diff --git a/feed.xml b/feed.xml index 5cc4ddf..de17e7e 100644 --- a/feed.xml +++ b/feed.xml @@ -7,272 +7,160 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 22 Dec 2025 00:02:46 +0000 + Tue, 23 Dec 2025 00:02:36 +0000 - LLaDA2.0: Scaling Up Diffusion Language Models to 100B - https://arxiv.org/abs/2512.15745 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.15745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tiwei Bie, Maosong Cao, Kun Chen, Lun Du, Mingliang Gong, Zhuochen Gong, Yanmei Gu, Jiaqi Hu, Zenan Huang, Zhenzhong Lan, Chengxi Li, Chongxuan Li, Jianguo Li, Zehuan Li, Huabin Liu, Ling Liu, Guoshan Lu, Xiaocheng Lu, Yuxin Ma, Jianfeng Tan, Lanning Wei, Ji-Rong Wen, Yipeng Xing, Xiaolu Zhang, Junbo Zhao, Da Zheng, Jun Zhou, Junlin Zhou, Zhanchao Zhou, Liwang Zhu, Yihong Zhuang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> This paper presents LLaDA2.0 -- a tuple of discrete diffusion large language models (dLLM) scaling up to 100B total parameters through systematic conversion from auto-regressive (AR) models -- establishing a new paradigm for frontier-scale deployment. Instead of costly training from scratch, LLaDA2.0 upholds knowledge inheritance, progressive adaption and efficiency-aware design principle, and seamless converts a pre-trained AR model into dLLM with a novel 3-phase block-level WSD based training scheme: progressive increasing block-size in block diffusion (warm-up), large-scale full-sequence diffusion (stable) and reverting back to compact-size block diffusion (decay). Along with post-training alignment with SFT and DPO, we obtain LLaDA2.0-mini (16B) and LLaDA2.0-flash (100B), two instruction-tuned Mixture-of-Experts (MoE) variants optimized for practical deployment. By preserving the advantages of parallel decoding, these models deliver superior performance and efficiency at the frontier scale. Both models were open-sourced.</p> - https://arxiv.org/abs/2512.15745 - Wed, 10 Dec 2025 09:26:18 +0000 + An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges + https://arxiv.org/abs/2512.11362 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11362.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Xu, Suyu Zhang, Yang Liu, Baigui Sun, Weihong Chen, Bo Xu, Qi Liu, Juncheng Wang, Shujun Wang, Shan Luo, Jan Peters, Athanasios V. Vasilakos, Stefanos Zafeiriou, Jiankang Deng</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Vision-Language-Action (VLA) models are driving a revolution in robotics, enabling machines to understand instructions and interact with the physical world. This field is exploding with new models and datasets, making it both exciting and challenging to keep pace with. This survey offers a clear and structured guide to the VLA landscape. We design it to follow the natural learning path of a researcher: we start with the basic Modules of any VLA model, trace the history through key Milestones, and then dive deep into the core Challenges that define recent research frontier. Our main contribution is a detailed breakdown of the five biggest challenges in: (1) Representation, (2) Execution, (3) Generalization, (4) Safety, and (5) Dataset and Evaluation. This structure mirrors the developmental roadmap of a generalist agent: establishing the fundamental perception-action loop, scaling capabilities across diverse embodiments and environments, and finally ensuring trustworthy deployment-all supported by the essential data infrastructure. For each of them, we review existing approaches and highlight future opportunities. We position this paper as both a foundational guide for newcomers and a strategic roadmap for experienced researchers, with the dual aim of accelerating learning and inspiring new ideas in embodied intelligence. A live version of this survey, with continuous updates, is maintained on our https://suyuz1.github.io/Survery/{project page}.</p> + https://arxiv.org/abs/2512.11362 + Fri, 12 Dec 2025 08:22:03 +0000 - Bidirectional Normalizing Flow: From Data to Noise and Back - https://arxiv.org/abs/2512.10953 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiyang Lu, Qiao Sun, Xianbang Wang, Zhicheng Jiang, Hanhong Zhao, Kaiming He</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Normalizing Flows (NFs) have been established as a principled framework for generative modeling. Standard NFs consist of a forward process and a reverse process: the forward process maps data to noise, while the reverse process generates samples by inverting it. Typical NF forward transformations are constrained by explicit invertibility, ensuring that the reverse process can serve as their exact analytic inverse. Recent developments in TARFlow and its variants have revitalized NF methods by combining Transformers and autoregressive flows, but have also exposed causal decoding as a major bottleneck. In this work, we introduce Bidirectional Normalizing Flow (BiFlow), a framework that removes the need for an exact analytic inverse. BiFlow learns a reverse model that approximates the underlying noise-to-data inverse mapping, enabling more flexible loss functions and architectures. Experiments on ImageNet demonstrate that BiFlow, compared to its causal decoding counterpart, improves generation quality while accelerating sampling by up to two orders of magnitude. BiFlow yields state-of-the-art results among NF-based methods and competitive performance among single-evaluation ("1-NFE") methods. Following recent encouraging progress on NFs, we hope our work will draw further attention to this classical paradigm.</p> - https://arxiv.org/abs/2512.10953 - Thu, 11 Dec 2025 18:59:55 +0000 + MineTheGap: Automatic Mining of Biases in Text-to-Image Models + https://arxiv.org/abs/2512.13427 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Noa Cohen, Nurit Spingarn-Eliezer, Inbar Huberman-Spiegelglas, Tomer Michaeli</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Text-to-Image (TTI) models generate images based on text prompts, which often leave certain aspects of the desired image ambiguous. When faced with these ambiguities, TTI models have been shown to exhibit biases in their interpretations. These biases can have societal impacts, e.g., when showing only a certain race for a stated occupation. They can also affect user experience when creating redundancy within a set of generated images instead of spanning diverse possibilities. Here, we introduce MineTheGap - a method for automatically mining prompts that cause a TTI model to generate biased outputs. Our method goes beyond merely detecting bias for a given prompt. Rather, it leverages a genetic algorithm to iteratively refine a pool of prompts, seeking for those that expose biases. This optimization process is driven by a novel bias score, which ranks biases according to their severity, as we validate on a dataset with known biases. For a given prompt, this score is obtained by comparing the distribution of generated images to the distribution of LLM-generated texts that constitute variations on the prompt. Code and examples are available on the project's webpage.</p> + https://arxiv.org/abs/2512.13427 + Mon, 15 Dec 2025 15:17:02 +0000 - Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language - https://arxiv.org/abs/2512.11251 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11251.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunkai Zhang, Yawen Zhang, Ming Zheng, Kezhen Chen, Chongyang Gao, Ruian Ge, Siyuan Teng, Amine Jelloul, Jinmeng Rao, Xiaoyuan Guo, Chiang-Wei Fang, Zeyu Zheng, Jie Yang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Time-series data is critical across many scientific and industrial domains, including environmental analysis, agriculture, transportation, and finance. However, mining insights from this data typically requires deep domain expertise, a process that is both time-consuming and labor-intensive. In this paper, we propose Insight Miner, a large-scale multimodal model (LMM) designed to generate high-quality, comprehensive time-series descriptions enriched with domain-specific knowledge. To facilitate this, we introduce TS-InsightsAvailable at \href{https://huggingface.co/datasets/zhykoties/time-series-language-alignment{https://huggingface.co/datasets/zhykoties/time-series-language-alignment}.}, the first general-domain dataset for time series and language alignment. TS-Insights contains 100k time-series windows sampled from 20 forecasting datasets. We construct this dataset using a novel agentic workflow, where we use statistical tools to extract features from raw time series before synthesizing them into coherent trend descriptions with GPT-4. Following instruction tuning on TS-Insights, Insight Miner outperforms state-of-the-art multimodal models, such as LLaVA liu2023llava and GPT-4, in generating time-series descriptions and insights. Our findings suggest a promising direction for leveraging LMMs in time series analysis, and serve as a foundational step toward enabling LLMs to interpret time series as a native input modality.</p> - https://arxiv.org/abs/2512.11251 - Fri, 12 Dec 2025 03:18:00 +0000 + HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering + https://arxiv.org/abs/2512.14870 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14870.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Video Large Language Models (Video-LLMs) are rapidly improving, yet current Video Question Answering (VideoQA) benchmarks often allow questions to be answered from a single salient cue, under-testing reasoning that must aggregate multiple, temporally separated visual evidence. We present HERBench, a VideoQA benchmark purpose-built to assess multi-evidence integration across time. Each question requires aggregating at least three non-overlapping evidential cues across distinct video segments, so neither language priors nor a single snapshot can suffice. HERBench comprises 26K five-way multiple-choice questions organized into twelve compositional tasks that probe identity binding, cross-entity relations, temporal ordering, co-occurrence verification, and counting. To make evidential demand measurable, we introduce the Minimum Required Frame-Set (MRFS), the smallest number of frames a model must fuse to answer correctly, and show that HERBench imposes substantially higher demand than prior datasets (mean MRFS 5.5 vs. 2.6-4.2). Evaluating 13 state-of-the-art Video-LLMs on HERBench reveals pervasive failures: accuracies of 31-42% are only slightly above the 20% random-guess baseline. We disentangle this failure into two critical bottlenecks: (1) a retrieval deficit, where frame selectors overlook key evidence, and (2) a fusion deficit, where models fail to integrate information even when all necessary evidence is provided. By making cross-time evidence both unavoidable and quantifiable, HERBench establishes a principled target for advancing robust, compositional video understanding.</p> + https://arxiv.org/abs/2512.14870 + Tue, 16 Dec 2025 19:34:47 +0000 - Coupled Variational Reinforcement Learning for Language Model General Reasoning - https://arxiv.org/abs/2512.12576 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xueru Wen, Jie Lou, Yanjiang Liu, Hongyu Lin, Ben He, Xianpei Han, Le Sun, Yaojie Lu, Debing Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> While reinforcement learning have achieved impressive progress in language model reasoning, they are constrained by the requirement for verifiable rewards. Recent verifier-free RL methods address this limitation by utilizing the intrinsic probabilities of LLMs generating reference answers as reward signals. However, these approaches typically sample reasoning traces conditioned only on the question. This design decouples reasoning-trace sampling from answer information, leading to inefficient exploration and incoherence between traces and final answers. In this paper, we propose \b{Coupled Variational Reinforcement Learning} (CoVRL), which bridges variational inference and reinforcement learning by coupling prior and posterior distributions through a hybrid sampling strategy. By constructing and optimizing a composite distribution that integrates these two distributions, CoVRL enables efficient exploration while preserving strong thought-answer coherence. Extensive experiments on mathematical and general reasoning benchmarks show that CoVRL improves performance by 12.4\% over the base model and achieves an additional 2.3\% improvement over strong state-of-the-art verifier-free RL baselines, providing a principled framework for enhancing the general reasoning capabilities of language models.</p> - https://arxiv.org/abs/2512.12576 - Sun, 14 Dec 2025 07:03:51 +0000 + Bolmo: Byteifying the Next Generation of Language Models + https://arxiv.org/abs/2512.15586 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.15586.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Benjamin Minixhofer, Tyler Murray, Tomasz Limisiewicz, Anna Korhonen, Luke Zettlemoyer, Noah A. Smith, Edoardo M. Ponti, Luca Soldaini, Valentin Hofmann</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce Bolmo, the first family of competitive fully open byte-level language models (LMs) at the 1B and 7B parameter scales. In contrast to prior research on byte-level LMs, which focuses predominantly on training from scratch, we train Bolmo by byteifying existing subword-level LMs. Byteification enables overcoming the limitations of subword tokenization - such as insufficient character understanding and efficiency constraints due to the fixed subword vocabulary - while performing at the level of leading subword-level LMs. Bolmo is specifically designed for byteification: our architecture resolves a mismatch between the expressivity of prior byte-level architectures and subword-level LMs, which makes it possible to employ an effective exact distillation objective between Bolmo and the source subword model. This allows for converting a subword-level LM to a byte-level LM by investing less than 1\% of a typical pretraining token budget. Bolmo substantially outperforms all prior byte-level LMs of comparable size, and outperforms the source subword-level LMs on character understanding and, in some cases, coding, while coming close to matching the original LMs' performance on other tasks. Furthermore, we show that Bolmo can achieve inference speeds competitive with subword-level LMs by training with higher token compression ratios, and can be cheaply and effectively post-trained by leveraging the existing ecosystem around the source subword-level LM. Our results finally make byte-level LMs a practical choice competitive with subword-level LMs across a wide set of use cases.</p> + https://arxiv.org/abs/2512.15586 + Wed, 17 Dec 2025 16:46:11 +0000 - Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space - https://arxiv.org/abs/2512.12623 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12623.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengzhi Liu, Yuzhe Yang, Yue Fan, Qingyue Wei, Sheng Liu, Xin Eric Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies extend the CoT mechanism to the visual modality, enabling models to integrate visual information during reasoning through external tools or explicit image generation. However, these methods remain dependent on explicit step-by-step reasoning, unstable perception-reasoning interaction and notable computational overhead. Inspired by human cognition, we posit that thinking unfolds not linearly but through the dynamic interleaving of reasoning and perception within the mind. Motivated by this perspective, we propose DMLR, a test-time Dynamic Multimodal Latent Reasoning framework that employs confidence-guided latent policy gradient optimization to refine latent think tokens for in-depth reasoning. Furthermore, a Dynamic Visual Injection Strategy is introduced, which retrieves the most relevant visual features at each latent think token and updates the set of best visual patches. The updated patches are then injected into latent think token to achieve dynamic visual-textual interleaving. Experiments across seven multimodal reasoning benchmarks and various model architectures demonstrate that DMLR significantly improves reasoning and perception performance while maintaining high inference efficiency.</p> - https://arxiv.org/abs/2512.12623 - Sun, 14 Dec 2025 10:07:45 +0000 + Are We on the Right Way to Assessing LLM-as-a-Judge? + https://arxiv.org/abs/2512.16041 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16041.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanning Feng, Sinan Wang, Zhengxiang Cheng, Yao Wan, Dongping Chen</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> LLM-as-a-Judge has been widely adopted as an evaluation method and served as supervised rewards in model training. However, existing benchmarks for LLM-as-a-Judge are mainly relying on human-annotated ground truth, which introduces human bias that undermines the assessment of reliability and imposes scalability constraints. To overcome these limitations, we introduce Sage, a novel evaluation suite that assesses the quality of LLM judges without necessitating any human annotation. Inspired by axioms of rational choice theory, Sage introduces two new lenses for measuring LLM-as-a-Judge: local self-consistency (pair-wise preference stability) and global logical consistency (transitivity across a full set of preferences). We curate a dataset of 650 questions by combining structured benchmark problems with real-world user queries. Our experiments demonstrate both the stability of our metrics and their high correlation with supervised benchmarks like LLMBar and RewardBench2, confirming Sage's reliability as an evaluation suite for the robustness and accuracy of LLM-as-a-Judge. Based on Sage, we reveal that current state-of-the-art LLMs exhibit significant reliability problems when acting as judges in both scoring and pairwise settings; even the top-performing models, Gemini-2.5-Pro and GPT-5, fail to maintain consistent preferences in nearly a quarter of difficult cases. We attribute this to a new phenomenon called situational preference, which explains why explicit rubrics or criteria can help the model judge consistently across answer pairs. Our further analysis shows that finetuned LLM-as-a-Judge is a feasible method to boost performance, and the panel-based judge as well as deep reasoning can enhance the judging consistency. We also find substantial inconsistency in human judgments, which indicates that human annotation may not be a reliable gold standard.</p> + https://arxiv.org/abs/2512.16041 + Wed, 17 Dec 2025 23:49:55 +0000 - Improving Recursive Transformers with Mixture of LoRAs - https://arxiv.org/abs/2512.12880 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammadmahdi Nouriborji, Morteza Rohanian, Omid Rohanian</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Parameter sharing in recursive transformers reduces model size but collapses layer-wise expressivity. We propose Mixture of LoRAs (MoL), a lightweight conditional-computation mechanism that inserts Low-Rank Adaptation (LoRA) experts inside a shared feed-forward network (FFN). MoL enables token-conditional weight-space modulation of the shared FFN without untying backbone parameters, unlike prior approaches that add fixed or externally attached adapters. We pretrain a modernised recursive architecture, ModernALBERT, integrating rotary embeddings, GeGLU, FlashAttention, and a distillation-based initialisation. Across GLUE, SQuAD-v2, and BEIR, ModernALBERT (50M--120M) achieves state-of-the-art performance among compact models and surpasses larger fully parameterised baselines. We also propose an expert-merging procedure that compresses MoL into a single adapter at inference while preserving accuracy, enabling efficient deployment. Our results show that conditional weight-space modulation effectively restores the expressivity lost under aggressive parameter sharing in recursive transformers.</p> - https://arxiv.org/abs/2512.12880 - Sun, 14 Dec 2025 23:39:30 +0000 + Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows + https://arxiv.org/abs/2512.16969 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16969.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanghan Xu, Yuhao Zhou, Yifan Zhou, Qinglong Cao, Shuo Li, Jia Bu, Bo Liu, Yixin Chen, Xuming He, Xiangyu Zhao, Xiang Zhuang, Fengxiang Wang, Zhiwang Zhou, Qiantai Feng, Wenxuan Huang, Jiaqi Wei, Hao Wu, Yuejin Yang, Guangshuai Wang, Sheng Xu, Ziyan Huang, Xinyao Liu, Jiyao Liu, Cheng Tang, Wei Li, Ying Chen, Junzhi Ning, Pengfei Jiang, Chenglong Ma, Ye Du, Changkai Ji, Huihui Xu, Ming Hu, Jiangbin Zheng, Xin Chen, Yucheng Wu, Feifei Jiang, Xi Chen, Xiangru Tang, Yuchen Fu, Yingzhou Lu, Yuanyuan Zhang, Lihao Sun, Chengbo Li, Jinzhe Ma, Wanhao Liu, Yating Liu, Kuo-Cheng Wu, Shengdu Chai, Yizhou Wang, Ouwen Zhangjin, Chen Tang, Shufei Zhang, Wenbo Cao, Junjie Ren, Taoyong Cui, Zhouheng Yao, Juntao Deng, Yijie Sun, Feng Liu, Wangxu Wei, Jingyi Xu, Zhangrui Li, Junchao Gong, Zijie Guo, Zhiyu Yao, Zaoyu Chen, Tianhao Peng, Fangchen Yu, Bo Zhang, Dongzhan Zhou, Shixiang Tang, Jiaheng Liu, Fenghua Ling, Yan Lu, Yuchen Ren, Ben Fei, Zhen Zhao, Xinyu Gu, Rui Su, Xiao-Ming Wu, Weikang Si, Yang Liu, Hao Chen, Xiangchao Yan, Xue Yang, Junchi Yan, Jiamin Wu, Qihao Zheng, Chenhui Li, Zhiqiang Gao, Hao Kong, Junjun He, Mao Su, Tianfan Fu, Peng Ye, Chunfeng Song, Nanqing Dong, Yuqiang Li, Huazhu Fu, Siqi Sun, Lijing Cheng, Jintai Lin, Wanli Ouyang, Bowen Zhou, Wenlong Zhang, Lei Bai</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.</p> + https://arxiv.org/abs/2512.16969 + Thu, 18 Dec 2025 12:44:36 +0000 - Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model - https://arxiv.org/abs/2512.13507 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13507.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heyi Chen, Siyan Chen, Xin Chen, Yanfei Chen, Ying Chen, Zhuo Chen, Feng Cheng, Tianheng Cheng, Xinqi Cheng, Xuyan Chi, Jian Cong, Jing Cui, Qinpeng Cui, Qide Dong, Junliang Fan, Jing Fang, Zetao Fang, Chengjian Feng, Han Feng, Mingyuan Gao, Yu Gao, Dong Guo, Qiushan Guo, Boyang Hao, Qingkai Hao, Bibo He, Qian He, Tuyen Hoang, Ruoqing Hu, Xi Hu, Weilin Huang, Zhaoyang Huang, Zhongyi Huang, Donglei Ji, Siqi Jiang, Wei Jiang, Yunpu Jiang, Zhuo Jiang, Ashley Kim, Jianan Kong, Zhichao Lai, Shanshan Lao, Yichong Leng, Ai Li, Feiya Li, Gen Li, Huixia Li, JiaShi Li, Liang Li, Ming Li, Shanshan Li, Tao Li, Xian Li, Xiaojie Li, Xiaoyang Li, Xingxing Li, Yameng Li, Yifu Li, Yiying Li, Chao Liang, Han Liang, Jianzhong Liang, Ying Liang, Zhiqiang Liang, Wang Liao, Yalin Liao, Heng Lin, Kengyu Lin, Shanchuan Lin, Xi Lin, Zhijie Lin, Feng Ling, Fangfang Liu, Gaohong Liu, Jiawei Liu, Jie Liu, Jihao Liu, Shouda Liu, Shu Liu, Sichao Liu, Songwei Liu, Xin Liu, Xue Liu, Yibo Liu, Zikun Liu, Zuxi Liu, Junlin Lyu, Lecheng Lyu, Qian Lyu, Han Mu, Xiaonan Nie, Jingzhe Ning, Xitong Pan, Yanghua Peng, Lianke Qin, Xueqiong Qu, Yuxi Ren, Kai Shen, Guang Shi, Lei Shi, Yan Song, Yinglong Song, Fan Sun, Li Sun, Renfei Sun, Yan Sun, Zeyu Sun, Wenjing Tang, Yaxue Tang, Zirui Tao, Feng Wang, Furui Wang, Jinran Wang, Junkai Wang, Ke Wang, Kexin Wang, Qingyi Wang, Rui Wang, Sen Wang, Shuai Wang, Tingru Wang, Weichen Wang, Xin Wang, Yanhui Wang, Yue Wang, Yuping Wang, Yuxuan Wang, Ziyu Wang, Guoqiang Wei, Wanru Wei, Di Wu, Guohong Wu, Hanjie Wu, Jian Wu, Jie Wu, Ruolan Wu, Xinglong Wu, Yonghui Wu, Ruiqi Xia, Liang Xiang, Fei Xiao, XueFeng Xiao, Pan Xie, Shuangyi Xie, Shuang Xu, Jinlan Xue, Shen Yan, Bangbang Yang, Ceyuan Yang, Jiaqi Yang, Runkai Yang, Tao Yang, Yang Yang, Yihang Yang, ZhiXian Yang, Ziyan Yang, Songting Yao, Yifan Yao, Zilyu Ye, Bowen Yu, Jian Yu, Chujie Yuan, Linxiao Yuan, Sichun Zeng, Weihong Zeng, Xuejiao Zeng, Yan Zeng, Chuntao Zhang, Heng Zhang, Jingjie Zhang, Kuo Zhang, Liang Zhang, Liying Zhang, Manlin Zhang, Ting Zhang, Weida Zhang, Xiaohe Zhang, Xinyan Zhang, Yan Zhang, Yuan Zhang, Zixiang Zhang, Fengxuan Zhao, Huating Zhao, Yang Zhao, Hao Zheng, Jianbin Zheng, Xiaozheng Zheng, Yangyang Zheng, Yijie Zheng, Jiexin Zhou, Jiahui Zhu, Kuan Zhu, Shenhan Zhu, Wenjia Zhu, Benhui Zou, Feilong Zuo</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.</p> - https://arxiv.org/abs/2512.13507 - Mon, 15 Dec 2025 16:36:52 +0000 + StageVAR: Stage-Aware Acceleration for Visual Autoregressive Models + https://arxiv.org/abs/2512.16483 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16483.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Senmao Li, Kai Wang, Salman Khan, Fahad Shahbaz Khan, Jian Yang, Yaxing Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale prediction, enabling high-quality image generation. However, the VAR paradigm suffers from sharply increased computational complexity and running time at large-scale steps. Although existing acceleration methods reduce runtime for large-scale steps, but rely on manual step selection and overlook the varying importance of different stages in the generation process. To address this challenge, we present StageVAR, a systematic study and stage-aware acceleration framework for VAR models. Our analysis shows that early steps are critical for preserving semantic and structural consistency and should remain intact, while later steps mainly refine details and can be pruned or approximated for acceleration. Building on these insights, StageVAR introduces a plug-and-play acceleration strategy that exploits semantic irrelevance and low-rank properties in late-stage computations, without requiring additional training. Our proposed StageVAR achieves up to 3.4x speedup with only a 0.01 drop on GenEval and a 0.26 decrease on DPG, consistently outperforming existing acceleration baselines. These results highlight stage-aware design as a powerful principle for efficient visual autoregressive image generation.</p> + https://arxiv.org/abs/2512.16483 + Thu, 18 Dec 2025 12:51:19 +0000 - Sharing State Between Prompts and Programs - https://arxiv.org/abs/2512.14805 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14805.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ellie Y. Cheng, Logan Weber, Tian Jin, Michael Carbin</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The rise of large language models (LLMs) has introduced a new type of programming: natural language programming. By writing prompts that direct LLMs to perform natural language processing, code generation, reasoning, etc., users are writing code in natural language -- natural language code -- for the LLM to execute. An emerging area of research enables interoperability between natural language code and formal languages such as Python. We present a novel programming abstraction, shared program state, that removes the manual work required to enable interoperability between natural language code and program state. With shared program state, programmers can write natural code that directly writes program variables, computes with program objects, and implements control flow in the program. We present a schema for specifying natural function interfaces that extend programming systems to support natural code and leverage this schema to specify shared program state as a natural function interface. We implement shared program state in the Nightjar programming system. Nightjar enables programmers to write Python programs that contain natural code that shares the Python program state. We show that Nightjar programs achieve comparable or higher task accuracy than manually written implementations (+4-19%), while decreasing the lines of code by 39.6% on average. The tradeoff to using Nightjar is that it may incur runtime overhead (0.4-4.3x runtime of manual implementations).</p> - https://arxiv.org/abs/2512.14805 - Tue, 16 Dec 2025 18:41:50 +0000 + PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence + https://arxiv.org/abs/2512.16793 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaopeng Lin, Shijie Lian, Bin Yu, Ruoqi Yang, Changti Wu, Yuzhuo Miao, Yurun Jin, Yukun Shi, Cong Huang, Bojun Cheng, Kai Chen</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Robotic generalization relies on physical intelligence: the ability to reason about state changes, contact-rich interactions, and long-horizon planning under egocentric perception and action. However, most VLMs are trained primarily on third-person data, creating a fundamental viewpoint mismatch for humanoid robots. Scaling robot egocentric data collection remains impractical due to high cost and limited diversity, whereas large-scale human egocentric videos offer a scalable alternative that naturally capture rich interaction context and causal structure. The key challenge is to convert raw egocentric videos into structured and reliable embodiment training supervision. Accordingly, we propose an Egocentric2Embodiment translation pipeline that transforms first-person videos into multi-level, schema-driven VQA supervision with enforced evidence grounding and temporal consistency, enabling the construction of the Egocentric2Embodiment dataset (E2E-3M) at scale. An egocentric-aware embodied brain, termed PhysBrain, is obtained by training on the E2E-3M dataset. PhysBrain exhibits substantially improved egocentric understanding, particularly for planning on EgoThink. It provides an egocentric-aware initialization that enables more sample-efficient VLA fine-tuning and higher SimplerEnv success rates (53.9\%), demonstrating effective transfer from human egocentric supervision to downstream robot control.</p> + https://arxiv.org/abs/2512.16793 + Thu, 18 Dec 2025 17:27:03 +0000 - Vibe Spaces for Creatively Connecting and Expressing Visual Concepts - https://arxiv.org/abs/2512.14884 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14884.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huzheng Yang, Katherine Xu, Andrew Lu, Michael D. Grossberg, Yutong Bai, Jianbo Shi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Creating new visual concepts often requires connecting distinct ideas through their most relevant shared attributes -- their vibe. We introduce Vibe Blending, a novel task for generating coherent and meaningful hybrids that reveals these shared attributes between images. Achieving such blends is challenging for current methods, which struggle to identify and traverse nonlinear paths linking distant concepts in latent space. We propose Vibe Space, a hierarchical graph manifold that learns low-dimensional geodesics in feature spaces like CLIP, enabling smooth and semantically consistent transitions between concepts. To evaluate creative quality, we design a cognitively inspired framework combining human judgments, LLM reasoning, and a geometric path-based difficulty score. We find that Vibe Space produces blends that humans consistently rate as more creative and coherent than current methods.</p> - https://arxiv.org/abs/2512.14884 - Tue, 16 Dec 2025 20:03:23 +0000 + Meta-RL Induces Exploration in Language Agents + https://arxiv.org/abs/2512.16848 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulun Jiang, Liangze Jiang, Damien Teney, Michael Moor, Maria Brbic</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement learning (RL) has enabled the training of large language model (LLM) agents to interact with the environment and to solve multi-turn long-horizon tasks. However, the RL-trained agents often struggle in tasks that require active exploration and fail to efficiently adapt from trial-and-error experiences. In this paper, we present LaMer, a general Meta-RL framework that enables LLM agents to actively explore and learn from the environment feedback at test time. LaMer consists of two key components: (i) a cross-episode training framework to encourage exploration and long-term rewards optimization; and (ii) in-context policy adaptation via reflection, allowing the agent to adapt their policy from task feedback signal without gradient update. Experiments across diverse environments show that LaMer significantly improves performance over RL baselines, with 11%, 14%, and 19% performance gains on Sokoban, MineSweeper and Webshop, respectively. Moreover, LaMer also demonstrates better generalization to more challenging or previously unseen tasks compared to the RL-trained agents. Overall, our results demonstrate that Meta-RL provides a principled approach to induce exploration in language agents, enabling more robust adaptation to novel environments through learned exploration strategies.</p> + https://arxiv.org/abs/2512.16848 + Thu, 18 Dec 2025 18:22:17 +0000 - Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision - https://arxiv.org/abs/2512.15489 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.15489.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Du, Shubham Toshniwal, Branislav Kisacanin, Sadegh Mahdavi, Ivan Moshkov, George Armstrong, Stephen Ge, Edgar Minasyan, Feng Chen, Igor Gitman</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> High-quality mathematical reasoning supervision requires diverse reasoning styles, long-form traces, and effective tool integration, capabilities that existing datasets provide only in limited form. Leveraging the multi-mode generation ability of gpt-oss-120b, we introduce Nemotron-Math, a large-scale mathematical reasoning dataset containing 7.5M solution traces across high, medium, and low reasoning modes, each available both with and without Python tool-integrated reasoning (TIR). The dataset integrates 85K curated AoPS problems with 262K community-sourced StackExchange-Math problems, combining structured competition tasks with diverse real-world mathematical queries. We conduct controlled evaluations to assess the dataset quality. Nemotron-Math consistently outperforms the original OpenMathReasoning on matched AoPS problems. Incorporating StackExchange-Math substantially improves robustness and generalization, especially on HLE-Math, while preserving accuracy on math competition benchmarks. To support efficient long-context training, we develop a sequential bucketed strategy that accelerates 128K context-length fine-tuning by 2--3times without significant accuracy loss. Overall, Nemotron-Math enables state-of-the-art performance, including 100\% maj@16 accuracy on AIME 2024 and 2025 with Python TIR.</p> - https://arxiv.org/abs/2512.15489 - Wed, 17 Dec 2025 14:37:41 +0000 + Animate Any Character in Any World + https://arxiv.org/abs/2512.17796 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17796.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitong Wang, Fangyun Wei, Hongyang Zhang, Bo Dai, Yan Lu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent advances in world models have greatly enhanced interactive environment simulation. Existing methods mainly fall into two categories: (1) static world generation models, which construct 3D environments without active agents, and (2) controllable-entity models, which allow a single entity to perform limited actions in an otherwise uncontrollable environment. In this work, we introduce AniX, leveraging the realism and structural grounding of static world generation while extending controllable-entity models to support user-specified characters capable of performing open-ended actions. Users can provide a 3DGS scene and a character, then direct the character through natural language to perform diverse behaviors from basic locomotion to object-centric interactions while freely exploring the environment. AniX synthesizes temporally coherent video clips that preserve visual fidelity with the provided scene and character, formulated as a conditional autoregressive video generation problem. Built upon a pre-trained video generator, our training strategy significantly enhances motion dynamics while maintaining generalization across actions and characters. Our evaluation covers a broad range of aspects, including visual quality, character consistency, action controllability, and long-horizon coherence.</p> + https://arxiv.org/abs/2512.17796 + Thu, 18 Dec 2025 18:59:18 +0000 - EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration - https://arxiv.org/abs/2512.15528 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.15528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daiqing Wu, Dongbao Yang, Can Ma. Yu Zhou</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Visual Emotion Comprehension (VEC) aims to infer sentiment polarities or emotion categories from affective cues embedded in images. In recent years, Multimodal Large Language Models (MLLMs) have established a popular paradigm in VEC, leveraging their generalizability to unify VEC tasks defined under diverse emotion taxonomies. While this paradigm achieves notable success, it typically formulates VEC as a deterministic task, requiring the model to output a single, definitive emotion label for each image. Such a formulation insufficiently accounts for the inherent subjectivity of emotion perception, overlooking alternative interpretations that may be equally plausible to different viewers. To address this limitation, we propose equipping MLLMs with capabilities to verbalize their confidence in emotion predictions. This additional signal provides users with an estimate of both the plausibility of alternative interpretations and the MLLMs' self-assessed competence, thereby enhancing reliability in practice. Building on this insight, we introduce a three-stage training framework that progressively endows with structured reasoning, teaches to verbalize confidence, and calibrates confidence expression, culminating in EmoCaliber, a confidence-aware MLLM for VEC. Through fair and comprehensive evaluations on the unified benchmark VECBench, EmoCaliber demonstrates overall superiority against existing methods in both emotion prediction and confidence estimation. These results validate the effectiveness of our approach and mark a feasible step toward more reliable VEC systems. Project page: https://github.com/wdqqdw/EmoCaliber.</p> - https://arxiv.org/abs/2512.15528 - Wed, 17 Dec 2025 15:30:50 +0000 - - - TabReX : Tabular Referenceless eXplainable Evaluation - https://arxiv.org/abs/2512.15907 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.15907.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tejas Anvekar, Juhna Park, Aparna Garimella, Vivek Gupta</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Evaluating the quality of tables generated by large language models (LLMs) remains an open challenge: existing metrics either flatten tables into text, ignoring structure, or rely on fixed references that limit generalization. We present TabReX, a reference-less, property-driven framework for evaluating tabular generation via graph-based reasoning. TabReX converts both source text and generated tables into canonical knowledge graphs, aligns them through an LLM-guided matching process, and computes interpretable, rubric-aware scores that quantify structural and factual fidelity. The resulting metric provides controllable trade-offs between sensitivity and specificity, yielding human-aligned judgments and cell-level error traces. To systematically asses metric robustness, we introduce TabReX-Bench, a large-scale benchmark spanning six domains and twelve planner-driven perturbation types across three difficulty tiers. Empirical results show that TabReX achieves the highest correlation with expert rankings, remains stable under harder perturbations, and enables fine-grained model-vs-prompt analysis establishing a new paradigm for trustworthy, explainable evaluation of structured generation systems.</p> - https://arxiv.org/abs/2512.15907 - Wed, 17 Dec 2025 19:20:20 +0000 - - - ModelTables: A Corpus of Tables about Models - https://arxiv.org/abs/2512.16106 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengyuan Dong, Victor Zhong, Renée J. Miller</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present ModelTables, a benchmark of tables in Model Lakes that captures the structured semantics of performance and configuration tables often overlooked by text only retrieval. The corpus is built from Hugging Face model cards, GitHub READMEs, and referenced papers, linking each table to its surrounding model and publication context. Compared with open data lake tables, model tables are smaller yet exhibit denser inter table relationships, reflecting tightly coupled model and benchmark evolution. The current release covers over 60K models and 90K tables. To evaluate model and table relatedness, we construct a multi source ground truth using three complementary signals: (1) paper citation links, (2) explicit model card links and inheritance, and (3) shared training datasets. We present one extensive empirical use case for the benchmark which is table search. We compare canonical Data Lake search operators (unionable, joinable, keyword) and Information Retrieval baselines (dense, sparse, hybrid retrieval) on this benchmark. Union based semantic table retrieval attains 54.8 % P@1 overall (54.6 % on citation, 31.3 % on inheritance, 30.6 % on shared dataset signals); table based dense retrieval reaches 66.5 % P@1, and metadata hybrid retrieval achieves 54.1 %. This evaluation indicates clear room for developing better table search methods. By releasing ModelTables and its creation protocol, we provide the first large scale benchmark of structured data describing AI model. Our use case of table discovery in Model Lakes, provides intuition and evidence for developing more accurate semantic retrieval, structured comparison, and principled organization of structured model knowledge. Source code, data, and other artifacts have been made available at https://github.com/RJMillerLab/ModelTables.</p> - https://arxiv.org/abs/2512.16106 - Thu, 18 Dec 2025 02:51:46 +0000 - - - Adaptation of Agentic AI - https://arxiv.org/abs/2512.16301 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi, Zifeng Wang, Luxi He, Yichen Wu, Ming Zhong, Peiyang Song, Qizheng Zhang, Heng Wang, Xueqiang Xu, Hanwen Xu, Pengrui Han, Dylan Zhang, Jiashuo Sun, Chaoqi Yang, Kun Qian, Tian Wang, Changran Hu, Manling Li, Quanzheng Li, Hao Peng, Sheng Wang, Jingbo Shang, Chao Zhang, Jiaxuan You, Liyuan Liu, Pan Lu, Yu Zhang, Heng Ji, Yejin Choi, Dawn Song, Jimeng Sun, Jiawei Han</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Cutting-edge agentic AI systems are built on foundation models that can be adapted to plan, reason, and interact with external tools to perform increasingly complex and specialized tasks. As these systems grow in capability and scope, adaptation becomes a central mechanism for improving performance, reliability, and generalization. In this paper, we unify the rapidly expanding research landscape into a systematic framework that spans both agent adaptations and tool adaptations. We further decompose these into tool-execution-signaled and agent-output-signaled forms of agent adaptation, as well as agent-agnostic and agent-supervised forms of tool adaptation. We demonstrate that this framework helps clarify the design space of adaptation strategies in agentic AI, makes their trade-offs explicit, and provides practical guidance for selecting or switching among strategies during system design. We then review the representative approaches in each category, analyze their strengths and limitations, and highlight key open challenges and future opportunities. Overall, this paper aims to offer a conceptual foundation and practical roadmap for researchers and practitioners seeking to build more capable, efficient, and reliable agentic AI systems.</p> - https://arxiv.org/abs/2512.16301 - Thu, 18 Dec 2025 08:38:51 +0000 - - - Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs - https://arxiv.org/abs/2512.16378 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16378.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sara Papi, Javier Garcia Gilabert, Zachary Hopton, Vilém Zouhar, Carlos Escolano, Gerard I. Gállego, Jorge Iranzo-Sánchez, Ahrii Kim, Dominik Macháček, Patricia Schmidtova, Maike Züfle</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which aim to translate spoken language directly, thereby bypassing traditional transcription-based pipelines. Whether this integration improves speech-to-text translation quality over established cascaded architectures, however, remains an open question. We present Hearing to Translate, the first comprehensive test suite rigorously benchmarking 5 state-of-the-art SpeechLLMs against 16 strong direct and cascade systems that couple leading speech foundation models (SFM), with multilingual LLMs. Our analysis spans 16 benchmarks, 13 language pairs, and 9 challenging conditions, including disfluent, noisy, and long-form speech. Across this extensive evaluation, we find that cascaded systems remain the most reliable overall, while current SpeechLLMs only match cascades in selected settings and SFMs lag behind both, highlighting that integrating an LLM, either within the model or in a pipeline, is essential for high-quality speech translation.</p> - https://arxiv.org/abs/2512.16378 - Thu, 18 Dec 2025 10:21:14 +0000 - - - VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks - https://arxiv.org/abs/2512.16501 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Beitong Zhou, Zhexiao Huang, Yuan Guo, Zhangxuan Gu, Tianyu Xia, Zichen Luo, Fei Tang, Dehan Kong, Yanyi Shang, Suling Ou, Zhenlin Guo, Changhua Meng, Shuheng Shen</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> GUI grounding is a critical component in building capable GUI agents. However, existing grounding benchmarks suffer from significant limitations: they either provide insufficient data volume and narrow domain coverage, or focus excessively on a single platform and require highly specialized domain knowledge. In this work, we present VenusBench-GD, a comprehensive, bilingual benchmark for GUI grounding that spans multiple platforms, enabling hierarchical evaluation for real-word applications. VenusBench-GD contributes as follows: (i) we introduce a large-scale, cross-platform benchmark with extensive coverage of applications, diverse UI elements, and rich annotated data, (ii) we establish a high-quality data construction pipeline for grounding tasks, achieving higher annotation accuracy than existing benchmarks, and (iii) we extend the scope of element grounding by proposing a hierarchical task taxonomy that divides grounding into basic and advanced categories, encompassing six distinct subtasks designed to evaluate models from complementary perspectives. Our experimental findings reveal critical insights: general-purpose multimodal models now match or even surpass specialized GUI models on basic grounding tasks. In contrast, advanced tasks, still favor GUI-specialized models, though they exhibit significant overfitting and poor robustness. These results underscore the necessity of comprehensive, multi-tiered evaluation frameworks.</p> - https://arxiv.org/abs/2512.16501 - Thu, 18 Dec 2025 13:09:09 +0000 - - - N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models - https://arxiv.org/abs/2512.16561 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16561.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxin Wang, Lei Ke, Boqiang Zhang, Tianyuan Qu, Hanxun Yu, Zhenpeng Huang, Meng Yu, Dan Xu, Dong Yu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a novel unified framework that seamlessly integrates native 3D object perception with 3D-aware visual reasoning, enabling both precise 3D grounding and interpretable spatial understanding. Unlike conventional end-to-end models that directly predict answers from RGB/RGB-D inputs, our approach equips the model with native 3D object perception capabilities, enabling it to directly localize objects in 3D space based on textual descriptions. Building upon accurate 3D object localization, the model further performs explicit reasoning in 3D, achieving more interpretable and structured spatial understanding. To support robust training for these capabilities, we develop a scalable data construction pipeline that leverages depth estimation to lift large-scale 2D annotations into 3D space, significantly increasing the diversity and coverage for 3D object grounding data, yielding over six times larger than the largest existing single-image 3D detection dataset. Moreover, the pipeline generates spatial question-answering datasets that target chain-of-thought (CoT) reasoning in 3D, facilitating joint training for both 3D object localization and 3D spatial reasoning. Experimental results demonstrate that our unified framework not only achieves state-of-the-art performance on 3D grounding tasks, but also consistently surpasses existing methods in 3D spatial reasoning in vision-language model.</p> - https://arxiv.org/abs/2512.16561 - Thu, 18 Dec 2025 14:03:44 +0000 - - - Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers - https://arxiv.org/abs/2512.16615 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16615.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Zhou, Zeqi Xiao, Tianyi Wei, Shuai Yang, Xingang Pan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of DiTs by compressing tokens into block-wise representation and selecting a small set of relevant key blocks, but still suffer from (i) quadratic selection cost on compressed tokens and (ii) increasing K required to maintain model quality as sequences grow. We identify that their inefficiency is due to the single-level design, as a single coarse level is insufficient to represent the global structure. In this paper, we introduce Log-linear Sparse Attention (LLSA), a trainable sparse attention mechanism for extremely long token sequences that reduces both selection and attention costs from quadratic to log-linear complexity by utilizing a hierarchical structure. LLSA performs hierarchical Top-K selection, progressively adopting sparse Top-K selection with the indices found at the previous level, and introduces a Hierarchical KV Enrichment mechanism that preserves global context while using fewer tokens of different granularity during attention computation. To support efficient training, we develop a high-performance GPU implementation that uses only sparse indices for both the forward and backward passes, eliminating the need for dense attention masks. We evaluate LLSA on high-resolution pixel-space image generation without using patchification and VAE encoding. LLSA accelerates attention inference by 28.27x and DiT training by 6.09x on 256x256 pixel token sequences, while maintaining generation quality. The results demonstrate that LLSA offers a promising direction for training long-sequence DiTs efficiently. Code is available at: https://github.com/SingleZombie/LLSA</p> - https://arxiv.org/abs/2512.16615 - Thu, 18 Dec 2025 14:53:12 +0000 - - - DeContext as Defense: Safe Image Editing in Diffusion Transformers - https://arxiv.org/abs/2512.16625 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16625.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linghui Shen, Mingyue Cui, Xingyi Yang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily manipulated for identity impersonation, misinformation, or other malicious uses, all without the owner's consent. While prior work has explored input perturbations to protect against misuse in personalized text-to-image generation, the robustness of modern, large-scale in-context DiT-based models remains largely unexamined. In this paper, we propose DeContext, a new method to safeguard input images from unauthorized in-context editing. Our key insight is that contextual information from the source image propagates to the output primarily through multimodal attention layers. By injecting small, targeted perturbations that weaken these cross-attention pathways, DeContext breaks this flow, effectively decouples the link between input and output. This simple defense is both efficient and robust. We further show that early denoising steps and specific transformer blocks dominate context propagation, which allows us to concentrate perturbations where they matter most. Experiments on Flux Kontext and Step1X-Edit show that DeContext consistently blocks unwanted image edits while preserving visual quality. These results highlight the effectiveness of attention-based perturbations as a powerful defense against image manipulation.</p> - https://arxiv.org/abs/2512.16625 - Thu, 18 Dec 2025 15:01:44 +0000 - - - REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion - https://arxiv.org/abs/2512.16636 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16636.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Giorgos Petsangourakis, Christos Sgouropoulos, Bill Psomas, Theodoros Giannakopoulos, Giorgos Sfikas, Ioannis Kakogeorgiou</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Latent diffusion models (LDMs) achieve state-of-the-art image synthesis, yet their reconstruction-style denoising objective provides only indirect semantic supervision: high-level semantics emerge slowly, requiring longer training and limiting sample quality. Recent works inject semantics from Vision Foundation Models (VFMs) either externally via representation alignment or internally by jointly modeling only a narrow slice of VFM features inside the diffusion process, under-utilizing the rich, nonlinear, multi-layer spatial semantics available. We introduce REGLUE (Representation Entanglement with Global-Local Unified Encoding), a unified latent diffusion framework that jointly models (i) VAE image latents, (ii) compact local (patch-level) VFM semantics, and (iii) a global (image-level) [CLS] token within a single SiT backbone. A lightweight convolutional semantic compressor nonlinearly aggregates multi-layer VFM features into a low-dimensional, spatially structured representation, which is entangled with the VAE latents in the diffusion process. An external alignment loss further regularizes internal representations toward frozen VFM targets. On ImageNet 256x256, REGLUE consistently improves FID and accelerates convergence over SiT-B/2 and SiT-XL/2 baselines, as well as over REPA, ReDi, and REG. Extensive experiments show that (a) spatial VFM semantics are crucial, (b) non-linear compression is key to unlocking their full benefit, and (c) global tokens and external alignment act as complementary, lightweight enhancements within our global-local-latent joint modeling framework. The code is available at https://github.com/giorgospets/reglue .</p> - https://arxiv.org/abs/2512.16636 - Thu, 18 Dec 2025 15:10:42 +0000 - - - JustRL: Scaling a 1.5B LLM with a Simple RL Recipe - https://arxiv.org/abs/2512.16649 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16649.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bingxiang He, Zekai Qu, Zeyuan Liu, Yinghao Chen, Yuxin Zuo, Cheng Qian, Kaiyan Zhang, Weize Chen, Chaojun Xiao, Ganqu Cui, Ning Ding, Zhiyuan Liu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Recent advances in reinforcement learning for large language models have converged on increasing complexity: multi-stage training pipelines, dynamic hyperparameter schedules, and curriculum learning strategies. This raises a fundamental question: Is this complexity necessary? We present JustRL, a minimal approach using single-stage training with fixed hyperparameters that achieves state-of-the-art performance on two 1.5B reasoning models (54.9\% and 64.3\% average accuracy across nine mathematical benchmarks) while using 2times less compute than sophisticated approaches. The same hyperparameters transfer across both models without tuning, and training exhibits smooth, monotonic improvement over 4,000+ steps without the collapses or plateaus that typically motivate interventions. Critically, ablations reveal that adding ``standard tricks'' like explicit length penalties and robust verifiers may degrade performance by collapsing exploration. These results suggest that the field may be adding complexity to solve problems that disappear with a stable, scaled-up baseline. We release our models and code to establish a simple, validated baseline for the community.</p> - https://arxiv.org/abs/2512.16649 - Thu, 18 Dec 2025 15:21:25 +0000 - - - FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering - https://arxiv.org/abs/2512.16670 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16670.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ole Beisswenger, Jan-Niklas Dihlmann, Hendrik P. A. Lensch</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Neural rendering for interactive applications requires translating geometric and material properties (G-buffer) to photorealistic images with realistic lighting on a frame-by-frame basis. While recent diffusion-based approaches show promise for G-buffer-conditioned image synthesis, they face critical limitations: single-image models like RGBX generate frames independently without temporal consistency, while video models like DiffusionRenderer are too computationally expensive for most consumer gaming sets ups and require complete sequences upfront, making them unsuitable for interactive applications where future frames depend on user input. We introduce FrameDiffuser, an autoregressive neural rendering framework that generates temporally consistent, photorealistic frames by conditioning on G-buffer data and the models own previous output. After an initial frame, FrameDiffuser operates purely on incoming G-buffer data, comprising geometry, materials, and surface properties, while using its previously generated frame for temporal guidance, maintaining stable, temporal consistent generation over hundreds to thousands of frames. Our dual-conditioning architecture combines ControlNet for structural guidance with ControlLoRA for temporal coherence. A three-stage training strategy enables stable autoregressive generation. We specialize our model to individual environments, prioritizing consistency and inference speed over broad generalization, demonstrating that environment-specific training achieves superior photorealistic quality with accurate lighting, shadows, and reflections compared to generalized approaches.</p> - https://arxiv.org/abs/2512.16670 - Thu, 18 Dec 2025 15:41:08 +0000 - - - Make-It-Poseable: Feed-forward Latent Posing Model for 3D Humanoid Character Animation - https://arxiv.org/abs/2512.16767 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16767.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyang Guo, Ori Zhang, Jax Xiang, Alan Zhao, Wengang Zhou, Houqiang Li</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Posing 3D characters is a fundamental task in computer graphics and vision. However, existing methods like auto-rigging and pose-conditioned generation often struggle with challenges such as inaccurate skinning weight prediction, topological imperfections, and poor pose conformance, limiting their robustness and generalizability. To overcome these limitations, we introduce Make-It-Poseable, a novel feed-forward framework that reformulates character posing as a latent-space transformation problem. Instead of deforming mesh vertices as in traditional pipelines, our method reconstructs the character in new poses by directly manipulating its latent representation. At the core of our method is a latent posing transformer that manipulates shape tokens based on skeletal motion. This process is facilitated by a dense pose representation for precise control. To ensure high-fidelity geometry and accommodate topological changes, we also introduce a latent-space supervision strategy and an adaptive completion module. Our method demonstrates superior performance in posing quality. It also naturally extends to 3D editing applications like part replacement and refinement.</p> - https://arxiv.org/abs/2512.16767 - Thu, 18 Dec 2025 17:01:44 +0000 - - - Kling-Omni Technical Report - https://arxiv.org/abs/2512.16776 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16776.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kling Team, Jialu Chen, Yuanzheng Ci, Xiangyu Du, Zipeng Feng, Kun Gai, Sainan Guo, Feng Han, Jingbin He, Kang He, Xiao Hu, Xiaohua Hu, Boyuan Jiang, Fangyuan Kong, Hang Li, Jie Li, Qingyu Li, Shen Li, Xiaohan Li, Yan Li, Jiajun Liang, Borui Liao, Yiqiao Liao, Weihong Lin, Quande Liu, Xiaokun Liu, Yilun Liu, Yuliang Liu, Shun Lu, Hangyu Mao, Yunyao Mao, Haodong Ouyang, Wenyu Qin, Wanqi Shi, Xiaoyu Shi, Lianghao Su, Haozhi Sun, Peiqin Sun, Pengfei Wan, Chao Wang, Chenyu Wang, Meng Wang, Qiulin Wang, Runqi Wang, Xintao Wang, Xuebo Wang, Zekun Wang, Min Wei, Tiancheng Wen, Guohao Wu, Xiaoshi Wu, Zhenhua Wu, Da Xie, Yingtong Xiong, Yulong Xu, Sile Yang, Zikang Yang, Weicai Ye, Ziyang Yuan, Shenglong Zhang, Shuaiyu Zhang, Yuanxing Zhang, Yufan Zhang, Wenzheng Zhao, Ruiliang Zhou, Yan Zhou, Guosheng Zhu, Yongjie Zhu</p><p><b>Upvotes:</b> 135</p><p><b>Summary:</b> We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.</p> - https://arxiv.org/abs/2512.16776 - Thu, 18 Dec 2025 17:08:12 +0000 - - - RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing - https://arxiv.org/abs/2512.16864 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16864.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyuan Qu, Lei Ke, Xiaohang Zhan, Longxiang Tang, Yuqi Liu, Bohao Peng, Bei Yu, Dong Yu, Jiaya Jia</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, parallel multi-region edits without iterative inpainting. To strengthen planning, we apply GRPO-based reinforcement learning using 1K instruction-only examples, yielding substantial gains in reasoning fidelity and format reliability. We further present IV-Edit, a benchmark focused on fine-grained grounding and knowledge-intensive edits. Across IV-Complex settings, RePlan consistently outperforms strong baselines trained on far larger datasets, improving regional precision and overall fidelity. Our project page: https://replan-iv-edit.github.io</p> - https://arxiv.org/abs/2512.16864 - Thu, 18 Dec 2025 18:34:23 +0000 - - - Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image - https://arxiv.org/abs/2512.16899 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16899.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yushi Hu, Reyhane Askari-Hemmat, Melissa Hall, Emily Dinan, Luke Zettlemoyer, Marjan Ghazvininejad</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Reward models (RMs) are essential for training large language models (LLMs), but remain underexplored for omni models that handle interleaved image and text sequences. We introduce Multimodal RewardBench 2 (MMRB2), the first comprehensive benchmark for reward models on multimodal understanding and (interleaved) generation. MMRB2 spans four tasks: text-to-image, image editing, interleaved generation, and multimodal reasoning ("thinking-with-images"), providing 1,000 expert-annotated preference pairs per task from 23 models and agents across 21 source tasks. MMRB2 is designed with: (1) practical but challenging prompts; (2) responses from state-of-the-art models and agents; and (3) preference pairs with strong human-expert consensus, curated via an ensemble filtering strategy. Using MMRB2, we study existing judges for each subtask, including multimodal LLM-as-a-judge and models trained with human preferences. The latest Gemini 3 Pro attains 75-80% accuracy. GPT-5 and Gemini 2.5 Pro reach 66-75% accuracy, compared to >90% for humans, yet surpass the widely used GPT-4o (59%). The best performing open-source model Qwen3-VL-32B achieves similar accuracies as Gemini 2.5 Flash (64%). We also show that MMRB2 performance strongly correlates with downstream task success using Best-of-N sampling and conduct an in-depth analysis that shows key areas to improve the reward models going forward.</p> - https://arxiv.org/abs/2512.16899 - Thu, 18 Dec 2025 18:56:04 +0000 - - - FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction - https://arxiv.org/abs/2512.16900 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16900.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuyuan Tu, Yueming Pan, Yinming Huang, Xintong Han, Zhen Xing, Qi Dai, Kai Qiu, Chong Luo, Zuxuan Wu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6x acceleration in inference speed. In particular, FlashPortrait begins by computing the identity-agnostic facial expression features with an off-the-shelf extractor. It then introduces a Normalized Facial Expression Block to align facial features with diffusion latents by normalizing them with their respective means and variances, thereby improving identity stability in facial modeling. During inference, FlashPortrait adopts a dynamic sliding-window scheme with weighted blending in overlapping areas, ensuring smooth transitions and ID consistency in long animations. In each context window, based on the latent variation rate at particular timesteps and the derivative magnitude ratio among diffusion layers, FlashPortrait utilizes higher-order latent derivatives at the current timestep to directly predict latents at future timesteps, thereby skipping several denoising steps and achieving 6x speed acceleration. Experiments on benchmarks show the effectiveness of FlashPortrait both qualitatively and quantitatively.</p> - https://arxiv.org/abs/2512.16900 - Thu, 18 Dec 2025 18:56:05 +0000 - - - Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection - https://arxiv.org/abs/2512.16905 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16905.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaixin Ding, Yang Zhou, Xi Chen, Miao Yang, Jiarong Ou, Rui Chen, Xin Tao, Hengshuang Zhao</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Recent advances in Text-to-Image (T2I) generative models, such as Imagen, Stable Diffusion, and FLUX, have led to remarkable improvements in visual quality. However, their performance is fundamentally limited by the quality of training data. Web-crawled and synthetic image datasets often contain low-quality or redundant samples, which lead to degraded visual fidelity, unstable training, and inefficient computation. Hence, effective data selection is crucial for improving data efficiency. Existing approaches rely on costly manual curation or heuristic scoring based on single-dimensional features in Text-to-Image data filtering. Although meta-learning based method has been explored in LLM, there is no adaptation for image modalities. To this end, we propose **Alchemist**, a meta-gradient-based framework to select a suitable subset from large-scale text-image data pairs. Our approach automatically learns to assess the influence of each sample by iteratively optimizing the model from a data-centric perspective. Alchemist consists of two key stages: data rating and data pruning. We train a lightweight rater to estimate each sample's influence based on gradient information, enhanced with multi-granularity perception. We then use the Shift-Gsampling strategy to select informative subsets for efficient model training. Alchemist is the first automatic, scalable, meta-gradient-based data selection framework for Text-to-Image model training. Experiments on both synthetic and web-crawled datasets demonstrate that Alchemist consistently improves visual quality and downstream performance. Training on an Alchemist-selected 50% of the data can outperform training on the full dataset.</p> - https://arxiv.org/abs/2512.16905 - Thu, 18 Dec 2025 18:57:58 +0000 - - - MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning - https://arxiv.org/abs/2512.16909 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16909.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanchen Ju, Yongyuan Liang, Yen-Jen Wang, Nandiraju Gireesh, Yuanliang Ju, Seungjae Lee, Qiao Gu, Elvis Hsieh, Furong Huang, Koushil Sreenath</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Mobile manipulators in households must both navigate and manipulate. This requires a compact, semantically rich scene representation that captures where objects are, how they function, and which parts are actionable. Scene graphs are a natural choice, yet prior work often separates spatial and functional relations, treats scenes as static snapshots without object states or temporal updates, and overlooks information most relevant for accomplishing the current task. To address these limitations, we introduce MomaGraph, a unified scene representation for embodied agents that integrates spatial-functional relationships and part-level interactive elements. However, advancing such a representation requires both suitable data and rigorous evaluation, which have been largely missing. We thus contribute MomaGraph-Scenes, the first large-scale dataset of richly annotated, task-driven scene graphs in household environments, along with MomaGraph-Bench, a systematic evaluation suite spanning six reasoning capabilities from high-level planning to fine-grained scene understanding. Built upon this foundation, we further develop MomaGraph-R1, a 7B vision-language model trained with reinforcement learning on MomaGraph-Scenes. MomaGraph-R1 predicts task-oriented scene graphs and serves as a zero-shot task planner under a Graph-then-Plan framework. Extensive experiments demonstrate that our model achieves state-of-the-art results among open-source models, reaching 71.6% accuracy on the benchmark (+11.4% over the best baseline), while generalizing across public benchmarks and transferring effectively to real-robot experiments.</p> - https://arxiv.org/abs/2512.16909 - Thu, 18 Dec 2025 18:59:03 +0000 - - - Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward - https://arxiv.org/abs/2512.16912 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16912.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peter Chen, Xiaopeng Li, Ziniu Li, Wotao Yin, Xi Chen, Tianyi Lin</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Models (LLMs). Recent studies suggest that RLVR can elicit strong mathematical reasoning in LLMs through two seemingly paradoxical mechanisms: spurious rewards, which suppress exploitation by rewarding outcomes unrelated to the ground truth, and entropy minimization, which suppresses exploration by pushing the model toward more confident and deterministic outputs, highlighting a puzzling dynamic: both discouraging exploitation and discouraging exploration improve reasoning performance, yet the underlying principles that reconcile these effects remain poorly understood. We focus on two fundamental questions: (i) how policy entropy relates to performance, and (ii) whether spurious rewards yield gains, potentially through the interplay of clipping bias and model contamination. Our results show that clipping bias under spurious rewards reduces policy entropy, leading to more confident and deterministic outputs, while entropy minimization alone is insufficient for improvement. We further propose a reward-misalignment model explaining why spurious rewards can enhance performance beyond contaminated settings. Our findings clarify the mechanisms behind spurious-reward benefits and provide principles for more effective RLVR training.</p> - https://arxiv.org/abs/2512.16912 + A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos + https://arxiv.org/abs/2512.16978 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16978.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Jinxing Zhou, Sahal Shaji Mullappilly, Mohammad Almansoori, Noor Ahsan, Beknur Kalmakhanbet, Sambal Shikhar, Rishabh Lalla, Jean Lahoud, Mariette Awad, Fahad Shahbaz Khan, Salman Khan, Rao Muhammad Anwer, Hisham Cholakkal</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Long-form multimodal video understanding requires integrating vision, speech, and ambient audio with coherent long-range reasoning. Existing benchmarks emphasize either temporal length or multimodal richness, but rarely both and while some incorporate open-ended questions and advanced metrics, they mostly rely on single-score accuracy, obscuring failure modes. We introduce LongShOTBench, a diagnostic benchmark with open-ended, intent-driven questions; single- and multi-turn dialogues; and tasks requiring multimodal reasoning and agentic tool use across video, audio, and speech. Each item includes a reference answer and graded rubric for interpretable, and traceable evaluation. LongShOTBench is produced via a scalable, human-validated pipeline to ensure coverage and reproducibility. All samples in our LongShOTBench are human-verified and corrected. Furthermore, we present LongShOTAgent, an agentic system that analyzes long videos via preprocessing, search, and iterative refinement. On LongShOTBench, state-of-the-art MLLMs show large gaps: Gemini-2.5-Flash achieves 52.95%, open-source models remain below 30%, and LongShOTAgent attains 44.66%. These results underscore the difficulty of real-world long-form video understanding. LongShOTBench provides a practical, reproducible foundation for evaluating and improving MLLMs. All resources are available on GitHub: https://github.com/mbzuai-oryx/longshot.</p> + https://arxiv.org/abs/2512.16978 Thu, 18 Dec 2025 18:59:27 +0000 - Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation - https://arxiv.org/abs/2512.16913 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Lin, Meixi Song, Dizhe Zhang, Wenxuan Lu, Haodong Li, Bo Du, Ming-Hsuan Yang, Truong Nguyen, Lu Qi</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> In this work, we present a panoramic metric depth foundation model that generalizes across diverse scene distances. We explore a data-in-the-loop paradigm from the view of both data construction and framework design. We collect a large-scale dataset by combining public datasets, high-quality synthetic data from our UE5 simulator and text-to-image models, and real panoramic images from the web. To reduce domain gaps between indoor/outdoor and synthetic/real data, we introduce a three-stage pseudo-label curation pipeline to generate reliable ground truth for unlabeled images. For the model, we adopt DINOv3-Large as the backbone for its strong pre-trained generalization, and introduce a plug-and-play range mask head, sharpness-centric optimization, and geometry-centric optimization to improve robustness to varying distances and enforce geometric consistency across views. Experiments on multiple benchmarks (e.g., Stanford2D3D, Matterport3D, and Deep360) demonstrate strong performance and zero-shot generalization, with particularly robust and stable metric predictions in diverse real-world scenes. The project page can be found at: https://insta360-research-team.github.io/DAP_website/ {https://insta360-research-team.github.io/DAP\_website/}</p> - https://arxiv.org/abs/2512.16913 - Thu, 18 Dec 2025 18:59:29 +0000 + Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs + https://arxiv.org/abs/2512.17008 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junbo Li, Peng Zhou, Rui Meng, Meet P. Vadera, Lihong Li, Yang Li</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn tasks exposes notable limitations, particularly in scenarios requiring long-horizon reasoning. To address these challenges, we investigate more stable and effective advantage estimation strategies, especially for multi-turn settings. We first explore Proximal Policy Optimization (PPO) as an alternative and find it to be more robust than GRPO. To further enhance PPO in multi-turn scenarios, we introduce turn-PPO, a variant that operates on a turn-level MDP formulation, as opposed to the commonly used token-level MDP. Our results on the WebShop and Sokoban datasets demonstrate the effectiveness of turn-PPO, both with and without long reasoning components.</p> + https://arxiv.org/abs/2512.17008 + Thu, 18 Dec 2025 19:07:25 +0000 - StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors - https://arxiv.org/abs/2512.16915 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16915.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guibao Shen, Yihua Du, Wenhang Ge, Jing He, Chirui Chang, Donghao Zhou, Zhen Yang, Luozhou Wang, Xin Tao, Ying-Cong Chen</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> The rapid growth of stereoscopic displays, including VR headsets and 3D cinemas, has led to increasing demand for high-quality stereo video content. However, producing 3D videos remains costly and complex, while automatic Monocular-to-Stereo conversion is hindered by the limitations of the multi-stage ``Depth-Warp-Inpaint'' (DWI) pipeline. This paradigm suffers from error propagation, depth ambiguity, and format inconsistency between parallel and converged stereo configurations. To address these challenges, we introduce UniStereo, the first large-scale unified dataset for stereo video conversion, covering both stereo formats to enable fair benchmarking and robust model training. Building upon this dataset, we propose StereoPilot, an efficient feed-forward model that directly synthesizes the target view without relying on explicit depth maps or iterative diffusion sampling. Equipped with a learnable domain switcher and a cycle consistency loss, StereoPilot adapts seamlessly to different stereo formats and achieves improved consistency. Extensive experiments demonstrate that StereoPilot significantly outperforms state-of-the-art methods in both visual fidelity and computational efficiency. Project page: https://hit-perfect.github.io/StereoPilot/.</p> - https://arxiv.org/abs/2512.16915 - Thu, 18 Dec 2025 18:59:50 +0000 + 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation + https://arxiv.org/abs/2512.17012 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chiao-An Yang, Ryo Hachiuma, Sifei Liu, Subhashree Radhakrishnan, Raymond A. Yeh, Yu-Chiang Frank Wang, Min-Hung Chen</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Despite advances in Multimodal LLMs (MLLMs), their ability to reason over 3D structures and temporal dynamics remains limited, constrained by weak 4D perception and temporal understanding. Existing 3D and 4D Video Question Answering (VQA) benchmarks also emphasize static scenes and lack region-level prompting. We tackle these issues by introducing: (a) 4D-RGPT, a specialized MLLM designed to capture 4D representations from video inputs with enhanced temporal perception; (b) Perceptual 4D Distillation (P4D), a training framework that transfers 4D representations from a frozen expert model into 4D-RGPT for comprehensive 4D perception; and (c) R4D-Bench, a benchmark for depth-aware dynamic scenes with region-level prompting, built via a hybrid automated and human-verified pipeline. Our 4D-RGPT achieves notable improvements on both existing 4D VQA benchmarks and the proposed R4D-Bench benchmark.</p> + https://arxiv.org/abs/2512.17012 + Thu, 18 Dec 2025 19:13:44 +0000 - AdaTooler-V: Adaptive Tool-Use for Images and Videos - https://arxiv.org/abs/2512.16918 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16918.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang, Xiangyu Yue</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind tool-use reasoning patterns, invoking vision tools even when they are unnecessary, which significantly increases inference overhead and degrades model performance. To this end, we propose AdaTooler-V, an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools. First, we introduce AT-GRPO, a reinforcement learning algorithm that adaptively adjusts reward scales based on the Tool Benefit Score of each sample, encouraging the model to invoke tools only when they provide genuine improvements. Moreover, we construct two datasets to support training: AdaTooler-V-CoT-100k for SFT cold start and AdaTooler-V-300k for RL with verifiable rewards across single-image, multi-image, and video data. Experiments across twelve benchmarks demonstrate the strong reasoning capability of AdaTooler-V, outperforming existing methods in diverse visual reasoning tasks. Notably, AdaTooler-V-7B achieves an accuracy of 89.8\% on the high-resolution benchmark V*, surpassing the commercial proprietary model GPT-4o and Gemini 1.5 Pro. All code, models, and data are released.</p> - https://arxiv.org/abs/2512.16918 - Thu, 18 Dec 2025 18:59:55 +0000 + Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience + https://arxiv.org/abs/2512.17260 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17260.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangjie Chen, Wenxiang Chen, Jiacheng Du, Jinyi Hu, Zhicheng Jiang, Allan Jie, Xiaoran Jin, Xing Jin, Chenggang Li, Wenlei Shi, Zhihong Wang, Mingxuan Wang, Chenrui Wei, Shufa Wei, Huajian Xin, Fan Yang, Weihao Gao, Zheng Yuan, Tianyang Zhan, Zeyu Zheng, Tianxi Zhou, Thomas Hanwen Zhu</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Large language models have recently made significant progress to generate rigorous mathematical proofs. In contrast, utilizing LLMs for theorem proving in formal languages (such as Lean) remains challenging and computationally expensive, particularly when addressing problems at the undergraduate level and beyond. In this work, we present Seed-Prover 1.5, a formal theorem-proving model trained via large-scale agentic reinforcement learning, alongside an efficient test-time scaling (TTS) workflow. Through extensive interactions with Lean and other tools, the model continuously accumulates experience during the RL process, substantially enhancing the capability and efficiency of formal theorem proving. Furthermore, leveraging recent advancements in natural language proving, our TTS workflow efficiently bridges the gap between natural and formal languages. Compared to state-of-the-art methods, Seed-Prover 1.5 achieves superior performance with a smaller compute budget. It solves 88\% of PutnamBench (undergraduate-level), 80\% of Fate-H (graduate-level), and 33\% of Fate-X (PhD-level) problems. Notably, using our system, we solved 11 out of 12 problems from Putnam 2025 within 9 hours. Our findings suggest that scaling learning from experience, driven by high-quality formal feedback, holds immense potential for the future of formal mathematical reasoning.</p> + https://arxiv.org/abs/2512.17260 + Fri, 19 Dec 2025 06:19:55 +0000 - Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification - https://arxiv.org/abs/2512.16921 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16921.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihao Liu, Chengzhi Mao, Yaojie Liu, Alan Yuille, Wen-Sheng Chu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps across models. To address this, we introduce AuditDM, an automated framework that actively discovers and rectifies MLLM failure modes by auditing their divergence. AuditDM fine-tunes an MLLM as an auditor via reinforcement learning to generate challenging questions and counterfactual images that maximize disagreement among target models. Once trained, the auditor uncovers diverse, interpretable exemplars that reveal model weaknesses and serve as annotation-free data for rectification. When applied to SoTA models like Gemma-3 and PaliGemma-2, AuditDM discovers more than 20 distinct failure types. Fine-tuning on these discoveries consistently improves all models across 16 benchmarks, and enables a 3B model to surpass its 28B counterpart. Our results suggest that as data scaling hits diminishing returns, targeted model auditing offers an effective path to model diagnosis and improvement.</p> - https://arxiv.org/abs/2512.16921 - Thu, 18 Dec 2025 18:59:57 +0000 + Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers + https://arxiv.org/abs/2512.17351 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17351.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyuan Allen-Zhu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Understanding architectural differences in language models is challenging, especially at academic-scale pretraining (e.g., 1.3B parameters, 100B tokens), where results are often dominated by noise and randomness. To overcome this, we introduce controlled synthetic pretraining tasks that isolate and evaluate core model capabilities. Within this framework, we discover CANON LAYERS: lightweight architectural components -- named after the musical term "canon" -- that promote horizontal information flow across neighboring tokens. Canon layers compute weighted sums of nearby token representations and integrate seamlessly into Transformers, linear attention, state-space models, or any sequence architecture. We present 12 key results. This includes how Canon layers enhance reasoning depth (e.g., by 2times), reasoning breadth, knowledge manipulation, etc. They lift weak architectures like NoPE to match RoPE, and linear attention to rival SOTA linear models like Mamba2/GDN -- validated both through synthetic tasks and real-world academic-scale pretraining. This synthetic playground offers an economical, principled path to isolate core model capabilities often obscured at academic scales. Equipped with infinite high-quality data, it may even PREDICT how future architectures will behave as training pipelines improve -- e.g., through better data curation or RL-based post-training -- unlocking deeper reasoning and hierarchical inference.</p> + https://arxiv.org/abs/2512.17351 + Fri, 19 Dec 2025 08:47:28 +0000 - EasyV2V: A High-quality Instruction-based Video Editing Framework - https://arxiv.org/abs/2512.16920 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16920.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinjie Mai, Chaoyang Wang, Guocheng Gordon Qian, Willi Menapace, Sergey Tulyakov, Bernard Ghanem, Peter Wonka, Ashkan Mirzaei</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce EasyV2V, a simple and effective framework for instruction-based video editing. On the data side, we compose existing experts with fast inverses to build diverse video pairs, lift image edit pairs into videos via single-frame supervision and pseudo pairs with shared affine motion, mine dense-captioned clips for video pairs, and add transition supervision to teach how edits unfold. On the model side, we observe that pretrained text-to-video models possess editing capability, motivating a simplified design. Simple sequence concatenation for conditioning with light LoRA fine-tuning suffices to train a strong model. For control, we unify spatiotemporal control via a single mask mechanism and support optional reference images. Overall, EasyV2V works with flexible inputs, e.g., video+text, video+mask+text, video+mask+reference+text, and achieves state-of-the-art video editing results, surpassing concurrent and commercial systems. Project page: https://snap-research.github.io/easyv2v/</p> - https://arxiv.org/abs/2512.16920 - Thu, 18 Dec 2025 18:59:57 +0000 + SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories + https://arxiv.org/abs/2512.17419 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lilin Wang, Lucas Ramalho, Alan Celestino, Phuc Anthony Pham, Yu Liu, Umang Kumar Sinha, Andres Portillo, Onassis Osunwa, Gabriel Maduekwe</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Benchmarks like SWE-bench have standardized the evaluation of Large Language Models (LLMs) on repository-level software engineering tasks. However, these efforts remain limited by manual curation, static datasets, and a focus on Python-based bug fixes. We introduce SWE-Bench++, an automated framework that generates repository-level coding tasks from open-source GitHub projects. Unlike synthetic approaches, our pipeline harvests live pull requests to cover both bug fixes and feature requests across 11 languages. SWE-Bench++ turns GitHub pull requests (PRs) into reproducible, execution-based tasks via four stages: programmatic sourcing, environment synthesis, test oracle extraction, and quality assurance. A final hint-guided trajectory synthesis step converts instances that strong models fail on into training trajectories. Our initial benchmark consists of 11,133 instances from 3,971 repositories across 11 languages. On a subset of 1,782 instances of this benchmark, today's strongest models perform as follows: claude-sonnet-4.5 achieves 36.20% pass@10, gpt-5-2025-08-07 34.57%, gemini/gemini-2.5-pro 24.92%, and gpt-4o 16.89%. We further demonstrate the utility of our dataset by showing that fine-tuning on SWE-Bench++ instances yields measurable improvements on the SWE-bench Multilingual benchmark. SWE-Bench++ provides a scalable, multilingual benchmark for evaluating and improving repository-level code generation.</p> + https://arxiv.org/abs/2512.17419 + Fri, 19 Dec 2025 10:16:51 +0000 - Next-Embedding Prediction Makes Strong Vision Learners - https://arxiv.org/abs/2512.16922 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16922.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sihan Xu, Ziqiao Ma, Wenhao Chai, Xuweiyi Chen, Weiyang Jin, Joyce Chai, Saining Xie, Stella X. Yu</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use, we train them to generate embeddings to perform predictive tasks directly. This work explores such a shift from learning representations to learning models. Specifically, models learn to predict future patch embeddings conditioned on past ones, using causal masking and stop gradient, which we refer to as Next-Embedding Predictive Autoregression (NEPA). We demonstrate that a simple Transformer pretrained on ImageNet-1k with next embedding prediction as its sole learning objective is effective - no pixel reconstruction, discrete tokens, contrastive loss, or task-specific heads. This formulation retains architectural simplicity and scalability, without requiring additional design complexity. NEPA achieves strong results across tasks, attaining 83.8% and 85.3% top-1 accuracy on ImageNet-1K with ViT-B and ViT-L backbones after fine-tuning, and transferring effectively to semantic segmentation on ADE20K. We believe generative pretraining from embeddings provides a simple, scalable, and potentially modality-agnostic alternative to visual self-supervised learning.</p> - https://arxiv.org/abs/2512.16922 - Thu, 18 Dec 2025 18:59:58 +0000 + 3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework + https://arxiv.org/abs/2512.17459 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17459.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tobias Sautter, Jan-Niklas Dihlmann, Hendrik P. A. Lensch</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in 3D scene generation produce visually appealing output, but current representations hinder artists' workflows that require modifiable 3D textured mesh scenes for visual effects and game development. Despite significant advances, current textured mesh scene reconstruction methods are far from artist ready, suffering from incorrect object decomposition, inaccurate spatial relationships, and missing backgrounds. We present 3D-RE-GEN, a compositional framework that reconstructs a single image into textured 3D objects and a background. We show that combining state of the art models from specific domains achieves state of the art scene reconstruction performance, addressing artists' requirements. Our reconstruction pipeline integrates models for asset detection, reconstruction, and placement, pushing certain models beyond their originally intended domains. Obtaining occluded objects is treated as an image editing task with generative models to infer and reconstruct with scene level reasoning under consistent lighting and geometry. Unlike current methods, 3D-RE-GEN generates a comprehensive background that spatially constrains objects during optimization and provides a foundation for realistic lighting and simulation tasks in visual effects and games. To obtain physically realistic layouts, we employ a novel 4-DoF differentiable optimization that aligns reconstructed objects with the estimated ground plane. 3D-RE-GEN~achieves state of the art performance in single image 3D scene reconstruction, producing coherent, modifiable scenes through compositional generation guided by precise camera recovery and spatial optimization.</p> + https://arxiv.org/abs/2512.17459 + Fri, 19 Dec 2025 11:20:52 +0000 - The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text - https://arxiv.org/abs/2512.16924 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16924.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanlin Wang, Hao Ouyang, Qiuyu Wang, Yue Yu, Yihao Meng, Wen Wang, Ka Leong Cheng, Shuailei Ma, Qingyan Bai, Yixuan Li, Cheng Chen, Yanhong Zeng, Xing Zhu, Yujun Shen, Qifeng Chen</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We present WorldCanvas, a framework for promptable world events that enables rich, user-directed simulation by combining text, trajectories, and reference images. Unlike text-only approaches and existing trajectory-controlled image-to-video methods, our multimodal approach combines trajectories -- encoding motion, timing, and visibility -- with natural language for semantic intent and reference images for visual grounding of object identity, enabling the generation of coherent, controllable events that include multi-agent interactions, object entry/exit, reference-guided appearance and counterintuitive events. The resulting videos demonstrate not only temporal coherence but also emergent consistency, preserving object identity and scene despite temporary disappearance. By supporting expressive world events generation, WorldCanvas advances world models from passive predictors to interactive, user-shaped simulators. Our project page is available at: https://worldcanvas.github.io/.</p> - https://arxiv.org/abs/2512.16924 - Thu, 18 Dec 2025 18:59:59 +0000 + GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation + https://arxiv.org/abs/2512.17495 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17495.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rang Li, Lei Li, Shuhuai Ren, Hao Tian, Shuhao Gu, Shicheng Li, Zihao Yue, Yudong Wang, Wenhan Ma, Zhe Yang, Jingyuan Ma, Zhifang Sui, Fuli Luo</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language models (MLLMs) achieve impressive scores on existing benchmarks, a fundamental question remains: can MLLMs truly ground language in vision with human-like sophistication, or are they merely pattern-matching on simplified datasets? Current benchmarks fail to capture real-world complexity where humans effortlessly navigate ambiguous references and recognize when grounding is impossible. To rigorously assess MLLMs' true capabilities, we introduce GroundingME, a benchmark that systematically challenges models across four critical dimensions: (1) Discriminative, distinguishing highly similar objects, (2) Spatial, understanding complex relational descriptions, (3) Limited, handling occlusions or tiny objects, and (4) Rejection, recognizing ungroundable queries. Through careful curation combining automated generation with human verification, we create 1,005 challenging examples mirroring real-world complexity. Evaluating 25 state-of-the-art MLLMs reveals a profound capability gap: the best model achieves only 45.1% accuracy, while most score 0% on rejection tasks, reflexively hallucinating objects rather than acknowledging their absence, raising critical safety concerns for deployment. We explore two strategies for improvements: (1) test-time scaling selects optimal response by thinking trajectory to improve complex grounding by up to 2.9%, and (2) data-mixture training teaches models to recognize ungroundable queries, boosting rejection accuracy from 0% to 27.9%. GroundingME thus serves as both a diagnostic tool revealing current limitations in MLLMs and a roadmap toward human-level visual grounding.</p> + https://arxiv.org/abs/2512.17495 + Fri, 19 Dec 2025 12:06:25 +0000 - Generative Refocusing: Flexible Defocus Control from a Single Image - https://arxiv.org/abs/2512.16923 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.16923.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chun-Wei Tuan Mu, Jia-Bin Huang, Yu-Lun Liu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Depth-of-field control is essential in photography, but getting the perfect focus often takes several tries or special equipment. Single-image refocusing is still difficult. It involves recovering sharp content and creating realistic bokeh. Current methods have significant drawbacks. They need all-in-focus inputs, depend on synthetic data from simulators, and have limited control over aperture. We introduce Generative Refocusing, a two-step process that uses DeblurNet to recover all-in-focus images from various inputs and BokehNet for creating controllable bokeh. Our main innovation is semi-supervised training. This method combines synthetic paired data with unpaired real bokeh images, using EXIF metadata to capture real optical characteristics beyond what simulators can provide. Our experiments show we achieve top performance in defocus deblurring, bokeh synthesis, and refocusing benchmarks. Additionally, our Generative Refocusing allows text-guided adjustments and custom aperture shapes.</p> - https://arxiv.org/abs/2512.16923 - Thu, 18 Dec 2025 18:59:59 +0000 + Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding + https://arxiv.org/abs/2512.17532 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17532.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Tang, Jianmin Chen, Wei Wei, Xiaogang Xu, Runtao Liu, Xiangyu Wu, Qipeng Xie, Jiafei Wu, Lei Zhang, Qifeng Chen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.</p> + https://arxiv.org/abs/2512.17532 + Fri, 19 Dec 2025 12:56:17 +0000 + + + RadarGen: Automotive Radar Point Cloud Generation from Cameras + https://arxiv.org/abs/2512.17897 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tomer Borreda, Fangqiang Ding, Sanja Fidler, Shengyu Huang, Or Litany</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-latent diffusion to the radar domain by representing radar measurements in bird's-eye-view form that encodes spatial structure together with radar cross section (RCS) and Doppler attributes. A lightweight recovery step reconstructs point clouds from the generated maps. To better align generation with the visual scene, RadarGen incorporates BEV-aligned depth, semantic, and motion cues extracted from pretrained foundation models, which guide the stochastic generation process toward physically plausible radar patterns. Conditioning on images makes the approach broadly compatible, in principle, with existing visual datasets and simulation frameworks, offering a scalable direction for multimodal generative simulation. Evaluations on large-scale driving data show that RadarGen captures characteristic radar measurement distributions and reduces the gap to perception models trained on real data, marking a step toward unified generative simulation across sensing modalities.</p> + https://arxiv.org/abs/2512.17897 + Fri, 19 Dec 2025 18:57:33 +0000 + + + When Reasoning Meets Its Laws + https://arxiv.org/abs/2512.17901 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17901.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyu Zhang, Yifan Sun, Tianang Leng, Jingyan Shen, Liu Ziyin, Paul Pu Liang, Huan Zhang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, leading to suboptimal reasoning capabilities. To theoretically formalize the desired reasoning behaviors, this paper presents the Laws of Reasoning (LoRe), a unified framework that characterizes intrinsic reasoning patterns in LRMs. We first propose compute law with the hypothesis that the reasoning compute should scale linearly with question complexity. Beyond compute, we extend LoRe with a supplementary accuracy law. Since the question complexity is difficult to quantify in practice, we examine these hypotheses by two properties of the laws, monotonicity and compositionality. We therefore introduce LoRe-Bench, a benchmark that systematically measures these two tractable properties for large reasoning models. Evaluation shows that most reasoning models exhibit reasonable monotonicity but lack compositionality. In response, we develop an effective finetuning approach that enforces compute-law compositionality. Extensive empirical studies demonstrate that better compliance with compute laws yields consistently improved reasoning performance on multiple benchmarks, and uncovers synergistic effects across properties and laws. Project page: https://lore-project.github.io/</p> + https://arxiv.org/abs/2512.17901 + Fri, 19 Dec 2025 18:59:11 +0000 + + + Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing + https://arxiv.org/abs/2512.17909 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17909.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shilong Zhang, He Zhang, Zhifei Zhang, Chongjian Ge, Shuchen Xue, Shaoteng Liu, Mengwei Ren, Soo Ye Kim, Yuqian Zhou, Qing Liu, Daniil Pakhomov, Kai Zhang, Zhe Lin, Ping Luo</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents. However, we empirically identify two fundamental obstacles in this paradigm: (1) the discriminative feature space lacks compact regularization, making diffusion models prone to off-manifold latents that lead to inaccurate object structures; and (2) the encoder's inherently weak pixel-level reconstruction hinders the generator from learning accurate fine-grained geometry and texture. In this paper, we propose a systematic framework to adapt understanding-oriented encoder features for generative tasks. We introduce a semantic-pixel reconstruction objective to regularize the latent space, enabling the compression of both semantic information and fine-grained details into a highly compact representation (96 channels with 16x16 spatial downsampling). This design ensures that the latent space remains semantically rich and achieves state-of-the-art image reconstruction, while remaining compact enough for accurate generation. Leveraging this representation, we design a unified Text-to-Image (T2I) and image editing model. Benchmarking against various feature spaces, we demonstrate that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both T2I and editing tasks, validating that representation encoders can be effectively adapted into robust generative components.</p> + https://arxiv.org/abs/2512.17909 + Fri, 19 Dec 2025 18:59:57 +0000