Daily Paper Cast

🤗 Upvotes: 58 | cs. CV, cs. AI Authors: Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li Title: Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes Arxiv: http://arxiv.org/abs/2610.18356v1 Abstract: City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor s...

🤗 Upvotes: 55 | cs. CL, cs. AI Authors: Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Weiqiang Hang, Luqing Wang, Zejian Wang, Zirui Tu, Jingsheng Mao, Shaobo Hu, Yang Luo, Jiale Guo, Jin Zhang, Yudan Liu, Zhaokai Luo, Ren Huan, Yao Hu, Chengyue Jiang, Wenjie Li, Chuan Mu Title: Vela: User Behavior as Supervision Sparks LLM Intelligence Arxiv: http://arxiv.org/abs/2610.14709v1 Abstract: Large lan...

🤗 Upvotes: 54 | cs. LG Authors: Fanxu Meng, Taosong Fang Title: DoSA: Dots Sparse Attention Arxiv: http://arxiv.org/abs/2610.13990v1 Abstract: Sparse attention visits few keys, yet finding them can still require scoring every key with every indexer head. We introduce DoSA (Dots Sparse Attention), a lossless method for making this computation conditional while preserving exact token selection. Its...

🤗 Upvotes: 48 | cs. RO, cs. AI Authors: Minghao Fu, Tavis Siebert, Eryk Halicki, Randall Balestriero Title: LeWAM: End-to-End World and Action Modeling with JEPAs Arxiv: http://arxiv.org/abs/2610.12818v1 Abstract: Joint-embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically train visual representations and actio...

🤗 Upvotes: 40 | cs. AI Authors: Qi Li, Xinchao Wang Title: Jeva: System One Models from First Principles Arxiv: http://arxiv.org/abs/2610.18773v1 Abstract: System one models enable direct, low-latency decision-making. Yet recent practice of predicting an answer from serialized text does not, by itself, respect the structure of a decision problem. We argue that current designs underemphasize four...

🤗 Upvotes: 36 | cs. LG, cs. CL Authors: Futing Wang, Chenxi Li, Jianhao Yan, Yun Luo, Zhi Wang, Yizhuo Li, Runzhe Zhan, Yu Cheng, Tao Lin Title: TPPO: Tracking-Value PPO For Language Model Reasoning Arxiv: http://arxiv.org/abs/2610.16794v1 Abstract: Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning. While \emph{value e...

🤗 Upvotes: 35 | cs. CV Authors: Yuhan Zhu, Xiangyu Zeng, Qingyi Si, Chenxu Yang, Yifei Li, Luozheng Qin, Junhao Zhou, Dingyu Yao, Jun Zhang, Chuanyu Qin, Zhiqiu Zhang, Yuandong Yang, Yuqi Xu, Tianyu Zhang, Hongcheng Guo, Jiaqi Wang, Nan Duan, Limin Wang Title: VideoJev: System One Model for Video Understanding and Interaction Arxiv: http://arxiv.org/abs/2610.18615v1 Abstract: Visual agents must t...

🤗 Upvotes: 34 | cs. AI, cs. CL, cs. LG Authors: Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu, Bhavana Dalvi Mishra, Yifei Ming, Han Yu, Rujun Han, Chen-Yu Lee, Tomas Pfister Title: Harness^2: Recursive Agent Harnessing for an Open World Arxiv: http://arxiv.org/abs/2610.14224v1 Abstract: LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursiv...

🤗 Upvotes: 33 | cs. CL, cs. AI Authors: Jungwoo Park, Taewhoo Lee, Jaewoo Kang Title: UltraBERT: Beyond the Limit of BERT Pre-Training Arxiv: http://arxiv.org/abs/2610.15028v1 Abstract: Recent bidirectional encoders have been modernized with innovations from causal large language models (LLMs). However, the pretraining recipe itself remains inherited from small-scale conventions, leaving encoders...

🤗 Upvotes: 33 | cs. LG, cs. AI Authors: Maoqi Liu, Junwei He, Bowen Zhang, Feiran Li, Wentao Ma, Rongyi Lin, Shuhan Zhong, Quan Fang Title: Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics Arxiv: http://arxiv.org/abs/2609.38847v1 Abstract: Rubric-based reinforcement learning (Rubric-RL) trains language models where no verifier exists. A judg...

🤗 Upvotes: 107 | cs. CV, cs. AI, cs. LG, cs. RO Authors: Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang, Yi Zou, Kaixuan Wang, Tianxing Chen, Wenxuan Song, Bohan Zhou, Mingleyang Li, Siqiao Huang, Yuqi Ye, Caigao Jiang, Wei Wei, Ruihai Wu, Hang Zhang, Yixiao Ge, Shuchang Zhou, Shilong Liu, Xianming Liu, Ping Luo, Shiyu Huang Title: GroundingPI: A Ground...

🤗 Upvotes: 85 | cs. CL Authors: Shun Zou, Ziyu Ma, Yi Zou, Yong Wang, Lin Chen, Zehui Chen, Guanhua Chen, Xiangxiang Chu, Feng Zhao Title: Scaling Agentic Data for Long-Horizon Terminal Intelligence Arxiv: http://arxiv.org/abs/2610.13166v1 Abstract: Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and t...

🤗 Upvotes: 70 | cs. SE, cs. AI, cs. LG Authors: Jiahao Wang, Hongjin Qian, Yuyang Hu, Jiajun Zhang, Zheng Liu Title: AgentSWE: Can Coding Agents Build the Agent You Actually Want? Arxiv: http://arxiv.org/abs/2610.13361v1 Abstract: As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own workflows...

🤗 Upvotes: 43 | cs. CL Authors: Dianqiao Lei, Kevin Qinghong Lin, Pan Lu, Philip Torr, James Zou Title: Thinking Inertia: LLMs Keep Thinking When Told Not To Arxiv: http://arxiv.org/abs/2610.11765v1 Abstract: Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention. We study LLMs' no-thinking behavior alon...

🤗 Upvotes: 32 | cs. CL, cs. CV Authors: Xiaohan Qin, Xiangdong Zhang, Tuo Dai, Sunan Zou, Huaijin Wu, Yebin Yang, Zhuo Xia, Lin Yao, Yuliang Liu, Junchi Yan Title: Multi-Stream Attention Residuals Arxiv: http://arxiv.org/abs/2610.13630v1 Abstract: Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the...

🤗 Upvotes: 28 | cs. CV Authors: Fuyao Zhang, Xuan Wang, Zherui Li, Jiaming Zhang, Longtao Huang, Wei Yang Bryan Lim Title: Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents Arxiv: http://arxiv.org/abs/2609.33304v1 Abstract: Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to an...

🤗 Upvotes: 96 | cs. CV Authors: Jiawei Chi, Shangchen Miao, Zhiyuan Shi, Kailu Wu, Hanyang Wang, Weiliang Chen, Qiyu Dai, Jinshan Ren, Jun Gao, Mingsheng Long, Yueqi Duan, Jiangran Lyu, Jialong Wu, Fangfu Liu Title: AgentGarten: Code Worlds for Evolving Agents Arxiv: http://arxiv.org/abs/2610.12374v1 Abstract: Interactive virtual worlds allow agents to learn through exploration and interaction. W...

🤗 Upvotes: 95 | cs. AI Authors: Yibo Li, Jinhang Qiu, Zhi Zheng, Qianyun Guo, Jiaying Wu, Shuo Ji, Bryan Hooi Title: Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Arxiv: http://arxiv.org/abs/2610.08215v2 Abstract: Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore i...

🤗 Upvotes: 84 | cs. CL Authors: Tianyu Fu, Tengxuan Liu, Ruoxi Wang, Yixin Dong, Yi Ge, Yichen You, Yu Wang Title: TokenRouter: Efficient Serving System for Token-Level LLM Routing Arxiv: http://arxiv.org/abs/2610.12242v1 Abstract: Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While coarse-grained...

🤗 Upvotes: 71 | cs. CL Authors: Quanyu Long, Xiao Chen, Jianda Chen, Haozhen Zhang, Qisheng Hu, Jianzhu Bao, Wenya Wang Title: From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Arxiv: http://arxiv.org/abs/2610.06100v1 Abstract: Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems...

🤗 Upvotes: 59 | cs. RO, cs. CV Authors: Jinkai Zhang, Jingyi Xu, Yuanhong Yu, Jiarui Guo, Ruizhen Hu, Hujun Bao, Xiaowei Zhou, Sida Peng Title: SuperNav: An Agentic Navigation System for Any Task in Any Scene Arxiv: http://arxiv.org/abs/2610.12126v1 Abstract: General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task ge...

🤗 Upvotes: 43 | cs. CL Authors: Xiaomi LLM-Core Team, Zongming Qiao, Ziyue Hua, Zirui Ou, Zihao Yue, Zihan Jiang, Zhuo Huang, Zhiyang Chen, Zhixian Zheng, Zhipeng Xu, Zhengrui Ma, Yuyang Hu, Yuhang Dong, Yuechen Zhang, Yudong Wang, Yuanxin Liu, Yixin Yang, Yishuo Cai, Yikai Zhao, Yihan Yan, Yifan Zhang, Yifan Song, Xiyu Wei, Xing Zhang, Xin Zhang, Xiaoqian Liu, Xiaodong Ji, Xiangwei Deng, Xueyu G...

🤗 Upvotes: 38 | cs. RO Authors: Minxing Li, Minghao Han, Weizhi Zhao, Hanwen Wang, Xiangshuo Liu, Shuyao Shang, Jingxiang Zhou, Mingchao Sun, Hongyu Pan, Mu Xu, Yu Liu, Lue Fan, Zhaoxiang Zhang Title: In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks Arxiv: http://arxiv.org/abs/2609.38173v2 Abstract: We study robotic in-context learning (ICL), an emerging paradig...

🤗 Upvotes: 36 | cs. CV, cs. AI Authors: Dahyun Chung, Siyoon Jin, Hyunwook Choi, Honggyu An, Junyoung Seo, Hyunsung Kim, Seung Wook Kim, Seungryong Kim Title: Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Arxiv: http://arxiv.org/abs/2610.12299v1 Abstract: Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a si...

🤗 Upvotes: 32 | cs. RO, cs. CV Authors: Junyan Li, Ruizhi Li, Yu Liu, Xiangshuo Liu, Mingchao Sun, Hongyu Pan, Mu Xu, Lue Fan, Zhaoxiang Zhang Title: DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training Arxiv: http://arxiv.org/abs/2610.12468v1 Abstract: We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible vid...