Daily Paper Cast

🤗 Upvotes: 131 | cs. CV Authors: Yihao Hu, Yitong Lin, Pan Wang, Zhihao Wen, Hang Wang, Yiwen Zhao, Deyuan Liu, Yutong Li, Mingda Wan, Yuchen Mao, Tao Lin Title: ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence Arxiv: http://arxiv.org/abs/2610.34283v1 Abstract: Training a spatial VLM to answer which side an object lies on does not require it to preserve the metr...

🤗 Upvotes: 103 | cs. RO, cs. CV, cs. LG Authors: Hanqing Wang, Zhaotian Cai, Ruichuan An, Bohan Zeng, Tao Zhang, Yilin Chen, Xu Jiang, Kaiquan Chen, Chongyang Wu, Haoran Li, Fan Yang, Mingan Lin, Wentao Zhang, Zenan Zhou, Youzheng Wu Title: PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations Arxiv: http://arxiv.org/abs/2610.37381v1 Abstract: Vision--Language--Action (VLA...

🤗 Upvotes: 89 | cs. CV Authors: Qiaoling Chen, Jiaxiang Cheng, Xueqing Deng, Tiankai Hang, Ji Hou, Jiaqi Li, Yifan Liu, Tao Lu, Junshu Tang, Yu Tang, Yao Teng, Yu Tian, Heng Wang, Weizhi Wang, Xiyao Wang, Xilun Wu, Mingyu Yang, Yangbin Yu, Rui Zhao, Longjun Cao, Linghao Chen, Haoyi Duan, Jiaming Han, Mingji Han, Enhua Jiang, Shunkai Li, Yanzhe Liang, Qinwei Ma, Cong Wang, Lei Wang, Bing Wu, Ke Xi...

🤗 Upvotes: 51 | cs. AI Authors: Junming Zhang, Rubin Wei, Xu Cheng, Hao Sun, Jiarui Wang, Ruoxi Cheng, Xiquan Wang, Peisong Wu, Mingsong Chen, Zhouhan Lin Title: HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory Arxiv: http://arxiv.org/abs/2610.24520v2 Abstract: In long-term interactions with large language model (LLM) agents, users reveal habits through thei...

🤗 Upvotes: 48 | cs. RO, cs. AI, cs. LG Authors: Jiayi Luo, Yang Zhang, Liliang Chen, Nan Wang, Chen Gao, Boxiang Qiu, Zhuoxuan Li, Baorui Peng, Chuankang Li, Yuxiang Yan, Si Liu, Qingyun Sun, Shuicheng Yan, Maoqing Yao, Jianxin Li, Guanghui Ren Title: Rollback: Experience Backtracking in World Models for Policy Improvement Arxiv: http://arxiv.org/abs/2610.36068v1 Abstract: Action-conditioned worl...

🤗 Upvotes: 46 | cs. CV Authors: Jiafu Tang, Yifan Xu, Eric Tang, Junjie Zhao, Shipeng Luo, Te Sun, Haoxuan Hu, Yiyan Ji, Xinlong Chen, Zihao Wang, Yang Shi, Yuanxing Zhang, Pengfei Wan, Jiaheng Liu Title: CodeCap-Bench: Can Code Serve as a Good Video Caption? Arxiv: http://arxiv.org/abs/2610.37341v1 Abstract: Video captioning aims to preserve visual information through compact descriptions, predo...

🤗 Upvotes: 45 | cs. CL Authors: Xuan He, Sining Zhoubian, Ruozhen Yang, Yuhao Wen, Zhineng Wang, Yuyang Hu, Ke Yang, Yuyu Zhang, Ping Nie, Jiawei Han, ChengXiang Zhai Title: Memory Tax: Dissecting the Net Value of Agent Memory Arxiv: http://arxiv.org/abs/2610.34073v1 Abstract: Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw h...

🤗 Upvotes: 42 | cs. RO, cs. AI, cs. CV Authors: Chaehyun Kim, Chi-Pin Huang, Jisoo Kim, Min-Hung Chen, Yu-Chiang Frank Wang, Seungryong Kim, Fu-En Yang Title: ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Arxiv: http://arxiv.org/abs/2610.37666v1 Abstract: Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization rem...

🤗 Upvotes: 32 | cs. AI, cs. LG Authors: Yepeng Liu, Shengmai Chen, Xuandong Zhao, Chengzhi Liu, Dawn Song, Xin Eric Wang, Yuheng Bu Title: Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? Arxiv: http://arxiv.org/abs/2610.32046v1 Abstract: Recent \emph{test-time training} (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform infe...

🤗 Upvotes: 150 | cs. CL Authors: Yihao Hu, Zhihao Wen, Yitong Lin, Siyuan Lu, Pan Wang, Wei Wu, Jiang-Ming Yang, Tao Lin Title: Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents Arxiv: http://arxiv.org/abs/2610.33568v1 Abstract: Successful tool-use trajectories are not necessarily useful supervision. Even successful interactions may underrepresent multi-ste...

🤗 Upvotes: 139 | cs. CV Authors: Chengzhi Liu, Yuxiang Lai, Yuzhe Yang, Yanqing Liu, Jiheng Hou, Yue Cao, Haonan Wang, Ruixi Fan, Lan Wang, Sheng Liu, Songyou Peng, Yale Song, Kevin Qinghong Lin, Xin Eric Wang, Jui-Hsin Lai, Youbao Tang Title: StreamVibe: Proactive Video Agents for Evolving User Intent Arxiv: http://arxiv.org/abs/2610.34662v1 Abstract: Vision-language models are shifting from off...

🤗 Upvotes: 117 | cs. AI Authors: Zhiyong Cao, Hengjie Zhu, Yongxin Wang, Xuchen Li, Jintao Li, Shuxia Liu, Dunqiang Liu, Bo Wang, Kairan Zhang, Cong Lin, JiangDi Yu, Siyuan Liu, Sijia Yao, Yi-Liang Wei, Lingxu Ma, Aijia Wang, Anxin Chen, Zixian Wei, Xiang Ruan, Ruizhi Xu, Ruqian Shi, Baihua Xiao, Sicheng Zhou Title: Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attri...

🤗 Upvotes: 78 | cs. HC, cs. CV Authors: Qinsi Wang, Wei Wen, Chong Zhou, Saksham Suri, Zechun Liu, Lemeng Wu, Hai Helen Li, Yiran Chen, Raghuraman Krishnamoorthi, Qi Qian Title: InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants Arxiv: http://arxiv.org/abs/2610.33966v1 Abstract: People have long dreamed of an assistant that is always there to...

🤗 Upvotes: 65 | cs. MA Authors: Ruhao Liu, Qi Li, Shizun Wang, Xinchao Wang Title: DynaFlow: Learning Free-Form Multi-Agent Orchestration Arxiv: http://arxiv.org/abs/2610.34467v1 Abstract: Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements. We introduce DynaFlow, a framework that integrates free-form executable workf...

🤗 Upvotes: 41 | cs. CV Authors: Lei Cao, Yu Liu, Wenhua Liao, Peng Zhang, Fei Wang, Hao Zhang, Jiajun Le, Daiguo Zhou, Jian Luan, Jiayi Ma Title: WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control Arxiv: http://arxiv.org/abs/2610.33135v1 Abstract: Precise camera control is essential for cinematic character video generation, yet existing methods struggle to foll...

🤗 Upvotes: 31 | cs. SD, cs. AI Authors: Kam Man Wu, Yu Zhang, Pengjun Fang, Mingfei Chen, Weijia Chen, Zeyue Tian, Qifeng Chen Title: Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion Arxiv: http://arxiv.org/abs/2610.34415v1 Abstract: Spatial audio authoring coordinates source decisions with soundfield synthesis. For editing, plans specify what to change a...

🤗 Upvotes: 22 | cs. CL Authors: Hyun Ryu, Jong-Heon Kim, Yiqing Xie, Seungone Kim, Carolyn Rose, Eunho Yang Title: Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL Arxiv: http://arxiv.org/abs/2610.33512v1 Abstract: Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weigh...

🤗 Upvotes: 108 | cs. IR, cs. MM, cs. SE Authors: Xiaomin Yu, Hongliang Chen, Zhe Huang, Shilin Yan, Shao-Rong Su, Xuqiao Ma, Feiyang Wang, Jiayu Chen, Jiwei Fang, Yu Yan, Yini Huang, Chen Chen, Ruoxi Cheng, Yuzhi He, Yuhui Zhang, Xiaoxing Hu, Chen Liu, Jianbo Lin, Yijiang Li, Xiaobin Hu, Menglong Li, Zhuoran Lu, Weishi Wang, Zhongqi Yue, Chengwei Qin Title: Deep Search in Real-World Web Environme...

🤗 Upvotes: 97 | cs. CV Authors: Songlin Yang, Zhe Wang, Xiaotong Zhao, Xi Wang, Ran Zhang, Shuai Li, Taiyi Wu, Songlian Li, Eric Liu, Alan Zhao, Anyi Rao Title: Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation Arxiv: http://arxiv.org/abs/2610.30926v1 Abstract: Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse r...

🤗 Upvotes: 31 | cs. CL Authors: Rubin Wei, Siyuan Sun, Hao Sun, Yuliang Liu, Xiang Shi, Jiarui Wang, Junming Zhang, Zhouhan Lin Title: Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models Arxiv: http://arxiv.org/abs/2610.25100v1 Abstract: Large language models need effective ways to acquire and use external knowledge beyond what they retain from pretraining. Continued pre...

🤗 Upvotes: 25 | cs. CV, cs. LG Authors: Junha Song, Geonmo Gu, Jeongeun Park, Heejeong Nam, Lucas Maes, Byeongho Heo, Dongyoon Han, Sangdoo Yun Title: LaLa-World: Scaling Latent World Models with Natural Language Actions Arxiv: http://arxiv.org/abs/2610.27851v2 Abstract: This paper shows that JEPA-style latent world models (LWMs) can learn across diverse domains and data sources by adopting the l...

🤗 Upvotes: 22 | cs. AI Authors: Ermo Hua, Xiangyu Hong, Baiting Wu, Che Jiang, Haozheng Hou, Yicheng Gu, Hanjing Wang, Qirui Zeng, Ming Zhang, Ning Ding, Qipeng Guo, Youbang Sun, Biqing Qi, Bowen Zhou Title: Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE Arxiv: http://arxiv.org/abs/2610.27598v1 Abstract: As model parameters scale up, sparsely activated Mixture-of...

🤗 Upvotes: 21 | cs. RO, cs. AI Authors: Meng Luo, Zechen Bai, Shanqing Xu, Yanlin Li, Kaixin Li, Mengchen Qian, Weifeng Lu, Ran Zhang, Yingtian Zou, Ziyang Luo, Wei Chen, Hongzhan Lin Title: Toward Recursive Self-Improvement in Physical AI Arxiv: http://arxiv.org/abs/2610.29677v1 Abstract: Recursive self-improvement (RSI) describes a system that improves not only its behavior but also the process...

🤗 Upvotes: 62 | cs. CL Authors: Tianyu Fu, Ruoxi Wang, Zihan Min, Zhongqi Ren, Zhihao Li, Tengxuan Liu, Shengxu Mu, Hanling Zhang, Yu Wang Title: Cache Engineering for Agents Arxiv: http://arxiv.org/abs/2610.28577v1 Abstract: Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV)...

🤗 Upvotes: 56 | cs. AI, cs. CL, cs. LG Authors: Zhaoyang Wang, Qianhui Wu, Haorui Wang, Simon Yu, Baolin Peng, Canwen Xu, Hao Cheng, Wenlin Yao, Boyi Liu, Yite Wang, Jianfeng Gao, Huaxiu Yao Title: Agent World Model in the Wild: Computer-Use Agent Environment Synthesis Arxiv: http://arxiv.org/abs/2610.26828v1 Abstract: Agent learning is shifting from learning from human data toward learning throu...