arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of California, Berkeley(加州大学伯克利分校)

2025-11-18 至 2025-11-18 共收录 11
2511.13714 2025-11-18 cs.CV cs.AI cs.LG

UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity

Junwei Yu, Trevor Darrell, XuDong Wang

机构 * UC Berkeley(加州大学伯克利分校)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13016 2025-11-18 cs.LG

The Good, The Bad, and The Hybrid: A Reward Structure Showdown in Reasoning Models Training

Subramanyam Sahoo

机构 * Berkeley AI Safety Initiative (BASIS) UC Berkeley(伯克利人工智能安全计划(BASIS)加州大学伯克利分校)

Comments Paper accepted to the 2nd Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET 2025) at NeurIPS; the paper consists of 14 pages (including the appendix) and contains 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12448 2025-11-18 cs.CR cs.AI

SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing

Aidan Wen, Norah A. Alzahrani, Jingzhi Jiang, Andrew Joe, Karen Shieh, Andy Zhang, Basel Alomair, David Wagner

机构 * University of California, Berkeley(加州大学伯克利分校)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01110 2025-11-18 econ.GN cs.AI cs.LG q-fin.EC q-fin.GN

NoLBERT: A No Lookahead(back) Foundational Language Model

Ali Kakhbod, Peiyao Li

机构 * Haas School of Business University of California, Berkeley(哈斯商学院 加州大学伯克利分校)

Journal ref NeurIPS 2025 (GenAI in Finance)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.12659 2025-11-18 cs.CY cs.AI

The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1

Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao, Shreedhar Jangam, Jayanth Srinivasa, Gaowen Liu, Dawn Song, Xin Eric Wang

机构 * UC Santa Cruz(加州大学圣克ruz分校) UC Santa Barbara(加州大学圣芭芭拉分校) UC Berkeley(加州大学伯克利分校) Cisco Research(思科研究)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.16480 2025-11-18 cs.RO cs.LG eess.SP

Dynamic Risk Assessment for Autonomous Vehicles from Spatio-Temporal Probabilistic Occupancy Heatmaps

Han Wang, Yuneil Yeo, Antonio R. Paiva, Jean Utke, Maria Laura Delle Monache

机构 * Department of Civil and Environmental Engineering, University of California, Berkeley, CA, USA(加州大学伯克利分校土木与环境工程系) D3 Analytics Innovation, Allstate Insurance Company, Northbrook, IL, USA(Allstate保险公司D3 Analytics创新部门) Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA(加州大学伯克利分校电气工程与计算机科学系)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.12155 2025-11-18 cs.LG cs.AI cs.RO

Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning

Younggyo Seo, Pieter Abbeel

机构 * UC Berkeley(伯克利大学)

Comments 18 Pages. Website: https://younggyo.me/cqn-as/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11840 2025-11-18 cs.RO

LAVQA: A Latency-Aware Visual Question Answering Framework for Shared Autonomy in Self-Driving Vehicles

Shuangyu Xie, Kaiyuan Chen, Wenjing Chen, Chengyuan Qian, Christian Juette, Liu Ren, Dezhen Song, Ken Goldberg

机构 * University of California Berkeley(加州大学伯克利分校) Bosch Research(博世研究) MBZUAI Texas A&M University(德克萨斯农工大学) IEOR UC Berkeley(伯克利大学工业工程与运筹学系)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11592 2025-11-18 cs.LG cs.AI stat.ML

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL

Guojian Zhan, Likun Wang, Pengcheng Wang, Feihong Zhang, Jingliang Duan, Masayoshi Tomizuka, Shengbo Eben Li

机构 * School of Vehicle and Mobility, Tsinghua University(清华大学车辆与移动系统学院) Department of Mechanical Engineering, UC Berkeley(伯克利加州大学机械工程系) School of Mechanical Engineering, University of Science and Technology Beijing(北京科技大学机械工程学院)

Comments 17 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07208 2025-11-18 cs.LG cs.AI

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

Chanakya Ekbote, Marco Bondaschi, Nived Rajaraman, Jason D. Lee, Michael Gastpar, Ashok Vardhan Makkuva, Paul Pu Liang

机构 * Massachusetts Institute of Technology(麻省理工学院) École Polytechnique Fédérale de Lausanne(瑞士联邦理工学院) University of California, Berkeley(加州大学伯克利分校) Princeton University(普林斯顿大学)

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15217 2025-11-18 cs.SD cs.AI cs.LG cs.MM

DRAGON: Distributional Rewards Optimize Diffusion Generative Models

Yatong Bai, Jonah Casebeer, Somayeh Sojoudi, Nicholas J. Bryan

机构 * University of California, Berkeley(加州大学伯克利分校) Adobe Research(Adobe研究)

Comments Accepted to TMLR

详情

展开后加载摘要…

URL PDF HTML 收藏