Daily Paper Cast

🤗 Upvotes: 48 | cs. AI, cs. CL, cs. LG Authors: Wenbo Pan, Shujie Liu, Chin-Yew Lin, Jingying Zeng, Xianfeng Tang, Xiangyang Zhou, Yan Lu, Xiaohua Jia Title: Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference Arxiv: http://arxiv.org/abs/2606.05922v2 Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improvi...

🤗 Upvotes: 46 | cs. AI Authors: Pu Ning, Quan Chen, Kun Tao, Xinyu Tang, Tianshu Wang, Qianggang Cao, Xinyu Kong, Zujie Wen, Zhiqiang Zhang, Jun Zhou Title: SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research Arxiv: http://arxiv.org/abs/2606.09730v1 Abstract: Large language models are increasingly expected to handle complex, long-horizon real-world tasks wh...

🤗 Upvotes: 41 | cs. LG, cs. AI Authors: Renjie Mao, Xiangxin Zhou, Lvfang Tao, Yixin Ding, Yu Shi, Yongguang Lin, Yuheng Wu, Honglin Zhu, Qian Qiu, Wenxi Zhu Title: Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning Arxiv: http://arxiv.org/abs/2606.10968v2 Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, e...

🤗 Upvotes: 35 | cs. LG Authors: Bowen Ping, Xiangxin Zhou, Penghui Qi, Minnan Luo, Liefeng Bo, Tianyu Pang Title: Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models Arxiv: http://arxiv.org/abs/2606.11025v1 Abstract: Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and...

🤗 Upvotes: 32 | cs. CV Authors: Wenhao Yan, Fengjia Guo, Zhuoyi Yang, Jie Tang Title: SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning Arxiv: http://arxiv.org/abs/2606.10804v2 Abstract: Controlled character animation requires transferring motion from a driving sequence to a reference character. Prior works heavily rely on intermediate representations, inclu...

🤗 Upvotes: 29 | cs. CV Authors: Paul Hyunbin Cho, Jinhyuk Jang, SeokYoung Lee, Joungbin Lee, Siyoon Jin, Heeseong Shin, Jung Yi, Yunjin Park, Chulmin Park, Seungryong Kim Title: Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization Arxiv: http://arxiv.org/abs/2606.11180v1 Abstract: Diffusion-based lip synchronization models achieve strong visual quality and audio-visual...

🤗 Upvotes: 115 | cs. AI, cs. CL, cs. LG Authors: Yiyou Sun, Xinyang Han, Weichen Zhang, Yuanbo Pang, Tianyu Wang, Yuhan Cao, Yixiao Huang, Chris Duroiu, Haoyun Zhang, Jeffrey Lin, Weishu Zhang, Tyler Zeng, Ying Yan, Bo Liu, Hanson Wen, Mingyang Xu, Xiaoyuan Liu, Zimeng Chen, Weiyan Shi, Amanda Dsouza, Vincent Sunn Chen, Patrick Bryant, Carl Boettiger, Yamini Rangan, Bradley Rothenberg, Kyle Stein...

🤗 Upvotes: 102 | cs. SE, cs. CL Authors: Shaoqiu Zhang, Yuhang Wang, Jialiang Liang, Yuling Shi, Wenhao Zeng, Maoquan Wang, Shilin He, Ningyuan Xu, Siyu Ye, Kai Cai, Xiaodong Gu Title: SWE-Explore: Benchmarking How Coding Agents Explore Repositories Arxiv: http://arxiv.org/abs/2606.07297v1 Abstract: Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities...

🤗 Upvotes: 59 | cs. LG, cs. AI Authors: Zhennan Shen, Yanshu Li, Qingyu Yin, Chak Tou Leong, Zhilin Wang, Yanxu Chen, Rongduo Han, Sunbowen Lee, Yi R. Fung Title: On the Geometry of On-Policy Distillation Arxiv: http://arxiv.org/abs/2606.07082v1 Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood...

🤗 Upvotes: 52 | cs. CL, cs. AI Authors: Aofan Yu, Chenyu Zhou, Tianyi Xu, Zihan Guo, Rong Shan, Zhihui Fu, Jun Wang, Weiwen Liu, Yong Yu, Weinan Zhang, Jianghao Lin Title: LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents Arxiv: http://arxiv.org/abs/2606.06087v1 Abstract: Agent systems increasingly use textual skills to encode reusable task procedures, but inje...

🤗 Upvotes: 49 | cs. CV Authors: Weijie Wang, Haoyu Zhao, Yifan Yang, Feng Chen, Zeyu Zhang, Yefei He, Zicheng Duan, Donny Y. Chen, Yuqing Yang, Bohan Zhuang Title: Latent Spatial Memory for Video World Models Arxiv: http://arxiv.org/abs/2606.09828v1 Abstract: Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed i...

🤗 Upvotes: 46 | cs. LG, cs. AI Authors: Yan Wang, Qifan Zhang, Jiachen Yu, Tian Liang, Dongyang Ma, Xiang Hu, Zibo Lin, Chunyang Li, Zhichao Wang, Miao Peng, Nuo Chen, Jia Li, Yujiu Yang, Haitao Mi, Dong Yu Title: FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention Arxiv: http://arxiv.org/abs/2606.09079v2 Abstract: Conventional LLMs keep the full KV cache lo...

🤗 Upvotes: 44 | cs. CV, cs. AI Authors: Jiangtao Wu, Jiaming Wang, Yiwen He, Yuanxing Zhang, Shihao Li, Dunyuan Liu, Xuedong Zhao, Jialu Chen, Zekun Moore Wang, Jiaheng Liu Title: CoVEBench: Can Video Editing Models Handle Complex Instructions? Arxiv: http://arxiv.org/abs/2606.08415v1 Abstract: While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object i...

🤗 Upvotes: 37 | cs. AI, cs. CL Authors: Hongcheng Gao, Hailong Qu, Jingyi Tang, Jiahao Wang, Zihao Huang, Hengkang Qiao, Shihong Huang, Junming Yang, Yi Li, Hongyixuan Yuan, Wenjie Li, Bohan Zeng, Wenbo Li, Bo Wang, Jianhui Liu, Olive Huang, Haoyang Huang, Wentao Zhang, Guoqing Huang, Nan Duan, Yinpeng Dong Title: SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Re...

🤗 Upvotes: 31 | cs. CL, cs. AI Authors: Woojung Song, Dongmin Choi, Yoonah Park, Jongwook Han, Eun-Ju Lee, Yohan Jo Title: Human Psychometric Questionnaires Mischaracterize LLM Behavior Arxiv: http://arxiv.org/abs/2509.10078v4 Abstract: We examine whether human psychometric questionnaires can serve as reliable tools for characterizing and predicting LLM behavior in everyday user interactions. We...

🤗 Upvotes: 29 | cs. CV, cs. GR, cs. LG Authors: Wayne King, Zeyue Xue, Yuxuan Bian, Jie Huang, Haoran Li, Yaowei Li, Yaofeng Su, Yuming Li, Haoyu Wang, Shiyi Zhang, Songchun Zhang, Yuwei Niu, Sihan Xu, Junhao Zhuang, Haoyang Huang, Nan Duan Title: Echo-Memory: A Controlled Study of Memory in Action World Models Arxiv: http://arxiv.org/abs/2606.09803v1 Abstract: We present \textbf{Echo-Memory}, a...

🤗 Upvotes: 42 | cs. CV Authors: Yuval Golbari, Navve Wasserman, Matias Cosarinsky, Roman Beliy, Aude Oliva, Antonio Torralba, Michal Irani, Tamar Rott Shaham Title: From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain Arxiv: http://arxiv.org/abs/2605.23895v1 Abstract: Identifying which brain regions represent a visual concept in the human brain is a central...

🤗 Upvotes: 33 | cs. RO, cs. AI, cs. CV Authors: Zekun Qi, Xuchuan Chen, Dairu Liu, Chenghuai Lin, Yunrui Lian, Sikai Liang, Zhikai Zhang, Yu Guan, Jilong Wang, Wenyao Zhang, Xinqiang Yu, He Wang, Li Yi Title: Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking Arxiv: http://arxiv.org/abs/2606.03985v1 Abstract: We introduce Humanoid-GPT, a GPT-style Transformer with causal atten...

🤗 Upvotes: 33 | cs. LG, cs. CL Authors: Xingrun Xing, Haoqing Wang, Boyan Gao, Ziheng Li, Yehui Tang Title: Trust Region On-Policy Distillation Arxiv: http://arxiv.org/abs/2606.01249v2 Abstract: On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent learning, multi-task enhancement, and model compressio...

🤗 Upvotes: 27 | cs. LG Authors: Lorenz K. Muller, Philippe Bich, Chiara Boretti, Hyun-Min Chang, Jiawei Zhuang, Lukas Cavigelli Title: KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Arxiv: http://arxiv.org/abs/2606.03458v1 Abstract: Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-...

🤗 Upvotes: 73 | cs. AI, cs. CL, cs. LG Authors: Tianyi Zhou, Dongrui Liu, Leitao Yuan, Jing Shao, Xia Hu Title: COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Arxiv: http://arxiv.org/abs/2605.31264v1 Abstract: LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and inter...

🤗 Upvotes: 44 | cs. CV Authors: Yuqing Wang, Zhijie Lin, Ceyuan Yang, Yang Zhao, Fei Xiao, Hao He, Qi Zhao, Zihan Ding, Fuyun Wang, Shuai Wang, Youliang Zhang, Haoqi Fan, Xihui Liu Title: Representation Forcing for Bottleneck-Free Unified Multimodal Models Arxiv: http://arxiv.org/abs/2605.31604v1 Abstract: Unified multimodal models (UMMs) aim to handle perception and generation in a single model....

🤗 Upvotes: 35 | cs. CL Authors: Marko Kojic, Ivan Bondyrev, Aral de Moor, Joseph Shtok, Petr Borovlev, Kseniia Lysaniuk, Madeeswaran Kannan, Ivan Dolgov, Nikita Pavlichenko Title: Mellum2 Technical Report Arxiv: http://arxiv.org/abs/2605.31268v1 Abstract: We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a...

🤗 Upvotes: 33 | cs. CV Authors: Ruiqi Wang, Qimin Chen, Daniel Ritchie, Angel X. Chang, Manolis Savva, Kai Wang, Hao Zhang Title: Function2Scene: 3D Indoor Scene Layout from Functional Specifications Arxiv: http://arxiv.org/abs/2605.30819v1 Abstract: Most text-driven 3D indoor scene synthesis methods generate rooms from object-centric prompts, asking what furniture should be placed rather than ho...

🤗 Upvotes: 31 | cs. CV Authors: Xiangtao Kong, Jixin Zhao, Lingchen Sun, Rongyuan Wu, Lei Zhang Title: GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration Arxiv: http://arxiv.org/abs/2605.31039v1 Abstract: Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real...