arxiv.org/abs/2601.03256 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03256.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hexiao Lu, Xiaokun Sun, Zeyu Cai, Hao Guo, Ying Tai, Jian Yang, Zhenyu Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We present Muses, the first training-free method for fantastic 3D creature generation in a feed-forward paradigm. Previous methods, which rely on part-aware optimization, manual assembly, or 2D image generation, often produce unrealistic or incoherent 3D assets due to the challenges of intricate part-level manipulation and limited out-of-domain generation. In contrast, Muses leverages the 3D skeleton, a fundamental representation of biological forms, to explicitly and rationally compose diverse elements. This skeletal foundation formalizes 3D content creation as a structure-aware pipeline of design, composition, and generation. Muses begins by constructing a creatively composed 3D skeleton with coherent layout and scale through graph-constrained reasoning. This skeleton then guides a voxel-based assembly process within a structured latent space, integrating regions from different objects. Finally, image-guided appearance modeling under skeletal conditions is applied to generate a style-consistent and harmonious texture for the assembled shape. Extensive experiments establish Muses' state-of-the-art performance in terms of visual fidelity and alignment with textual descriptions, and potential on flexible 3D object editing. Project page: https://luhexiao.github.io/Muses.github.io/.</p> - https://arxiv.org/abs/2601.03256 - Tue, 06 Jan 2026 18:59:57 +0000 + Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models + https://arxiv.org/abs/2601.08955 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youwei Liu, Jian Wang, Hanlin Wang, Beichen Guo, Wenjie Li</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon rollouts, leaving their potential for complex task planning under-exploited. We propose Imagine-then-Plan (ITP), a unified framework for agent learning via lookahead imagination, where an agent's policy model interacts with the learned world model, yielding multi-step ``imagined'' trajectories. Since the imagination horizon may vary by tasks and stages, we introduce a novel adaptive lookahead mechanism by trading off the ultimate goal and task progress. The resulting imagined trajectories provide rich signals about future consequences, such as achieved progress and potential conflicts, which are fused with current observations, formulating a partially observable and imaginable Markov decision process to guide policy learning. We instantiate ITP with both training-free and reinforcement-trained variants. Extensive experiments across representative agent benchmarks demonstrate that ITP significantly outperforms competitive baselines. Further analyses validate that our adaptive lookahead largely enhances agents' reasoning capability, providing valuable insights into addressing broader, complex tasks.</p> + https://arxiv.org/abs/2601.08955 + Tue, 13 Jan 2026 19:49:58 +0000 - Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views - https://arxiv.org/abs/2601.03362 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03362.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiang Zhang, Yang Zhang, Lukas Mehl, Markus Gross, Christopher Schroers</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Soft boundaries, like thin hairs, are commonly observed in natural and computer-generated imagery, but they remain challenging for 3D vision due to the ambiguous mixing of foreground and background cues. This paper introduces Guardians of the Hair (HairGuard), a framework designed to recover fine-grained soft boundary details in 3D vision tasks. Specifically, we first propose a novel data curation pipeline that leverages image matting datasets for training and design a depth fixer network to automatically identify soft boundary regions. With a gated residual module, the depth fixer refines depth precisely around soft boundaries while maintaining global depth quality, allowing plug-and-play integration with state-of-the-art depth models. For view synthesis, we perform depth-based forward warping to retain high-fidelity textures, followed by a generative scene painter that fills disoccluded regions and eliminates redundant background artifacts within soft boundaries. Finally, a color fuser adaptively combines warped and inpainted results to produce novel views with consistent geometry and fine-grained details. Extensive experiments demonstrate that HairGuard achieves state-of-the-art performance across monocular depth estimation, stereo image/video conversion, and novel view synthesis, with significant improvements in soft boundary regions.</p> - https://arxiv.org/abs/2601.03362 - Tue, 06 Jan 2026 19:02:34 +0000 + TranslateGemma Technical Report + https://arxiv.org/abs/2601.09012 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mara Finkelstein, Isaac Caswell, Tobias Domhan, Jan-Thorsten Peter, Juraj Juraska, Parker Riley, Daniel Deutsch, Cole Dilanni, Colin Cherry, Eleftheria Briakou, Elizabeth Nielsen, Jiaming Luo, Kat Black, Ryan Mullins, Sweta Agrawal, Wenda Xu, Erin Kats, Stephane Jaskiewicz, Markus Freitag, David Vilar</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We present TranslateGemma, a suite of open machine translation models based on the Gemma 3 foundation models. To enhance the inherent multilingual capabilities of Gemma 3 for the translation task, we employ a two-stage fine-tuning process. First, supervised fine-tuning is performed using a rich mixture of high-quality large-scale synthetic parallel data generated via state-of-the-art models and human-translated parallel data. This is followed by a reinforcement learning phase, where we optimize translation quality using an ensemble of reward models, including MetricX-QE and AutoMQM, targeting translation quality. We demonstrate the effectiveness of TranslateGemma with human evaluation on the WMT25 test set across 10 language pairs and with automatic evaluation on the WMT24++ benchmark across 55 language pairs. Automatic metrics show consistent and substantial gains over the baseline Gemma 3 models across all sizes. Notably, smaller TranslateGemma models often achieve performance comparable to larger baseline models, offering improved efficiency. We also show that TranslateGemma models retain strong multimodal capabilities, with enhanced performance on the Vistra image translation benchmark. The release of the open TranslateGemma models aims to provide the research community with powerful and adaptable tools for machine translation.</p> + https://arxiv.org/abs/2601.09012 + Tue, 13 Jan 2026 22:23:24 +0000 - The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models - https://arxiv.org/abs/2601.03425 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03425.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Wang, Yitao Xu, Nanhan Shen, Jinyan Su, Jimin Huang, Zining Zhu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumption by introducing COMMITTEEAUDIT, a post hoc framework that analyzes routing behavior at the level of expert groups rather than individual experts. Across three representative models and the MMLU benchmark, we uncover a domain-invariant Standing Committee. This is a compact coalition of routed experts that consistently captures the majority of routing mass across domains, layers, and routing budgets, even when architectures already include shared experts. Qualitative analysis further shows that Standing Committees anchor reasoning structure and syntax, while peripheral experts handle domain-specific knowledge. These findings reveal a strong structural bias toward centralized computation, suggesting that specialization in Mixture of Experts models is far less pervasive than commonly believed. This inherent bias also indicates that current training objectives, such as load-balancing losses that enforce uniform expert utilization, may be working against the model's natural optimization path, thereby limiting training efficiency and performance.</p> - https://arxiv.org/abs/2601.03425 - Tue, 06 Jan 2026 21:29:45 +0000 + OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG + https://arxiv.org/abs/2601.09028 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09028.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fengran Mo, Zhan Su, Yuchen Hui, Jinghan Zhang, Jia Ao Sun, Zheyuan Liu, Chao Zhang, Tetsuya Sakai, Jian-Yun Nie</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> The development of large language models (LLMs) has achieved superior performance in a range of downstream tasks, including LLM-based retrieval-augmented generation (RAG). The quality of generated content heavily relies on the usefulness of the retrieved information and the capacity of LLMs' internal information processing mechanism to incorporate it in answer generation. It is generally assumed that the retrieved information is relevant to the question. However, the retrieved information may have a variable degree of relevance and usefulness, depending on the question and the document collection. It is important to take into account the relevance of the retrieved information in answer generation. In this paper, we propose OpenDecoder, a new approach that leverages explicit evaluation of the retrieved information as quality indicator features for generation. We aim to build a RAG model that is more robust to varying levels of noisy context. Three types of explicit evaluation information are considered: relevance score, ranking score, and QPP (query performance prediction) score. The experimental results on five benchmark datasets demonstrate the effectiveness and better robustness of OpenDecoder by outperforming various baseline methods. Importantly, this paradigm is flexible to be integrated with the post-training of LLMs for any purposes and incorporated with any type of external indicators.</p> + https://arxiv.org/abs/2601.09028 + Tue, 13 Jan 2026 23:26:30 +0000 - Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks - https://arxiv.org/abs/2601.03448 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Atsuki Yamaguchi, Maggie Mi, Nikolaos Aletras</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning of world knowledge and reasoning, it does not explicitly optimize for linguistic competence. To bridge this gap, we propose L2T, a pre-training framework integrating Language Learning Tasks alongside standard next-token prediction. Inspired by human language acquisition, L2T transforms raw text into structured input-output pairs to provide explicit linguistic stimulation. Pre-training LMs on a mixture of raw text and L2T data not only improves overall performance on linguistic competence benchmarks but accelerates its acquisition, while maintaining competitive performance on general reasoning tasks.</p> - https://arxiv.org/abs/2601.03448 - Tue, 06 Jan 2026 22:28:15 +0000 + Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning + https://arxiv.org/abs/2601.09088 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09088.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaotian Yan, Kaiyuan Liu, Chen Shen, Bing Wang, Sinan Fan, Jun Zhang, Yue Wu, Zheng Wang, Jieping Ye</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> In this report, we introduce DASD-4B-Thinking, a lightweight yet highly capable, fully open-source reasoning model. It achieves SOTA performance among open-source models of comparable scale across challenging benchmarks in mathematics, scientific reasoning, and code generation -- even outperforming several larger models. We begin by critically reexamining a widely adopted distillation paradigm in the community: SFT on teacher-generated responses, also known as sequence-level distillation. Although a series of recent works following this scheme have demonstrated remarkable efficiency and strong empirical performance, they are primarily grounded in the SFT perspective. Consequently, these approaches focus predominantly on designing heuristic rules for SFT data filtering, while largely overlooking the core principle of distillation itself -- enabling the student model to learn the teacher's full output distribution so as to inherit its generalization capability. Specifically, we identify three critical limitations in current practice: i) Inadequate representation of the teacher's sequence-level distribution; ii) Misalignment between the teacher's output distribution and the student's learning capacity; and iii) Exposure bias arising from teacher-forced training versus autoregressive inference. In summary, these shortcomings reflect a systemic absence of explicit teacher-student interaction throughout the distillation process, leaving the essence of distillation underexploited. To address these issues, we propose several methodological innovations that collectively form an enhanced sequence-level distillation training pipeline. Remarkably, DASD-4B-Thinking obtains competitive results using only 448K training samples -- an order of magnitude fewer than those employed by most existing open-source efforts. To support community research, we publicly release our models and the training dataset.</p> + https://arxiv.org/abs/2601.09088 + Wed, 14 Jan 2026 02:43:17 +0000 - ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing - https://arxiv.org/abs/2601.03467 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03467.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengjia Li, Liming Jiang, Qing Yan, Yizhi Song, Hao Kang, Zichuan Liu, Xin Lu, Boxi Wu, Deng Cai</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning (RL) has been investigated for improving the quality of image editing, but it faces three key challenges: (1) limited reasoning exploration confined to denoising stochasticity, (2) biased reward fusion, and (3) unstable VLM-based instruction rewards. In this work, we propose ThinkRL-Edit, a reasoning-centric RL framework that decouples visual reasoning from image synthesis and expands reasoning exploration beyond denoising. To the end, we introduce Chain-of-Thought (CoT)-based reasoning sampling with planning and reflection stages prior to generation in online sampling, compelling the model to explore multiple semantic hypotheses and validate their plausibility before committing to a visual outcome. To avoid the failures of weighted aggregation, we propose an unbiased chain preference grouping strategy across multiple reward dimensions. Moreover, we replace interval-based VLM scores with a binary checklist, yielding more precise, lower-variance, and interpretable rewards for complex reasoning. Experiments show our method significantly outperforms prior work on reasoning-centric image editing, producing instruction-faithful, visually coherent, and semantically grounded edits.</p> - https://arxiv.org/abs/2601.03467 - Tue, 06 Jan 2026 23:43:00 +0000 + SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL + https://arxiv.org/abs/2601.09136 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lijun Liu, Linwei Chen, Zhishou Zhang, Meng Tian, Hengfu Cui, Ruiyang Li, Zhaocheng Liu, Qiang Ju, Qianxi Li, Hong-Yu Zhou</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> General-purpose Large Vision-Language Models (LVLMs), despite their massive scale, often falter in dermatology due to "diffuse attention" - the inability to disentangle subtle pathological lesions from background noise. In this paper, we challenge the assumption that parameter scaling is the only path to medical precision. We introduce SkinFlow, a framework that treats diagnosis as an optimization of visual information transmission efficiency. Our approach utilizes a Virtual-Width Dynamic Vision Encoder (DVE) to "unfold" complex pathological manifolds without physical parameter expansion, coupled with a two-stage Reinforcement Learning strategy. This strategy sequentially aligns explicit medical descriptions (Stage I) and reconstructs implicit diagnostic textures (Stage II) within a constrained semantic space. Furthermore, we propose a clinically grounded evaluation protocol that prioritizes diagnostic safety and hierarchical relevance over rigid label matching. Empirical results are compelling: our 7B model establishes a new state-of-the-art on the Fitzpatrick17k benchmark, achieving a +12.06% gain in Top-1 accuracy and a +28.57% boost in Top-6 accuracy over the massive general-purpose models (e.g., Qwen3VL-235B and GPT-5.2). These findings demonstrate that optimizing geometric capacity and information flow yields superior diagnostic reasoning compared to raw parameter scaling.</p> + https://arxiv.org/abs/2601.09136 + Wed, 14 Jan 2026 04:21:07 +0000 - EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering for Enhanced Alignment and Reasoning - https://arxiv.org/abs/2601.03471 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03471.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyang Wei, Dehai Min, Zewen Liu, Yuzhang Xie, Guanchen Wu, Carl Yang, Max S. Y. Lau, Qi He, Lu Cheng, Wei Jin</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reliable epidemiological reasoning requires synthesizing study evidence to infer disease burden, transmission dynamics, and intervention effects at the population level. Existing medical question answering benchmarks primarily emphasize clinical knowledge or patient-level reasoning, yet few systematically evaluate evidence-grounded epidemiological inference. We present EpiQAL, the first diagnostic benchmark for epidemiological question answering across diverse diseases, comprising three subsets built from open-access literature. The subsets respectively evaluate text-grounded factual recall, multi-step inference linking document evidence with epidemiological principles, and conclusion reconstruction with the Discussion section withheld. Construction combines expert-designed taxonomy guidance, multi-model verification, and retrieval-based difficulty control. Experiments on ten open models reveal that current LLMs show limited performance on epidemiological reasoning, with multi-step inference posing the greatest challenge. Model rankings shift across subsets, and scale alone does not predict success. Chain-of-Thought prompting benefits multi-step inference but yields mixed results elsewhere. EpiQAL provides fine-grained diagnostic signals for evidence grounding, inferential reasoning, and conclusion reconstruction.</p> - https://arxiv.org/abs/2601.03471 - Tue, 06 Jan 2026 23:49:10 +0000 + EvasionBench: Detecting Evasive Answers in Financial Q&A via Multi-Model Consensus and LLM-as-Judge + https://arxiv.org/abs/2601.09142 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09142.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijian Ma, Yan Lin, Yi Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Detecting evasive answers in earnings calls is critical for financial transparency, yet progress is hindered by the lack of large-scale benchmarks. We introduce EvasionBench, comprising 30,000 training samples and 1,000 human-annotated test samples (Cohen's Kappa 0.835) across three evasion levels. Our key contribution is a multi-model annotation framework leveraging a core insight: disagreement between frontier LLMs signals hard examples most valuable for training. We mine boundary cases where two strong annotators conflict, using a judge to resolve labels. This approach outperforms single-model distillation by 2.4 percent, with judge-resolved samples improving generalization despite higher training loss (0.421 vs 0.393) - evidence that disagreement mining acts as implicit regularization. Our trained model Eva-4B (4B parameters) achieves 81.3 percent accuracy, outperforming its base by 25 percentage points and approaching frontier LLM performance at a fraction of inference cost.</p> + https://arxiv.org/abs/2601.09142 + Wed, 14 Jan 2026 04:26:43 +0000 - Evolving Programmatic Skill Networks - https://arxiv.org/abs/2601.03509 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03509.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haochen Shi, Xingdi Yuan, Bang Liu</p><p><b>Upvotes:</b> 71</p><p><b>Summary:</b> We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)REFLECT for structured fault localization over skill compositions, (2) progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3) canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.\footnote{We plan to open-source the code.</p> - https://arxiv.org/abs/2601.03509 - Wed, 07 Jan 2026 01:43:25 +0000 + Geometric Stability: The Missing Axis of Representations + https://arxiv.org/abs/2601.09173 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09173.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prashant C. Raju</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Analysis of learned representations has a blind spot: it focuses on similarity, measuring how closely embeddings align with external references, but similarity reveals only what is represented, not whether that structure is robust. We introduce geometric stability, a distinct dimension that quantifies how reliably representational geometry holds under perturbation, and present Shesha, a framework for measuring it. Across 2,463 configurations in seven domains, we show that stability and similarity are empirically uncorrelated (ρapprox 0.01) and mechanistically distinct: similarity metrics collapse after removing the top principal components, while stability retains sensitivity to fine-grained manifold structure. This distinction yields actionable insights: for safety monitoring, stability acts as a functional geometric canary, detecting structural drift nearly 2times more sensitively than CKA while filtering out the non-functional noise that triggers false alarms in rigid distance metrics; for controllability, supervised stability predicts linear steerability (ρ= 0.89-0.96); for model selection, stability dissociates from transferability, revealing a geometric tax that transfer optimization incurs. Beyond machine learning, stability predicts CRISPR perturbation coherence and neural-behavioral coupling. By quantifying how reliably systems maintain structure, geometric stability provides a necessary complement to similarity for auditing representations across biological and computational systems.</p> + https://arxiv.org/abs/2601.09173 + Wed, 14 Jan 2026 05:15:22 +0000 - DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs - https://arxiv.org/abs/2601.03559 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03559.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shidong Cao, Hongzhan Lin, Yuxuan Gu, Ziyang Luo, Jing Ma</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias and error accumulation, as early mistakes propagate irreversibly through autoregressive decoding. In this work, we propose DiffCoT, a diffusion-styled CoT framework that reformulates CoT reasoning as an iterative denoising process. DiffCoT integrates diffusion principles at the reasoning-step level via a sliding-window mechanism, enabling unified generation and retrospective correction of intermediate steps while preserving token-level autoregression. To maintain causal consistency, we further introduce a causal diffusion noise schedule that respects the temporal structure of reasoning chains. Extensive experiments on three multi-step CoT reasoning benchmarks across diverse model backbones demonstrate that DiffCoT consistently outperforms existing CoT preference optimization methods, yielding improved robustness and error-correction capability in CoT reasoning.</p> - https://arxiv.org/abs/2601.03559 - Wed, 07 Jan 2026 03:58:42 +0000 + MAXS: Meta-Adaptive Exploration with LLM Agents + https://arxiv.org/abs/2601.09259 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Yu He, Haoran Luo, li yuan, Lingling Zhang, Rui Mao, Qika Lin, Jun Liu</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer from (i) locally myopic generation, due to the absence of lookahead, and (ii) trajectory instability, where minor early errors can escalate into divergent reasoning paths. These issues make it difficult to balance global effectiveness and computational efficiency. To address these two issues, we propose meta-adaptive exploration with LLM agents https://github.com/exoskeletonzj/MAXS, a meta-adaptive reasoning framework based on LLM Agents that flexibly integrates tool execution and reasoning planning. MAXS employs a lookahead strategy to extend reasoning paths a few steps ahead, estimating the advantage value of tool usage, and combines step consistency variance and inter-step trend slopes to jointly select stable, consistent, and high-value reasoning steps. Additionally, we introduce a trajectory convergence mechanism that controls computational cost by halting further rollouts once path consistency is achieved, enabling a balance between resource efficiency and global effectiveness in multi-tool reasoning. We conduct extensive empirical studies across three base models (MiMo-VL-7B, Qwen2.5-VL-7B, Qwen2.5-VL-32B) and five datasets, demonstrating that MAXS consistently outperforms existing methods in both performance and inference efficiency. Further analysis confirms the effectiveness of our lookahead strategy and tool usage.</p> + https://arxiv.org/abs/2601.09259 + Wed, 14 Jan 2026 07:48:00 +0000 - RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models - https://arxiv.org/abs/2601.03699 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03699.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quy-Anh Dang, Chris Ngo, Truong-Son Hy</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> As large language models (LLMs) become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount. However, existing red teaming datasets suffer from inconsistent risk categorizations, limited domain coverage, and outdated evaluations, hindering systematic vulnerability assessments. To address these challenges, we introduce RedBench, a universal dataset aggregating 37 benchmark datasets from leading conferences and repositories, comprising 29,362 samples across attack and refusal prompts. RedBench employs a standardized taxonomy with 22 risk categories and 19 domains, enabling consistent and comprehensive evaluations of LLM vulnerabilities. We provide a detailed analysis of existing datasets, establish baselines for modern LLMs, and open-source the dataset and evaluation code. Our contributions facilitate robust comparisons, foster future research, and promote the development of secure and reliable LLMs for real-world deployment. Code: https://github.com/knoveleng/redeval</p> - https://arxiv.org/abs/2601.03699 - Wed, 07 Jan 2026 08:34:17 +0000 + A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation + https://arxiv.org/abs/2601.09274 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09274.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Zhang, Yu He, Zhiyuan Wang, Zhangqi Wang, Kai He, Fangzhi Xu, Qika Lin, Jun Liu</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Scientific reasoning relies not only on logical inference but also on activating prior knowledge and experiential structures. Memory can efficiently reuse knowledge and enhance reasoning consistency and stability. However, existing benchmarks mainly evaluate final answers or step-by-step coherence, overlooking the memory-driven mechanisms that underlie human reasoning, which involves activating anchors and attractors, then integrating them into multi-step inference. To address this gap, we propose A^3-Bench~ https://a3-bench.github.io, a benchmark designed to evaluate scientific reasoning through dual-scale memory-driven activation, grounded in Anchor and Attractor Activation. First, we annotate 2,198 science reasoning problems across domains using the SAPM process(subject, anchor & attractor, problem, and memory developing). Second, we introduce a dual-scale memory evaluation framework utilizing anchors and attractors, along with the AAUI(Anchor--Attractor Utilization Index) metric to measure memory activation rates. Finally, through experiments with various base models and paradigms, we validate A^3-Bench and analyze how memory activation impacts reasoning performance, providing insights into memory-driven scientific reasoning.</p> + https://arxiv.org/abs/2601.09274 + Wed, 14 Jan 2026 08:17:41 +0000 - ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition - https://arxiv.org/abs/2601.03822 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03822.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muyang Zhao, Qi Qi, Hao Sun</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computation a task requires. We study budgeted inference-time reasoning for multiple tasks under a strict global token constraint and formalize it as a Ordered Stochastic Multiple-Choice Knapsack Problem(OS-MCKP). This perspective highlights a meta-cognitive requirement -- anticipating task difficulty, estimating return over investment (ROI), and allocating computation strategically. We propose ROI-Reasoning, a two-stage framework that endows LLMs with intrinsic, budget-aware rationality. In the first stage, Meta-Cognitive Fine-Tuning teaches models to predict reasoning cost and expected utility before generation, enabling explicit solve-or-skip decisions. Next, Rationality-Aware Reinforcement Learning optimizes sequential decision making under a hard token budget, allowing models to learn long-horizon allocation strategies. Across budgeted mathematical reasoning benchmarks, ROI-Reasoning consistently improves overall score while substantially reducing regret under tight computation budgets.</p> - https://arxiv.org/abs/2601.03822 - Wed, 07 Jan 2026 11:30:55 +0000 + EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines + https://arxiv.org/abs/2601.09465 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09465.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo Zhang, Chaofa Yuan, Ryan Guo, Xiaomin Yu, Rui Xu, Zhangquan Chen, Zinuo Li, Zhi Yang, Shuhao Guan, Zhenheng Tang, Sen Hu, Liwen Zhang, Ronghao Chen, Huacan Wang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work therefore explores self-evolution by allowing agents to rewrite their own code or prompts to improve problem-solving ability, but unconstrained optimization often triggers instability, hallucinations, and instruction drift. We propose EvoFSM, a structured self-evolving framework that achieves both adaptability and control by evolving an explicit Finite State Machine (FSM) instead of relying on free-form rewriting. EvoFSM decouples the optimization space into macroscopic Flow (state-transition logic) and microscopic Skill (state-specific behaviors), enabling targeted improvements under clear behavioral boundaries. Guided by a critic mechanism, EvoFSM refines the FSM through a small set of constrained operations, and further incorporates a self-evolving memory that distills successful trajectories as reusable priors and failure patterns as constraints for future queries. Extensive evaluations on five multi-hop QA benchmarks demonstrate the effectiveness of EvoFSM. In particular, EvoFSM reaches 58.0% accuracy on the DeepSearch benchmark. Additional results on interactive decision-making tasks further validate its generalization.</p> + https://arxiv.org/abs/2601.09465 + Wed, 14 Jan 2026 13:19:13 +0000 - Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning - https://arxiv.org/abs/2601.03872 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a high-dimensional optimization challenge. Existing approaches often rely on a single model or fixed tool-calling logic, failing to exploit the performance variations across heterogeneous model-tool pairs. In this paper, we present ATLAS (Adaptive Tool-LLM Alignment and Synergistic Invocation), a dual-path framework for dynamic tool usage in cross-domain complex reasoning. ATLAS operates via a dual-path approach: (1) training-free cluster-based routing that exploits empirical priors for domain-specific alignment, and (2) RL-based multi-step routing that explores autonomous trajectories for out-of-distribution generalization. Extensive experiments across 15 benchmarks demonstrate that our method outperforms closed-source models like GPT-4o, surpassing existing routing methods on both in-distribution (+10.1%) and out-of-distribution (+13.1%) tasks. Furthermore, our framework shows significant gains in visual reasoning by orchestrating specialized multi-modal tools.</p> - https://arxiv.org/abs/2601.03872 - Wed, 07 Jan 2026 12:38:33 +0000 + V-DPM: 4D Video Reconstruction with Dynamic Point Maps + https://arxiv.org/abs/2601.09499 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Edgar Sucar, Eldar Insafutdinov, Zihang Lai, Andrea Vedaldi</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Powerful 3D representations such as DUSt3R invariant point maps, which encode 3D shape and camera parameters, have significantly advanced feed forward 3D reconstruction. While point maps assume static scenes, Dynamic Point Maps (DPMs) extend this concept to dynamic 3D content by additionally representing scene motion. However, existing DPMs are limited to image pairs and, like DUSt3R, require post processing via optimization when more than two views are involved. We argue that DPMs are more useful when applied to videos and introduce V-DPM to demonstrate this. First, we show how to formulate DPMs for video input in a way that maximizes representational power, facilitates neural prediction, and enables reuse of pretrained models. Second, we implement these ideas on top of VGGT, a recent and powerful 3D reconstructor. Although VGGT was trained on static scenes, we show that a modest amount of synthetic data is sufficient to adapt it into an effective V-DPM predictor. Our approach achieves state of the art performance in 3D and 4D reconstruction for dynamic scenes. In particular, unlike recent dynamic extensions of VGGT such as P3, DPMs recover not only dynamic depth but also the full 3D motion of every point in the scene.</p> + https://arxiv.org/abs/2601.09499 + Wed, 14 Jan 2026 14:03:42 +0000 - ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation - https://arxiv.org/abs/2601.03955 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Zhang, Cheng Da, Huan Yang, Kun Gai, Ming Lu, Zhan Ma</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent tokens and treating visual data as flat sequential token streams. However, this language-like formulation overlooks key properties of vision, particularly the hierarchical and residual network designs that have long been essential for convergence and efficiency in visual models. To bring "vision" back to vision, we propose the Residual Tokenizer (ResTok), a 1D visual tokenizer that builds hierarchical residuals for both image tokens and latent tokens. The hierarchical representations obtained through progressively merging enable cross-level feature fusion at each layer, substantially enhancing representational capacity. Meanwhile, the semantic residuals between hierarchies prevent information overlap, yielding more concentrated latent distributions that are easier for AR modeling. Cross-level bindings consequently emerge without any explicit constraints. To accelerate the generation process, we further introduce a hierarchical AR generator that substantially reduces sampling steps by predicting an entire level of latent tokens at once rather than generating them strictly token-by-token. Extensive experiments demonstrate that restoring hierarchical residual priors in visual tokenization significantly improves AR image generation, achieving a gFID of 2.34 on ImageNet-256 with only 9 sampling steps. Code is available at https://github.com/Kwai-Kolors/ResTok.</p> - https://arxiv.org/abs/2601.03955 - Wed, 07 Jan 2026 14:09:18 +0000 + OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding + https://arxiv.org/abs/2601.09575 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sheng-Yu Huang, Jaesung Choe, Yu-Chiang Frank Wang, Cheng Sun</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> We propose OpenVoxel, a training-free algorithm for grouping and captioning sparse voxels for the open-vocabulary 3D scene understanding tasks. Given the sparse voxel rasterization (SVR) model obtained from multi-view images of a 3D scene, our OpenVoxel is able to produce meaningful groups that describe different objects in the scene. Also, by leveraging powerful Vision Language Models (VLMs) and Multi-modal Large Language Models (MLLMs), our OpenVoxel successfully build an informative scene map by captioning each group, enabling further 3D scene understanding tasks such as open-vocabulary segmentation (OVS) or referring expression segmentation (RES). Unlike previous methods, our method is training-free and does not introduce embeddings from a CLIP/BERT text encoder. Instead, we directly proceed with text-to-text search using MLLMs. Through extensive experiments, our method demonstrates superior performance compared to recent studies, particularly in complex referring expression segmentation (RES) tasks. The code will be open.</p> + https://arxiv.org/abs/2601.09575 + Wed, 14 Jan 2026 15:45:57 +0000 - Benchmark^2: Systematic Evaluation of LLM Benchmarks - https://arxiv.org/abs/2601.03986 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.03986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qi Qian, Chengsong Huang, Jingwen Xu, Changze Lv, Muling Wu, Wenhao Liu, Xiaohua Wang, Zhenghua Wang, Zisu Huang, Muzhao Tian, Jianhan Xu, Kun Hu, He-Da Wang, Yao Hu, Xuanjing Huang, Xiaoqing Zheng</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> The rapid proliferation of benchmarks for evaluating large language models (LLMs) has created an urgent need for systematic methods to assess benchmark quality itself. We propose Benchmark^2, a comprehensive framework comprising three complementary metrics: (1) Cross-Benchmark Ranking Consistency, measuring whether a benchmark produces model rankings aligned with peer benchmarks; (2) Discriminability Score, quantifying a benchmark's ability to differentiate between models; and (3) Capability Alignment Deviation, identifying problematic instances where stronger models fail but weaker models succeed within the same model family. We conduct extensive experiments across 15 benchmarks spanning mathematics, reasoning, and knowledge domains, evaluating 11 LLMs across four model families. Our analysis reveals significant quality variations among existing benchmarks and demonstrates that selective benchmark construction based on our metrics can achieve comparable evaluation performance with substantially reduced test sets.</p> - https://arxiv.org/abs/2601.03986 - Wed, 07 Jan 2026 14:59:03 +0000 + Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning + https://arxiv.org/abs/2601.09667 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Hu, Yunhai Hu, Juncheng Liu, Shuyue Stella Li, Yucheng Wang, Zhen Xu, See-Kiong Ng, Anh Tuan Luu, Xinxing Xu, Bryan Hooi, Cynthia Breazeal, Hae Won Park</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting teammates induce non-stationarity, and rewards are often sparse and high-variance. Therefore, we introduce Multi-Agent Test-Time Reinforcement Learning (MATTRL), a framework that injects structured textual experience into multi-agent deliberation at inference time. MATTRL forms a multi-expert team of specialists for multi-turn discussions, retrieves and integrates test-time experiences, and reaches consensus for final decision-making. We also study credit assignment for constructing a turn-level experience pool, then reinjecting it into the dialogue. Across challenging benchmarks in medicine, math, and education, MATTRL improves accuracy by an average of 3.67\% over a multi-agent baseline, and by 8.67\% over comparable single-agent baselines. Ablation studies examine different credit-assignment schemes and provide a detailed comparison of how they affect training outcomes. MATTRL offers a stable, effective and efficient path to distribution-shift-robust multi-agent reasoning without tuning.</p> + https://arxiv.org/abs/2601.09667 + Wed, 14 Jan 2026 17:57:43 +0000 - Klear: Unified Multi-Task Audio-Video Joint Generation - https://arxiv.org/abs/2601.04151 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04151.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jun Wang, Chunyu Qiang, Yuxin Guo, Yiran Wang, Xijuan Zeng, Chen Zhang, Pengfei Wan</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Audio-video joint generation has progressed rapidly, yet substantial challenges still remain. Non-commercial approaches still suffer audio-visual asynchrony, poor lip-speech alignment, and unimodal degradation, which can be stemmed from weak audio-visual correspondence modeling, limited generalization, and scarce high-quality dense-caption data. To address these issues, we introduce Klear and delve into three axes--model architecture, training strategy, and data curation. Architecturally, we adopt a single-tower design with unified DiT blocks and an Omni-Full Attention mechanism, achieving tight audio-visual alignment and strong scalability. Training-wise, we adopt a progressive multitask regime--random modality masking to joint optimization across tasks, and a multistage curriculum, yielding robust representations, strengthening A-V aligned world knowledge, and preventing unimodal collapse. For datasets, we present the first large-scale audio-video dataset with dense captions, and introduce a novel automated data-construction pipeline which annotates and filters millions of diverse, high-quality, strictly aligned audio-video-caption triplets. Building on this, Klear scales to large datasets, delivering high-fidelity, semantically and temporally aligned, instruction-following generation in both joint and unimodal settings while generalizing robustly to out-of-distribution scenarios. Across tasks, it substantially outperforms prior methods by a large margin and achieves performance comparable to Veo 3, offering a unified, scalable path toward next-generation audio-video synthesis.</p> - https://arxiv.org/abs/2601.04151 - Wed, 07 Jan 2026 18:03:45 +0000 + STEP3-VL-10B Technical Report + https://arxiv.org/abs/2601.09668 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ailin Huang, Chengyuan Yao, Chunrui Han, Fanqi Wan, Hangyu Guo, Haoran Lv, Hongyu Zhou, Jia Wang, Jian Zhou, Jianjian Sun, Jingcheng Hu, Kangheng Lin, Liang Zhao, Mitt Huang, Song Yuan, Wenwen Qu, Xiangfeng Wang, Yanlin Lai, Yingxiu Zhao, Yinmin Zhang, Yukang Shi, Yuyang Chen, Zejia Weng, Ziyang Meng, Ang Li, Aobo Kong, Bo Dong, Changyi Wan, David Wang, Di Qi, Dingming Li, En Yu, Guopeng Li, Haiquan Yin, Han Zhou, Hanshan Zhang, Haolong Yan, Hebin Zhou, Hongbo Peng, Jiaran Zhang, Jiashu Lv, Jiayi Fu, Jie Cheng, Jie Zhou, Jisheng Yin, Jingjing Xie, Jingwei Wu, Jun Zhang, Junfeng Liu, Kaijun Tan, Kaiwen Yan, Liangyu Chen, Lina Chen, Mingliang Li, Qian Zhao, Quan Sun, Shaoliang Pang, Shengjie Fan, Shijie Shang, Siyuan Zhang, Tianhao You, Wei Ji, Wuxun Xie, Xiaobo Yang, Xiaojie Hou, Xiaoran Jiao, Xiaoxiao Ren, Xiangwen Kong, Xin Huang, Xin Wu, Xing Chen, Xinran Wang, Xuelin Zhang, Yana Wei, Yang Li, Yanming Xu, Yeqing Shen, Yuang Peng, Yue Peng, Yu Zhou, Yusheng Li, Yuxiang Yang, Yuyang Zhang, Zhe Xie, Zhewei Huang, Zhenyi Lu, Zhimin Fan, Zihui Cheng, Daxin Jiang, Qi Han, Xiangyu Zhang, Yibo Zhu, Zheng Ge</p><p><b>Upvotes:</b> 161</p><p><b>Summary:</b> We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-VL-10B is realized through two strategic shifts: first, a unified, fully unfrozen pre-training strategy on 1.2T multimodal tokens that integrates a language-aligned Perception Encoder with a Qwen3-8B decoder to establish intrinsic vision-language synergy; and second, a scaled post-training pipeline featuring over 1k iterations of reinforcement learning. Crucially, we implement Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute, allocating resources to scalable perceptual reasoning that explores and synthesizes diverse visual hypotheses. Consequently, despite its compact 10B footprint, STEP3-VL-10B rivals or surpasses models 10times-20times larger (e.g., GLM-4.6V-106B, Qwen3-VL-235B) and top-tier proprietary flagships like Gemini 2.5 Pro and Seed-1.5-VL. Delivering best-in-class performance, it records 92.2% on MMBench and 80.11% on MMMU, while excelling in complex reasoning with 94.43% on AIME2025 and 75.95% on MathVision. We release the full model suite to provide the community with a powerful, efficient, and reproducible baseline.</p> + https://arxiv.org/abs/2601.09668 + Wed, 14 Jan 2026 17:58:24 +0000 - Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes - https://arxiv.org/abs/2601.04300 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenye Meng, Zejian Li, Zhongni Liu, Yize Li, Changle Xie, Kaixin Jia, Ling Yang, Huanghuang Deng, Shiying Ding, Shengyuan Zhang, Jiayi Li, Lingyun Sun</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is hierarchical and fine-grained. To address this, we first construct a hierarchical, fine-grained evaluation criteria with domain experts, which decomposes image quality into multiple positive and negative attributes organized in a tree structure. Building on this, we propose a two-stage alignment framework. First, we inject domain knowledge to an auxiliary diffusion model via Supervised Fine-Tuning. Second, we introduce Complex Preference Optimization (CPO) that extends DPO to align the target diffusion to our non-binary, hierarchical criteria. Specifically, we reformulate the alignment problem to simultaneously maximize the probability of positive attributes while minimizing the probability of negative attributes with the auxiliary diffusion. We instantiate our approach in the domain of painting generation and conduct CPO training with an annotated dataset of painting with fine-grained attributes based on our criteria. Extensive experiments demonstrate that CPO significantly enhances generation quality and alignment with expertise, opening new avenues for fine-grained criteria alignment.</p> - https://arxiv.org/abs/2601.04300 - Wed, 07 Jan 2026 18:11:22 +0000 + DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation + https://arxiv.org/abs/2601.09688 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09688.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibo Wang, Lei Wang, Yue Deng, Keming Wu, Yao Xiao, Huanjin Yao, Liwei Kang, Hai Ye, Yongcheng Jing, Lidong Bing</p><p><b>Upvotes:</b> 109</p><p><b>Summary:</b> Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require annotation-intensive task construction, rely on static evaluation dimensions, or fail to reliably verify facts when citations are missing. To bridge these gaps, we introduce DeepResearchEval, an automated framework for deep research task construction and agentic evaluation. For task construction, we propose a persona-driven pipeline generating realistic, complex research tasks anchored in diverse user profiles, applying a two-stage filter Task Qualification and Search Necessity to retain only tasks requiring multi-source evidence integration and external retrieval. For evaluation, we propose an agentic pipeline with two components: an Adaptive Point-wise Quality Evaluation that dynamically derives task-specific evaluation dimensions, criteria, and weights conditioned on each generated task, and an Active Fact-Checking that autonomously extracts and verifies report statements via web search, even when citations are missing.</p> + https://arxiv.org/abs/2601.09688 + Wed, 14 Jan 2026 18:38:31 +0000 - Agentic Rubrics as Contextual Verifiers for SWE Agents - https://arxiv.org/abs/2601.04171 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04171.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohit Raghavendra, Anisha Gunjal, Bing Liu, Yunzhong He</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE) agent settings often relies on code execution, which can be difficult to scale due to environment setup overhead. Scalable alternatives such as patch classifiers and heuristic methods exist, but they are less grounded in codebase context and harder to interpret. To this end, we explore Agentic Rubrics: an expert agent interacts with the repository to create a context-grounded rubric checklist, and candidate patches are then scored against it without requiring test execution. On SWE-Bench Verified under parallel TTS evaluation, Agentic Rubrics achieve a score of 54.2% on Qwen3-Coder-30B-A3B and 40.6% on Qwen3-32B, with at least a +3.5 percentage-point gain over the strongest baseline in our comparison set. We further analyze rubric behavior, showing that rubric scores are consistent with ground-truth tests while also flagging issues that tests do not capture. Our ablations show that agentic context gathering is essential for producing codebase-specific, unambiguous criteria. Together, these results suggest that Agentic Rubrics provide an efficient, scalable, and granular verification signal for SWE agents.</p> - https://arxiv.org/abs/2601.04171 - Wed, 07 Jan 2026 18:38:23 +0000 + Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering + https://arxiv.org/abs/2601.09697 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09697.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jieying Chen, Jeffrey Hu, Joan Lasenby, Ayush Tewari</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical barrier to deploying generative video in applications that require real-time interactions, such as embodied AI and VR/AR. This paper explores a new strategy for camera-conditioned video generation of static scenes: using diffusion-based generative models to generate a sparse set of keyframes, and then synthesizing the full video through 3D reconstruction and rendering. By lifting keyframes into a 3D representation and rendering intermediate views, our approach amortizes the generation cost across hundreds of frames while enforcing geometric consistency. We further introduce a model that predicts the optimal number of keyframes for a given camera trajectory, allowing the system to adaptively allocate computation. Our final method, SRENDER, uses very sparse keyframes for simple trajectories and denser ones for complex camera motion. This results in video generation that is more than 40 times faster than the diffusion-based baseline in generating 20 seconds of video, while maintaining high visual fidelity and temporal stability, offering a practical path toward efficient and controllable video synthesis.</p> + https://arxiv.org/abs/2601.09697 + Wed, 14 Jan 2026 18:50:06 +0000 - Choreographing a World of Dynamic Objects - https://arxiv.org/abs/2601.04194 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanzhe Lyu, Chen Geng, Karthik Dharmarajan, Yunzhi Zhang, Hadi Alzayer, Shangzhe Wu, Jiajun Wu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a universal generative pipeline, CHORD, for CHOReographing Dynamic objects and scenes and synthesizing this type of phenomena. Traditional rule-based graphics pipelines to create these dynamics are based on category-specific heuristics, yet are labor-intensive and not scalable. Recent learning-based methods typically demand large-scale datasets, which may not cover all object categories in interest. Our approach instead inherits the universality from the video generative models by proposing a distillation-based pipeline to extract the rich Lagrangian motion information hidden in the Eulerian representations of 2D videos. Our method is universal, versatile, and category-agnostic. We demonstrate its effectiveness by conducting experiments to generate a diverse range of multi-body 4D dynamics, show its advantage compared to existing methods, and demonstrate its applicability in generating robotics manipulation policies. Project page: https://yanzhelyu.github.io/chord</p> - https://arxiv.org/abs/2601.04194 - Wed, 07 Jan 2026 18:59:40 +0000 + Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning + https://arxiv.org/abs/2601.09708 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09708.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz, Yu-Chiang Frank Wang, Fu-En Yang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy reasoning traces. We propose Fast-ThinkAct, an efficient reasoning framework that achieves compact yet performant planning through verbalizable latent reasoning. Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodied control. This enables reasoning-enhanced policy learning that effectively connects compact reasoning to action execution. Extensive experiments across diverse embodied manipulation and reasoning benchmarks demonstrate that Fast-ThinkAct achieves strong performance with up to 89.3\% reduced inference latency over state-of-the-art reasoning VLAs, while maintaining effective long-horizon planning, few-shot adaptation, and failure recovery.</p> + https://arxiv.org/abs/2601.09708 + Wed, 14 Jan 2026 18:59:59 +0000 - ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers - https://arxiv.org/abs/2601.04342 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohsen Ghafoorian, Amirhossein Habibian</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in video diffusion models have shifted towards transformer-based architectures, achieving state-of-the-art video generation but at the cost of quadratic attention complexity, which severely limits scalability for longer sequences. We introduce ReHyAt, a Recurrent Hybrid Attention mechanism that combines the fidelity of softmax attention with the efficiency of linear attention, enabling chunk-wise recurrent reformulation and constant memory usage. Unlike the concurrent linear-only SANA Video, ReHyAt's hybrid design allows efficient distillation from existing softmax-based models, reducing the training cost by two orders of magnitude to ~160 GPU hours, while being competitive in the quality. Our light-weight distillation and finetuning pipeline provides a recipe that can be applied to future state-of-the-art bidirectional softmax-based models. Experiments on VBench and VBench-2.0, as well as a human preference study, demonstrate that ReHyAt achieves state-of-the-art video quality while reducing attention cost from quadratic to linear, unlocking practical scalability for long-duration and on-device video generation. Project page is available at https://qualcomm-ai-research.github.io/rehyat.</p> - https://arxiv.org/abs/2601.04342 - Wed, 07 Jan 2026 19:26:30 +0000 + Transition Matching Distillation for Fast Video Generation + https://arxiv.org/abs/2601.09881 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.09881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weili Nie, Julius Berner, Nanye Ma, Chao Liu, Saining Xie, Arash Vahdat</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work, we present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators. The central idea of TMD is to match the multi-step denoising trajectory of a diffusion model with a few-step probability transition process, where each transition is modeled as a lightweight conditional flow. To enable efficient distillation, we decompose the original diffusion backbone into two components: (1) a main backbone, comprising the majority of early layers, that extracts semantic representations at each outer transition step; and (2) a flow head, consisting of the last few layers, that leverages these representations to perform multiple inner flow updates. Given a pretrained video diffusion model, we first introduce a flow head to the model, and adapt it into a conditional flow map. We then apply distribution matching distillation to the student model with flow head rollout in each transition step. Extensive experiments on distilling Wan2.1 1.3B and 14B text-to-video models demonstrate that TMD provides a flexible and strong trade-off between generation speed and visual quality. In particular, TMD outperforms existing distilled models under comparable inference costs in terms of visual fidelity and prompt adherence. Project page: https://research.nvidia.com/labs/genair/tmd</p> + https://arxiv.org/abs/2601.09881 + Wed, 14 Jan 2026 21:30:03 +0000 - Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing - https://arxiv.org/abs/2601.04575 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuguang Yue, Irakli Salia, Samuel Hunt, Chris Green, Wenzhe Shi, Jonathan J Hunt</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Behavior cloning is enjoying a resurgence in popularity as scaling both model and data sizes proves to provide a strong starting point for many tasks of interest. In this work, we introduce an open recipe for training a video game playing foundation model designed for inference in realtime on a consumer GPU. We release all data (8300+ hours of high quality human gameplay), training and inference code, and pretrained checkpoints under an open license. We show that our best model is capable of playing a variety of 3D video games at a level competitive with human play. We use this recipe to systematically examine the scaling laws of behavior cloning to understand how the model's performance and causal reasoning varies with model and data scale. We first show in a simple toy problem that, for some types of causal reasoning, increasing both the amount of training data and the depth of the network results in the model learning a more causal policy. We then systematically study how causality varies with the number of parameters (and depth) and training steps in scaled models of up to 1.2 billion parameters, and we find similar scaling results to what we observe in the toy problem.</p> - https://arxiv.org/abs/2601.04575 - Thu, 08 Jan 2026 04:06:17 +0000 + CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation + https://arxiv.org/abs/2601.10061 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10061.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengzhuo Tong, Mingkun Chang, Shenglong Zhang, Yuran Wang, Cheng Liang, Zhizheng Zhao, Ruichuan An, Bohan Zeng, Yang Shi, Yifan Dai, Ziming Zhao, Guanbin Li, Pengfei Wan, Yuanxing Zhang, Wentao Zhang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Recent video generation models have revealed the emergence of Chain-of-Frame (CoF) reasoning, enabling frame-by-frame visual inference. With this capability, video models have been successfully applied to various visual tasks (e.g., maze solving, visual puzzles). However, their potential to enhance text-to-image (T2I) generation remains largely unexplored due to the absence of a clearly defined visual reasoning starting point and interpretable intermediate states in the T2I generation process. To bridge this gap, we propose CoF-T2I, a model that integrates CoF reasoning into T2I generation via progressive visual refinement, where intermediate frames act as explicit reasoning steps and the final frame is taken as output. To establish such an explicit generation process, we curate CoF-Evol-Instruct, a dataset of CoF trajectories that model the generation process from semantics to aesthetics. To further improve quality and avoid motion artifacts, we enable independent encoding operation for each frame. Experiments show that CoF-T2I significantly outperforms the base video model and achieves competitive performance on challenging benchmarks, reaching 0.86 on GenEval and 7.468 on Imagine-Bench. These results indicate the substantial promise of video models for advancing high-quality text-to-image generation.</p> + https://arxiv.org/abs/2601.10061 + Thu, 15 Jan 2026 04:33:06 +0000 - AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering - https://arxiv.org/abs/2601.04620 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Di Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While these approaches can raise aggregate scores, they often yield unstable and hard-to-audit improvement trajectories, making it difficult to guarantee non-regression or to reason about failures across versions. We reframe agent improvement as release engineering: agents are treated as shippable artifacts, and improvement is externalized into a regression-aware release pipeline. We introduce AgentDevel, a release engineering pipeline that iteratively runs the current agent, produces implementation-blind, symptom-level quality signals from execution traces, synthesizes a single release candidate (RC) via executable diagnosis, and promotes it under flip-centered gating. AgentDevel features three core designs: (i) an implementation-blind LLM critic that characterizes failure appearances without accessing agent internals, (ii) script-based executable diagnosis that aggregates dominant symptom patterns and produces auditable engineering specifications, and (iii) flip-centered gating that prioritizes pass to fail regressions and fail to pass fixes as first-class evidence. Unlike population-based search or in-agent self-refinement, AgentDevel maintains a single canonical version line and emphasizes non-regression as a primary objective. Experiments on execution-heavy benchmarks demonstrate that AgentDevel yields stable improvements with significantly fewer regressions while producing reproducible, auditable artifacts. Overall, AgentDevel provides a practical development discipline for building, debugging, and releasing LLM agents as software development.</p> - https://arxiv.org/abs/2601.04620 - Thu, 08 Jan 2026 05:49:01 +0000 + Deriving Character Logic from Storyline as Codified Decision Trees + https://arxiv.org/abs/2601.10080 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Letian Peng, Kun Zhou, Longfei Yun, Yupeng Hou, Jingbo Shang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Role-playing (RP) agents rely on behavioral profiles to act consistently across diverse narrative contexts, yet existing profiles are largely unstructured, non-executable, and weakly validated, leading to brittle agent behavior. We propose Codified Decision Trees (CDT), a data-driven framework that induces an executable and interpretable decision structure from large-scale narrative data. CDT represents behavioral profiles as a tree of conditional rules, where internal nodes correspond to validated scene conditions and leaves encode grounded behavioral statements, enabling deterministic retrieval of context-appropriate rules at execution time. The tree is learned by iteratively inducing candidate scene-action rules, validating them against data, and refining them through hierarchical specialization, yielding profiles that support transparent inspection and principled updates. Across multiple benchmarks, CDT substantially outperforms human-written profiles and prior profile induction methods on 85 characters across 16 artifacts, indicating that codified and validated behavioral representations lead to more reliable agent grounding.</p> + https://arxiv.org/abs/2601.10080 + Thu, 15 Jan 2026 05:12:43 +0000 - ProFuse: Efficient Cross-View Context Fusion for Open-Vocabulary 3D Gaussian Splatting - https://arxiv.org/abs/2601.04754 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04754.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yen-Jen Chiou, Wei-Tse Cheng, Yuan-Fu Yang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We present ProFuse, an efficient context-aware framework for open-vocabulary 3D scene understanding with 3D Gaussian Splatting (3DGS). The pipeline enhances cross-view consistency and intra-mask cohesion within a direct registration setup, adding minimal overhead and requiring no render-supervised fine-tuning. Instead of relying on a pretrained 3DGS scene, we introduce a dense correspondence-guided pre-registration phase that initializes Gaussians with accurate geometry while jointly constructing 3D Context Proposals via cross-view clustering. Each proposal carries a global feature obtained through weighted aggregation of member embeddings, and this feature is fused onto Gaussians during direct registration to maintain per-primitive language coherence across views. With associations established in advance, semantic fusion requires no additional optimization beyond standard reconstruction, and the model retains geometric refinement without densification. ProFuse achieves strong open-vocabulary 3DGS understanding while completing semantic attachment in about five minutes per scene, which is two times faster than SOTA.</p> - https://arxiv.org/abs/2601.04754 - Thu, 08 Jan 2026 09:20:46 +0000 + FlowAct-R1: Towards Interactive Humanoid Video Generation + https://arxiv.org/abs/2601.10103 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lizhen Wang, Yongming Zhu, Zhipeng Ge, Youwei Zheng, Longhao Zhang, Tianshu Hu, Shiyang Qin, Mingshuang Luo, Jiaxu Zhang, Xin Chen, Yulong Wang, Zerong Zheng, Jianwen Jiang, Chao Liang, Weifeng Chen, Xing Wang, Yuan Zhang, Mingyuan Gao</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Interactive humanoid video generation aims to synthesize lifelike visual agents that can engage with humans through continuous and responsive video. Despite recent advances in video synthesis, existing methods often grapple with the trade-off between high-fidelity synthesis and real-time interaction requirements. In this paper, we propose FlowAct-R1, a framework specifically designed for real-time interactive humanoid video generation. Built upon a MMDiT architecture, FlowAct-R1 enables the streaming synthesis of video with arbitrary durations while maintaining low-latency responsiveness. We introduce a chunkwise diffusion forcing strategy, complemented by a novel self-forcing variant, to alleviate error accumulation and ensure long-term temporal consistency during continuous interaction. By leveraging efficient distillation and system-level optimizations, our framework achieves a stable 25fps at 480p resolution with a time-to-first-frame (TTFF) of only around 1.5 seconds. The proposed method provides holistic and fine-grained full-body control, enabling the agent to transition naturally between diverse behavioral states in interactive scenarios. Experimental results demonstrate that FlowAct-R1 achieves exceptional behavioral vividness and perceptual realism, while maintaining robust generalization across diverse character styles.</p> + https://arxiv.org/abs/2601.10103 + Thu, 15 Jan 2026 06:16:22 +0000 - AT^2PO: Agentic Turn-based Policy Optimization via Tree Search - https://arxiv.org/abs/2601.04767 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04767.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zefang Zong, Dingwei Chen, Yang Li, Qi Yi, Bo Zhou, Chengming Li, Bo Qian, Peng Chen, Jie Jiang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> LLM agents have emerged as powerful systems for tackling multi-turn tasks by interleaving internal reasoning and external tool interactions. Agentic Reinforcement Learning has recently drawn significant research attention as a critical post-training paradigm to further refine these capabilities. In this paper, we present AT^2PO (Agentic Turn-based Policy Optimization via Tree Search), a unified framework for multi-turn agentic RL that addresses three core challenges: limited exploration diversity, sparse credit assignment, and misaligned policy optimization. AT^2PO introduces a turn-level tree structure that jointly enables Entropy-Guided Tree Expansion for strategic exploration and Turn-wise Credit Assignment for fine-grained reward propagation from sparse outcomes. Complementing this, we propose Agentic Turn-based Policy Optimization, a turn-level learning objective that aligns policy updates with the natural decision granularity of agentic interactions. ATPO is orthogonal to tree search and can be readily integrated into any multi-turn RL pipeline. Experiments across seven benchmarks demonstrate consistent improvements over the state-of-the-art baseline by up to 1.84 percentage points in average, with ablation studies validating the effectiveness of each component. Our code is available at https://github.com/zzfoutofspace/ATPO.</p> - https://arxiv.org/abs/2601.04767 - Thu, 08 Jan 2026 09:35:49 +0000 + LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning + https://arxiv.org/abs/2601.10129 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10129.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linquan Wu, Tianxiang Jiang, Yifei Dong, Haoyu Yang, Fengji Zhang, Shichaang Meng, Ai Xuan, Linqi Song, Jacky Keung</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critical Perception Gap in distillation: student models frequently mimic a teacher's textual output while attending to fundamentally divergent visual regions, effectively relying on language priors rather than grounded perception. To bridge this, we propose LaViT, a framework that aligns latent visual thoughts rather than static embeddings. LaViT compels the student to autoregressively reconstruct the teacher's visual semantics and attention trajectories prior to text generation, employing a curriculum sensory gating mechanism to prevent shortcut learning. Extensive experiments show that LaViT significantly enhances visual grounding, achieving up to +16.9% gains on complex reasoning tasks and enabling a compact 3B model to outperform larger open-source variants and proprietary models like GPT-4o.</p> + https://arxiv.org/abs/2601.10129 + Thu, 15 Jan 2026 07:14:24 +0000 - PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference - https://arxiv.org/abs/2601.04792 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04792.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Denis Korzhenkov, Adil Karjauv, Animesh Karnewar, Mohsen Ghafoorian, Amirhossein Habibian</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recently proposed pyramidal models decompose the conventional forward and backward diffusion processes into multiple stages operating at varying resolutions. These models handle inputs with higher noise levels at lower resolutions, while less noisy inputs are processed at higher resolutions. This hierarchical approach significantly reduces the computational cost of inference in multi-step denoising models. However, existing open-source pyramidal video models have been trained from scratch and tend to underperform compared to state-of-the-art systems in terms of visual plausibility. In this work, we present a pipeline that converts a pretrained diffusion model into a pyramidal one through low-cost finetuning, achieving this transformation without degradation in quality of output videos. Furthermore, we investigate and compare various strategies for step distillation within pyramidal models, aiming to further enhance the inference efficiency. Our results are available at https://qualcomm-ai-research.github.io/PyramidalWan.</p> - https://arxiv.org/abs/2601.04792 - Thu, 08 Jan 2026 10:16:06 +0000 + M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints + https://arxiv.org/abs/2601.10131 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10131.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhan Li, Florence Cloutier, Sifan Wu, Ali Parviz, Boris Knyazev, Yan Zhang, Glen Berseth, Bang Liu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and numeric reasoning without external structure and feedback. We introduce M olGen, a fragment-level, retrieval-augmented, two-stage framework for molecule generation under multi-property constraints. Stage I : Prototype generation: a multi-agent reasoner performs retrieval-anchored, fragment-level edits to produce a candidate near the feasible region. Stage II : RL-based fine-grained optimization: a fragment-level optimizer trained with Group Relative Policy Optimization (GRPO) applies one- or multi-hop refinements to explicitly minimize the property errors toward our target while regulating edit complexity and deviation from the prototype. A large, automatically curated dataset with reasoning chains of fragment edits and measured property deltas underpins both stages, enabling deterministic, reproducible supervision and controllable multi-hop reasoning. Unlike prior work, our framework better reasons about molecules by leveraging fragments and supports controllable refinement toward numeric targets. Experiments on generation under two sets of property constraints (QED, LogP, Molecular Weight and HOMO, LUMO) show consistent gains in validity and precise satisfaction of multi-property targets, outperforming strong LLMs and graph-based algorithms.</p> + https://arxiv.org/abs/2601.10131 + Thu, 15 Jan 2026 07:18:05 +0000 - Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers - https://arxiv.org/abs/2601.04890 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.04890.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maksim Velikanov, Ilyas Chahed, Jingwei Zuo, Dhia Eddine Rhaiem, Younes Belkada, Hakim Hacid</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Applying weight decay (WD) to matrix layers is standard practice in large-language-model pretraining. Prior work suggests that stochastic gradient noise induces a Brownian-like expansion of the weight matrices W, whose growth is counteracted by WD, leading to a WD-noise equilibrium with a certain weight norm ||W||. In this work, we view the equilibrium norm as a harmful artifact of the training procedure, and address it by introducing learnable multipliers to learn the optimal scale. First, we attach a learnable scalar multiplier to W and confirm that the WD-noise equilibrium norm is suboptimal: the learned scale adapts to data and improves performance. We then argue that individual row and column norms are similarly constrained, and free their scale by introducing learnable per-row and per-column multipliers. Our method can be viewed as a learnable, more expressive generalization of muP multipliers. It outperforms a well-tuned muP baseline, reduces the computational overhead of multiplier tuning, and surfaces practical questions such as forward-pass symmetries and the width-scaling of the learned multipliers. Finally, we validate learnable multipliers with both Adam and Muon optimizers, where it shows improvement in downstream evaluations matching the improvement of the switching from Adam to Muon.</p> - https://arxiv.org/abs/2601.04890 - Thu, 08 Jan 2026 12:41:49 +0000 + ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback + https://arxiv.org/abs/2601.10156 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10156.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutao Mou, Zhangchi Xue, Lijun Li, Peiyang Liu, Shikun Zhang, Wei Ye, Jing Shao</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before unsafe execution is critical for agent deployment, yet remains under-explored. In this work, we first construct TS-Bench, a novel benchmark for step-level tool invocation safety detection in LLM agents. We then develop a guardrail model, TS-Guard, using multi-task reinforcement learning. The model proactively detects unsafe tool invocation actions before execution by reasoning over the interaction history. It assesses request harmfulness and action-attack correlations, producing interpretable and generalizable safety judgments and feedback. Furthermore, we introduce TS-Flow, a guardrail-feedback-driven reasoning framework for LLM agents, which reduces harmful tool invocations of ReAct-style agents by 65 percent on average and improves benign task completion by approximately 10 percent under prompt injection attacks.</p> + https://arxiv.org/abs/2601.10156 + Thu, 15 Jan 2026 07:54:32 +0000 - Token-Level LLM Collaboration via FusionRoute - https://arxiv.org/abs/2601.05106 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nuoya Xiong, Yuhang Zhou, Hanqing Zeng, Zhaorun Chen, Furong Huang, Shuchao Bi, Lizhu Zhang, Zhuokai Zhao</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a single general-purpose model typically requires scaling to sizes that are prohibitively expensive to train and deploy. On the other hand, while smaller domain-specialized models are much more efficient, they struggle to generalize beyond their training distributions. To address this dilemma, we propose FusionRoute, a robust and effective token-level multi-LLM collaboration framework in which a lightweight router simultaneously (i) selects the most suitable expert at each decoding step and (ii) contributes a complementary logit that refines or corrects the selected expert's next-token distribution via logit addition. Unlike existing token-level collaboration methods that rely solely on fixed expert outputs, we provide a theoretical analysis showing that pure expert-only routing is fundamentally limited: unless strong global coverage assumptions hold, it cannot in general realize the optimal decoding policy. By augmenting expert selection with a trainable complementary generator, FusionRoute expands the effective policy class and enables recovery of optimal value functions under mild conditions. Empirically, across both Llama-3 and Gemma-2 families and diverse benchmarks spanning mathematical reasoning, code generation, and instruction following, FusionRoute outperforms both sequence- and token-level collaboration, model merging, and direct fine-tuning, while remaining competitive with domain experts on their respective tasks.</p> - https://arxiv.org/abs/2601.05106 - Thu, 08 Jan 2026 16:53:16 +0000 + PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary + https://arxiv.org/abs/2601.10201 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiarui Yao, Ruida Wang, Tong Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Improving the reasoning abilities of Large Language Models (LLMs) has been a continuous topic recently. But most relevant works are based on outcome rewards at the trajectory level, missing fine-grained supervision during the reasoning process. Other existing training frameworks that try to combine process signals together to optimize LLMs also rely heavily on tedious additional steps like MCTS, training a separate reward model, etc., doing harm to the training efficiency. Moreover, the intuition behind the process signals design lacks rigorous theoretical support, leaving the understanding of the optimization mechanism opaque. In this paper, we propose Process Reward Learning (PRL), which decomposes the entropy regularized reinforcement learning objective into intermediate steps, with rigorous process rewards that could be assigned to models accordingly. Starting from theoretical motivation, we derive the formulation of PRL that is essentially equivalent to the objective of reward maximization plus a KL-divergence penalty term between the policy model and a reference model. However, PRL could turn the outcome reward into process supervision signals, which helps better guide the exploration during RL optimization. From our experiment results, we demonstrate that PRL not only improves the average performance for LLMs' reasoning ability measured by average @ n, but also broadens the reasoning boundary by improving the pass @ n metric. Extensive experiments show the effectiveness of PRL could be verified and generalized.</p> + https://arxiv.org/abs/2601.10201 + Thu, 15 Jan 2026 09:01:53 +0000 - Agent-as-a-Judge - https://arxiv.org/abs/2601.05111 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05111.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runyang You, Hongru Cai, Caiqi Zhang, Qiancheng Xu, Meng Liu, Tiezheng Yu, Yongqi Li, Wenjie Li</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> LLM-as-a-Judge has revolutionized AI evaluation by leveraging large language models for scalable assessments. However, as evaluands become increasingly complex, specialized, and multi-step, the reliability of LLM-as-a-Judge has become constrained by inherent biases, shallow single-pass reasoning, and the inability to verify assessments against real-world observations. This has catalyzed the transition to Agent-as-a-Judge, where agentic judges employ planning, tool-augmented verification, multi-agent collaboration, and persistent memory to enable more robust, verifiable, and nuanced evaluations. Despite the rapid proliferation of agentic evaluation systems, the field lacks a unified framework to navigate this shifting landscape. To bridge this gap, we present the first comprehensive survey tracing this evolution. Specifically, we identify key dimensions that characterize this paradigm shift and establish a developmental taxonomy. We organize core methodologies and survey applications across general and professional domains. Furthermore, we analyze frontier challenges and identify promising research directions, ultimately providing a clear roadmap for the next generation of agentic evaluation.</p> - https://arxiv.org/abs/2601.05111 - Thu, 08 Jan 2026 16:58:10 +0000 + DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset + https://arxiv.org/abs/2601.10305 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10305.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengyu Shen, Tiancheng Gu, Bin Qin, Lan Wu, Yuling Wu, Shuo Tan, Zelong Sun, Jun Wang, Nan Wu, Xiang An, Weidong Cai, Ziyong Feng, Kaicheng Yang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Vision-Language Pre-training (VLP) models demonstrate strong performance across various downstream tasks by learning from large-scale image-text pairs through contrastive pretraining. The release of extensive English image-text datasets (e.g., COYO-700M and LAION-400M) has enabled widespread adoption of models such as CLIP and SigLIP in tasks including cross-modal retrieval and image captioning. However, the advancement of Chinese vision-language pretraining has substantially lagged behind, due to the scarcity of high-quality Chinese image-text data. To address this gap, we develop a comprehensive pipeline for constructing a high-quality Chinese cross-modal dataset. As a result, we propose DanQing, which contains 100 million image-text pairs collected from Common Crawl. Different from existing datasets, DanQing is curated through a more rigorous selection process, yielding superior data quality. Moreover, DanQing is primarily built from 2024-2025 web data, enabling models to better capture evolving semantic trends and thus offering greater practical utility. We compare DanQing with existing datasets by continual pre-training of the SigLIP2 model. Experimental results show that DanQing consistently achieves superior performance across a range of Chinese downstream tasks, including zero-shot classification, cross-modal retrieval, and LMM-based evaluations. To facilitate further research in Chinese vision-language pre-training, we will open-source the DanQing dataset under the Creative Common CC-BY 4.0 license.</p> + https://arxiv.org/abs/2601.10305 + Thu, 15 Jan 2026 11:28:58 +0000 - Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing - https://arxiv.org/abs/2601.05124 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runze He, Yiji Cheng, Tiankai Hang, Zhimin Li, Yu Xu, Zijin Yin, Shiyi Zhang, Wenxun Dai, Penghui Du, Ao Ma, Chunyu Wang, Qinglin Lu, Jizhong Han, Jiao Dai</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> In-context image generation and editing (ICGE) enables users to specify visual concepts through interleaved image-text prompts, demanding precise understanding and faithful execution of user intent. Although recent unified multimodal models exhibit promising understanding capabilities, these strengths often fail to transfer effectively to image generation. We introduce Re-Align, a unified framework that bridges the gap between understanding and generation through structured reasoning-guided alignment. At its core lies the In-Context Chain-of-Thought (IC-CoT), a structured reasoning paradigm that decouples semantic guidance and reference association, providing clear textual target and mitigating confusion among reference images. Furthermore, Re-Align introduces an effective RL training scheme that leverages a surrogate reward to measure the alignment between structured reasoning text and the generated image, thereby improving the model's overall performance on ICGE tasks. Extensive experiments verify that Re-Align outperforms competitive methods of comparable model scale and resources on both in-context image generation and editing tasks.</p> - https://arxiv.org/abs/2601.05124 - Thu, 08 Jan 2026 17:13:00 +0000 + Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders + https://arxiv.org/abs/2601.10332 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10332.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqi Kou, Jiachun Jin, Zetong Zhou, Ye Ma, Yugang Wang, Quan Chen, Peng Jiang, Xiao Yang, Jun Zhu, Kai Yu, Zhijie Deng</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Recent progress in text-to-image (T2I) diffusion models (DMs) has enabled high-quality visual synthesis from diverse textual prompts. Yet, most existing T2I DMs, even those equipped with large language model (LLM)-based text encoders, remain text-pixel mappers -- they employ LLMs merely as text encoders, without leveraging their inherent reasoning capabilities to infer what should be visually depicted given the textual prompt. To move beyond such literal generation, we propose the think-then-generate (T2G) paradigm, where the LLM-based text encoder is encouraged to reason about and rewrite raw user prompts; the states of the rewritten prompts then serve as diffusion conditioning. To achieve this, we first activate the think-then-rewrite pattern of the LLM encoder with a lightweight supervised fine-tuning process. Subsequently, the LLM encoder and diffusion backbone are co-optimized to ensure faithful reasoning about the context and accurate rendering of the semantics via Dual-GRPO. In particular, the text encoder is reinforced using image-grounded rewards to infer and recall world knowledge, while the diffusion backbone is pushed to produce semantically consistent and visually coherent images. Experiments show substantial improvements in factual consistency, semantic alignment, and visual realism across reasoning-based image generation and editing benchmarks, achieving 0.79 on WISE score, nearly on par with GPT-4. Our results constitute a promising step toward next-generation unified models with reasoning, expression, and demonstration capacities.</p> + https://arxiv.org/abs/2601.10332 + Thu, 15 Jan 2026 12:19:05 +0000 - VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control - https://arxiv.org/abs/2601.05138 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05138.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sixiao Zheng, Minghao Yin, Wenbo Hu, Xiaoyu Li, Ying Shan, Yanwei Fu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Video world models aim to simulate dynamic, real-world environments, yet existing methods struggle to provide unified and precise control over camera and multi-object motion, as videos inherently operate dynamics in the projected 2D image plane. To bridge this gap, we introduce VerseCrafter, a 4D-aware video world model that enables explicit and coherent control over both camera and object dynamics within a unified 4D geometric world state. Our approach is centered on a novel 4D Geometric Control representation, which encodes the world state through a static background point cloud and per-object 3D Gaussian trajectories. This representation captures not only an object's path but also its probabilistic 3D occupancy over time, offering a flexible, category-agnostic alternative to rigid bounding boxes or parametric models. These 4D controls are rendered into conditioning signals for a pretrained video diffusion model, enabling the generation of high-fidelity, view-consistent videos that precisely adhere to the specified dynamics. Unfortunately, another major challenge lies in the scarcity of large-scale training data with explicit 4D annotations. We address this by developing an automatic data engine that extracts the required 4D controls from in-the-wild videos, allowing us to train our model on a massive and diverse dataset.</p> - https://arxiv.org/abs/2601.05138 - Thu, 08 Jan 2026 17:28:52 +0000 + Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering + https://arxiv.org/abs/2601.10402 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10402.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Zhu, Yuzhu Cai, Zexi Liu, Bingyang Zheng, Cheng Wang, Rui Ye, Jiaao Chen, Hanrui Wang, Wei-Chen Wang, Yuzhi Zhang, Linfeng Zhang, Weinan E, Di Jin, Siheng Chen</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles spanning days or weeks. While Large Language Models (LLMs) have demonstrated prowess in short-horizon reasoning, they are easily overwhelmed by execution details in the high-dimensional, delayed-feedback environments of real-world research, failing to consolidate sparse feedback into coherent long-term guidance. Here, we present ML-Master 2.0, an autonomous agent that masters ultra-long-horizon machine learning engineering (MLE) which is a representative microcosm of scientific discovery. By reframing context management as a process of cognitive accumulation, our approach introduces Hierarchical Cognitive Caching (HCC), a multi-tiered architecture inspired by computer systems that enables the structural differentiation of experience over time. By dynamically distilling transient execution traces into stable knowledge and cross-task wisdom, HCC allows agents to decouple immediate execution from long-term experimental strategy, effectively overcoming the scaling limits of static context windows. In evaluations on OpenAI's MLE-Bench under 24-hour budgets, ML-Master 2.0 achieves a state-of-the-art medal rate of 56.44%. Our findings demonstrate that ultra-long-horizon autonomy provides a scalable blueprint for AI capable of autonomous exploration beyond human-precedent complexities.</p> + https://arxiv.org/abs/2601.10402 + Thu, 15 Jan 2026 13:52:04 +0000 - Multi-Scale Local Speculative Decoding for Image Generation - https://arxiv.org/abs/2601.05149 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05149.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elia Peruzzo, Guillaume Sautière, Amirhossein Habibian</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints. Speculative Decoding offers a promising avenue for acceleration, but existing approaches are limited by token-level ambiguity and lack of spatial awareness. In this work, we introduce Multi-Scale Local Speculative Decoding (MuLo-SD), a novel framework that combines multi-resolution drafting with spatially informed verification to accelerate AR image generation. Our method leverages a low-resolution drafter paired with learned up-samplers to propose candidate image tokens, which are then verified in parallel by a high-resolution target model. Crucially, we incorporate a local rejection and resampling mechanism, enabling efficient correction of draft errors by focusing on spatial neighborhoods rather than raster-scan resampling after the first rejection. We demonstrate that MuLo-SD achieves substantial speedups - up to 1.7times - outperforming strong speculative decoding baselines such as EAGLE-2 and LANTERN in terms of acceleration, while maintaining comparable semantic alignment and perceptual quality. These results are validated using GenEval, DPG-Bench, and FID/HPSv2 on the MS-COCO 5k validation split. Extensive ablations highlight the impact of up-sampling design, probability pooling, and local rejection and resampling with neighborhood expansion. Our approach sets a new state-of-the-art in speculative decoding for image synthesis, bridging the gap between efficiency and fidelity.</p> - https://arxiv.org/abs/2601.05149 - Thu, 08 Jan 2026 17:39:35 +0000 + Urban Socio-Semantic Segmentation with Vision-Language Reasoning + https://arxiv.org/abs/2601.10477 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10477.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Wang, Yi Wang, Rui Dai, Yujie Wang, Kaikui Liu, Xiangxiang Chu, Yansheng Li</p><p><b>Upvotes:</b> 148</p><p><b>Summary:</b> As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., buildings, water bodies) but still struggle with socially defined categories (e.g., schools, parks). In this work, we achieve socio-semantic segmentation by vision-language model reasoning. To facilitate this, we introduce the Urban Socio-Semantic Segmentation dataset named SocioSeg, a new resource comprising satellite imagery, digital maps, and pixel-level labels of social semantic entities organized in a hierarchical structure. Additionally, we propose a novel vision-language reasoning framework called SocioReasoner that simulates the human process of identifying and annotating social semantic entities via cross-modal recognition and multi-stage reasoning. We employ reinforcement learning to optimize this non-differentiable process and elicit the reasoning capabilities of the vision-language model. Experiments demonstrate our approach's gains over state-of-the-art models and strong zero-shot generalization. Our dataset and code are available in https://github.com/AMAP-ML/SocioReasoner.</p> + https://arxiv.org/abs/2601.10477 + Thu, 15 Jan 2026 15:00:36 +0000 - DocDancer: Towards Agentic Document-Grounded Information Seeking - https://arxiv.org/abs/2601.05163 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05163.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qintong Zhang, Xinjie Lv, Jialong Wu, Baixuan Li, Zhengwei Tao, Guochen Yan, Huanyao Zhang, Bin Wang, Jiahao Xu, Haitao Mi, Wentao Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Document Question Answering (DocQA) focuses on answering questions grounded in given documents, yet existing DocQA agents lack effective tool utilization and largely rely on closed-source models. In this work, we introduce DocDancer, an end-to-end trained open-source Doc agent. We formulate DocQA as an information-seeking problem and propose a tool-driven agent framework that explicitly models document exploration and comprehension. To enable end-to-end training of such agents, we introduce an Exploration-then-Synthesis data synthesis pipeline that addresses the scarcity of high-quality training data for DocQA. Training on the synthesized data, the trained models on two long-context document understanding benchmarks, MMLongBench-Doc and DocBench, show their effectiveness. Further analysis provides valuable insights for the agentic tool design and synthetic data.</p> - https://arxiv.org/abs/2601.05163 - Thu, 08 Jan 2026 17:54:32 +0000 + A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5 + https://arxiv.org/abs/2601.10527 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingjun Ma, Yixu Wang, Hengyuan Xu, Yutao Wu, Yifan Ding, Yunhan Zhao, Zilong Wang, Jiabin Hua, Ming Wen, Jianan Liu, Ranjie Duan, Yifeng Gao, Yingshui Tan, Yunhao Chen, Hui Xue, Xin Wang, Wei Cheng, Jingjing Chen, Zuxuan Wu, Bo Li, Yu-Gang Jiang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has produced substantial gains in reasoning, perception, and generative capability across language and vision. However, whether these advances yield commensurate improvements in safety remains unclear, in part due to fragmented evaluation practices limited to single modalities or threat models. In this report, we present an integrated safety evaluation of 7 frontier models: GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5. We evaluate each model across language, vision-language, and image generation settings using a unified protocol that integrates benchmark evaluation, adversarial evaluation, multilingual evaluation, and compliance evaluation. Aggregating our evaluations into safety leaderboards and model safety profiles across multiple evaluation modes reveals a sharply heterogeneous safety landscape. While GPT-5.2 demonstrates consistently strong and balanced safety performance across evaluations, other models exhibit pronounced trade-offs among benchmark safety, adversarial alignment, multilingual generalization, and regulatory compliance. Both language and vision-language modalities show significant vulnerability under adversarial evaluation, with all models degrading substantially despite strong results on standard benchmarks. Text-to-image models achieve relatively stronger alignment in regulated visual risk categories, yet remain brittle under adversarial or semantically ambiguous prompts. Overall, these results show that safety in frontier models is inherently multidimensional--shaped by modality, language, and evaluation scheme, underscoring the need for standardized safety evaluations to accurately assess real-world risk and guide responsible model development and deployment.</p> + https://arxiv.org/abs/2601.10527 + Thu, 15 Jan 2026 15:52:52 +0000 - RelayLLM: Efficient Reasoning via Collaborative Decoding - https://arxiv.org/abs/2601.05167 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05167.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengsong Huang, Tong Zheng, Langlin Huang, Jinyuan Li, Haolin Liu, Jiaxin Huang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Large Language Models (LLMs) for complex reasoning is often hindered by high computational costs and latency, while resource-efficient Small Language Models (SLMs) typically lack the necessary reasoning capacity. Existing collaborative approaches, such as cascading or routing, operate at a coarse granularity by offloading entire queries to LLMs, resulting in significant computational waste when the SLM is capable of handling the majority of reasoning steps. To address this, we propose RelayLLM, a novel framework for efficient reasoning via token-level collaborative decoding. Unlike routers, RelayLLM empowers the SLM to act as an active controller that dynamically invokes the LLM only for critical tokens via a special command, effectively "relaying" the generation process. We introduce a two-stage training framework, including warm-up and Group Relative Policy Optimization (GRPO) to teach the model to balance independence with strategic help-seeking. Empirical results across six benchmarks demonstrate that RelayLLM achieves an average accuracy of 49.52%, effectively bridging the performance gap between the two models. Notably, this is achieved by invoking the LLM for only 1.07% of the total generated tokens, offering a 98.2% cost reduction compared to performance-matched random routers.</p> - https://arxiv.org/abs/2601.05167 - Thu, 08 Jan 2026 17:56:16 +0000 + HeartMuLa: A Family of Open Sourced Music Foundation Models + https://arxiv.org/abs/2601.10547 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongchao Yang, Yuxin Xie, Yuguo Yin, Zheyu Wang, Xiaoyu Yi, Gongxi Zhu, Xiaolong Weng, Zihan Xiong, Yingzhe Ma, Dading Cong, Jingliang Liu, Zihang Huang, Jinghan Ru, Rongjie Huang, Haoran Wan, Peixu Wang, Kuoxi Yu, Helin Wang, Liming Liang, Xianwei Zhuang, Yuanyuan Wang, Haohan Guo, Junjie Cao, Zeqian Ju, Songxiang Liu, Yuewen Cao, Heming Weng, Yuexian Zou</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework consists of four major components: (1) HeartCLAP, an audio-text alignment model; (2) HeartTranscriptor, a robust lyric recognition model optimized for real-world music scenarios; and (3) HeartCodec, a low-frame-rate (12.5 Hz) yet high-fidelity music codec tokenizer that captures long-range musical structure while preserving fine-grained acoustic details and enabling efficient autoregressive modeling; (4) HeartMuLa, an LLM-based song generation model capable of synthesizing high-fidelity music under rich, user-controllable conditions (e.g., textual style descriptions, lyrics, and reference audio). In addition, it provides two specialized modes: (i) fine-grained musical attribute control, which allows users to specify the style of different song sections (e.g., intro, verse, chorus) using natural language prompts; and (ii) short, engaging music generation, which is suitable as background music for short videos. Lastly, HeartMuLa improves significantly when scaled to 7B parameters. For the first time, we show that a Suno-level, commercial-grade system can be reproduced using academic-scale data and GPU resources. We expect these foundation models to serve as strong baselines for future research and to facilitate practical applications in multimodal content production.</p> + https://arxiv.org/abs/2601.10547 + Thu, 15 Jan 2026 16:14:25 +0000 - CoV: Chain-of-View Prompting for Spatial Reasoning - https://arxiv.org/abs/2601.05172 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05172.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Zhao, Akide Liu, Zeyu Zhang, Weijie Wang, Feng Chen, Ruihan Zhu, Gholamreza Haffari, Bohan Zhuang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Embodied question answering (EQA) in 3D environments often requires collecting context that is distributed across multiple viewpoints and partially occluded. However, most recent vision--language models (VLMs) are constrained to a fixed and finite set of input views, which limits their ability to acquire question-relevant context at inference time and hinders complex spatial reasoning. We propose Chain-of-View (CoV) prompting, a training-free, test-time reasoning framework that transforms a VLM into an active viewpoint reasoner through a coarse-to-fine exploration process. CoV first employs a View Selection agent to filter redundant frames and identify question-aligned anchor views. It then performs fine-grained view adjustment by interleaving iterative reasoning with discrete camera actions, obtaining new observations from the underlying 3D scene representation until sufficient context is gathered or a step budget is reached. We evaluate CoV on OpenEQA across four mainstream VLMs and obtain an average +11.56\% improvement in LLM-Match, with a maximum gain of +13.62\% on Qwen3-VL-Flash. CoV further exhibits test-time scaling: increasing the minimum action budget yields an additional +2.51\% average improvement, peaking at +3.73\% on Gemini-2.5-Flash. On ScanQA and SQA3D, CoV delivers strong performance (e.g., 116 CIDEr / 31.9 EM@1 on ScanQA and 51.1 EM@1 on SQA3D). Overall, these results suggest that question-aligned view selection coupled with open-view search is an effective, model-agnostic strategy for improving spatial reasoning in 3D EQA without additional training.</p> - https://arxiv.org/abs/2601.05172 - Thu, 08 Jan 2026 17:59:42 +0000 + Inference-time Physics Alignment of Video Generative Models with Latent World Models + https://arxiv.org/abs/2601.10553 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10553.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari-Hemmat, Xiaochuang Han, Nicolas Ballas, Michal Drozdzal, Adriana Romero-Soriano</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency to insufficient physics understanding from pre-training, we find that the shortfall in physics plausibility also stems from suboptimal inference strategies. We therefore introduce WMReward and treat improving physics plausibility of video generation as an inference-time alignment problem. In particular, we leverage the strong physics prior of a latent world model (here, VJEPA-2) as a reward to search and steer multiple candidate denoising trajectories, enabling scaling test-time compute for better generation performance. Empirically, our approach substantially improves physics plausibility across image-conditioned, multiframe-conditioned, and text-conditioned generation settings, with validation from human preference study. Notably, in the ICCV 2025 Perception Test PhysicsIQ Challenge, we achieve a final score of 62.64%, winning first place and outperforming the previous state of the art by 7.42%. Our work demonstrates the viability of using latent world models to improve physics plausibility of video generation, beyond this specific instantiation or parameterization.</p> + https://arxiv.org/abs/2601.10553 + Thu, 15 Jan 2026 16:18:00 +0000 - VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice - https://arxiv.org/abs/2601.05175 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05175.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuming Liu, Mingchen Zhuge, Changsheng Zhao, Jun Chen, Lemeng Wu, Zechun Liu, Chenchen Zhu, Zhipeng Cai, Chong Zhou, Haozhe Liu, Ernie Chang, Saksham Suri, Hongyu Xu, Qi Qian, Wei Wen, Balakrishnan Varadarajan, Zhuang Liu, Hu Xu, Florian Bordes, Raghuraman Krishnamoorthi, Bernard Ghanem, Vikas Chandra, Yunyang Xiong</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by ~3.3x, e.g., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary.</p> - https://arxiv.org/abs/2601.05175 - Thu, 08 Jan 2026 18:00:59 +0000 + Action100M: A Large-scale Video Action Dataset + https://arxiv.org/abs/2601.10592 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Delong Chen, Tejaswi Kasarla, Yejin Bang, Mustafa Shukor, Willy Chung, Jade Yu, Allen Bolourchi, Theo Moutakanni, Pascale Fung</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Inferring physical actions from visual observations is a fundamental capability for advancing machine intelligence in the physical world. Achieving this requires large-scale, open-vocabulary video action datasets that span broad domains. We introduce Action100M, a large-scale dataset constructed from 1.2M Internet instructional videos (14.6 years of duration), yielding O(100 million) temporally localized segments with open-vocabulary action supervision and rich captions. Action100M is generated by a fully automated pipeline that (i) performs hierarchical temporal segmentation using V-JEPA 2 embeddings, (ii) produces multi-level frame and segment captions organized as a Tree-of-Captions, and (iii) aggregates evidence with a reasoning model (GPT-OSS-120B) under a multi-round Self-Refine procedure to output structured annotations (brief/detailed action, actor, brief/detailed caption). Training VL-JEPA on Action100M demonstrates consistent data-scaling improvements and strong zero-shot performance across diverse action recognition benchmarks, establishing Action100M as a new foundation for scalable research in video understanding and world modeling.</p> + https://arxiv.org/abs/2601.10592 + Thu, 15 Jan 2026 17:02:27 +0000 - Plenoptic Video Generation - https://arxiv.org/abs/2601.05239 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05239.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Fu, Shitao Tang, Min Shi, Xian Liu, Jinwei Gu, Ming-Yu Liu, Dahua Lin, Chen-Hsuan Lin</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency across multi-view scenarios. Ensuring spatio-temporal coherence in hallucinated regions remains challenging due to the inherent stochasticity of generative models. To address it, we introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain spatio-temporal memory. The core idea is to train a multi-in-single-out video-conditioned model in an autoregressive manner, aided by a camera-guided video retrieval strategy that adaptively selects salient videos from previous generations as conditional inputs. In addition, Our training incorporates progressive context-scaling to improve convergence, self-conditioning to enhance robustness against long-range visual degradation caused by error accumulation, and a long-video conditioning mechanism to support extended video generation. Extensive experiments on the Basic and Agibot benchmarks demonstrate that PlenopticDreamer achieves state-of-the-art video re-rendering, delivering superior view synchronization, high-fidelity visuals, accurate camera control, and diverse view transformations (e.g., third-person to third-person, and head-view to gripper-view in robotic manipulation). Project page: https://research.nvidia.com/labs/dir/plenopticdreamer/</p> - https://arxiv.org/abs/2601.05239 - Thu, 08 Jan 2026 18:58:32 +0000 + Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding + https://arxiv.org/abs/2601.10611 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Christopher Clark, Jieyu Zhang, Zixian Ma, Jae Sung Park, Mohammadreza Salehi, Rohun Tripathi, Sangho Lee, Zhongzheng Ren, Chris Dongjoo Kim, Yinuo Yang, Vincent Shao, Yue Yang, Weikai Huang, Ziqi Gao, Taira Anderson, Jianrui Zhang, Jitesh Jain, George Stoica, Winson Han, Ali Farhadi, Ranjay Krishna</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of-the-art video (and image) language models. Crucially, many downstream applications require more than just high-level video understanding; they require grounding -- either by pointing or by tracking in pixels. Even proprietary models lack this capability. We present Molmo2, a new family of VLMs that are state-of-the-art among open-source models and demonstrate exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks. Our key contribution is a collection of 7 new video datasets and 2 multi-image datasets, including a dataset of highly detailed video captions for pre-training, a free-form video Q&A dataset for fine-tuning, a new object tracking dataset with complex queries, and an innovative new video pointing dataset, all collected without the use of closed VLMs. We also present a training recipe for this data utilizing an efficient packing and message-tree encoding scheme, and show bi-directional attention on vision tokens and a novel token-weight strategy improves performance. Our best-in-class 8B model outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. On video-grounding Molmo2 significantly outperforms existing open-weight models like Qwen3-VL (35.5 vs 29.6 accuracy on video counting) and surpasses proprietary models like Gemini 3 Pro on some tasks (38.4 vs 20.0 F1 on video pointing and 56.2 vs 41.1 J&F on video tracking).</p> + https://arxiv.org/abs/2601.10611 + Thu, 15 Jan 2026 17:27:44 +0000 - RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation - https://arxiv.org/abs/2601.05241 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05241.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyang Wang, Haoran Zhang, Shujie Zhang, Jinkun Hao, Mingda Jia, Qi Lv, Yucheng Mao, Zhaoyang Lyu, Jia Zeng, Xudong Xu, Jiangmiao Pang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting large-scale real-world manipulation data remains difficult to scale across diverse environments. Recent work uses text-prompt conditioned image diffusion models to augment manipulation data by altering the backgrounds and tabletop objects in the visual observations. However, these approaches often overlook the practical need for multi-view and temporally coherent observations required by state-of-the-art policy models. Further, text prompts alone cannot reliably specify the scene setup. To provide the diffusion model with explicit visual guidance, we introduce visual identity prompting, which supplies exemplar images as conditioning inputs to guide the generation of the desired scene setup. To this end, we also build a scalable pipeline to curate a visual identity pool from large robotics datasets. Using our augmented manipulation data to train downstream vision-language-action and visuomotor policy models yields consistent performance gains in both simulation and real-robot settings.</p> - https://arxiv.org/abs/2601.05241 - Thu, 08 Jan 2026 18:59:22 +0000 + PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution + https://arxiv.org/abs/2601.10657 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10657.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minghao Yan, Bo Peng, Benjamin Coleman, Ziqi Chen, Zhouhang Xie, Zhankui He, Noveen Sachdeva, Isabella Ye, Weili Wang, Chi Wang, Ed H. Chi, Wang-Cheng Kang, Derek Zhiyuan Cheng, Beidou Wang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large Language Models (LLMs) have emerged as powerful operators for evolutionary search, yet the design of efficient search scaffolds remains ad hoc. While promising, current LLM-in-the-loop systems lack a systematic approach to managing the evolutionary process. We identify three distinct failure modes: Context Pollution, where experiment history biases future candidate generation; Mode Collapse, where agents stagnate in local minima due to poor exploration-exploitation balance; and Weak Collaboration, where rigid crossover strategies fail to leverage parallel search trajectories effectively. We introduce Progress-Aware Consistent Evolution (PACEvolve), a framework designed to robustly govern the agent's context and search dynamics, to address these challenges. PACEvolve combines hierarchical context management (HCM) with pruning to address context pollution; momentum-based backtracking (MBB) to escape local minima; and a self-adaptive sampling policy that unifies backtracking and crossover for dynamic search coordination (CE), allowing agents to balance internal refinement with cross-trajectory collaboration. We demonstrate that PACEvolve provides a systematic path to consistent, long-horizon self-improvement, achieving state-of-the-art results on LLM-SR and KernelBench, while discovering solutions surpassing the record on Modded NanoGPT.</p> + https://arxiv.org/abs/2601.10657 + Thu, 15 Jan 2026 18:25:23 +0000 - GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization - https://arxiv.org/abs/2601.05242 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shih-Yang Liu, Xin Dong, Ximing Lu, Shizhe Diao, Peter Belcak, Mingjie Liu, Min-Hung Chen, Hongxu Yin, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Yejin Choi, Jan Kautz, Pavlo Molchanov</p><p><b>Upvotes:</b> 137</p><p><b>Summary:</b> As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL) pipelines have begun incorporating multiple rewards, each capturing a distinct preference, to guide models toward these desired behaviors. However, recent work has defaulted to apply Group Relative Policy Optimization (GRPO) under multi-reward setting without examining its suitability. In this paper, we demonstrate that directly applying GRPO to normalize distinct rollout reward combinations causes them to collapse into identical advantage values, reducing the resolution of the training signal and resulting in suboptimal convergence and, in some cases, early training failure. We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues by decoupling the normalization of individual rewards, more faithfully preserving their relative differences and enabling more accurate multi-reward optimization, along with substantially improved training stability. We compare GDPO with GRPO across three tasks: tool calling, math reasoning, and coding reasoning, evaluating both correctness metrics (accuracy, bug ratio) and constraint adherence metrics (format, length). Across all settings, GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.</p> - https://arxiv.org/abs/2601.05242 - Thu, 08 Jan 2026 18:59:24 +0000 + MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching + https://arxiv.org/abs/2601.10712 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changle Qu, Sunhao Dai, Hengyi Cai, Jun Xu, Shuaiqiang Wang, Dawei Yin</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing reinforcement learning methods typically rely on outcome- or trajectory-level rewards, assigning uniform advantages to all steps within a trajectory. This coarse-grained credit assignment fails to distinguish effective tool calls from redundant or erroneous ones, particularly in long-horizon multi-turn scenarios. To address this, we propose MatchTIR, a framework that introduces fine-grained supervision via bipartite matching-based turn-level reward assignment and dual-level advantage estimation. Specifically, we formulate credit assignment as a bipartite matching problem between predicted and ground-truth traces, utilizing two assignment strategies to derive dense turn-level rewards. Furthermore, to balance local step precision with global task success, we introduce a dual-level advantage estimation scheme that integrates turn-level and trajectory-level signals, assigning distinct advantage values to individual interaction turns. Extensive experiments on three benchmarks demonstrate the superiority of MatchTIR. Notably, our 4B model surpasses the majority of 8B competitors, particularly in long-horizon and multi-turn tasks. Our codes are available at https://github.com/quchangle1/MatchTIR.</p> + https://arxiv.org/abs/2601.10712 + Thu, 15 Jan 2026 18:59:23 +0000 - RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes - https://arxiv.org/abs/2601.05249 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.05249.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan-Kang Lee, Kuan-Lin Chen, Chia-Che Chang, Yu-Lun Liu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Nighttime color constancy remains a challenging problem in computational photography due to low-light noise and complex illumination conditions. We present RL-AWB, a novel framework combining statistical methods with deep reinforcement learning for nighttime white balance. Our method begins with a statistical algorithm tailored for nighttime scenes, integrating salient gray pixel detection with novel illumination estimation. Building on this foundation, we develop the first deep reinforcement learning approach for color constancy that leverages the statistical algorithm as its core, mimicking professional AWB tuning experts by dynamically optimizing parameters for each image. To facilitate cross-sensor evaluation, we introduce the first multi-sensor nighttime dataset. Experiment results demonstrate that our method achieves superior generalization capability across low-light and well-illuminated images. Project page: https://ntuneillee.github.io/research/rl-awb/</p> - https://arxiv.org/abs/2601.05249 - Thu, 08 Jan 2026 18:59:55 +0000 + Alterbute: Editing Intrinsic Attributes of Objects in Images + https://arxiv.org/abs/2601.10714 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.10714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tal Reiss, Daniel Winter, Matan Cohen, Alex Rav-Acha, Yael Pritch, Ariel Shamir, Yedid Hoshen</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even the shape of an object, while preserving its perceived identity and scene context. Existing approaches either rely on unsupervised priors that often fail to preserve identity or use overly restrictive supervision that prevents meaningful intrinsic variations. Our method relies on: (i) a relaxed training objective that allows the model to change both intrinsic and extrinsic attributes conditioned on an identity reference image, a textual prompt describing the target intrinsic attributes, and a background image and object mask defining the extrinsic context. At inference, we restrict extrinsic changes by reusing the original background and object mask, thereby ensuring that only the desired intrinsic attributes are altered; (ii) Visual Named Entities (VNEs) - fine-grained visual identity categories (e.g., ''Porsche 911 Carrera'') that group objects sharing identity-defining features while allowing variation in intrinsic attributes. We use a vision-language model to automatically extract VNE labels and intrinsic attribute descriptions from a large public image dataset, enabling scalable, identity-preserving supervision. Alterbute outperforms existing methods on identity-preserving object intrinsic attribute editing.</p> + https://arxiv.org/abs/2601.10714 + Thu, 15 Jan 2026 18:59:53 +0000