Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning
机构 * UC San Diego(加州大学圣地亚哥分校)
高校专区
机构 * UC San Diego(加州大学圣地亚哥分校)
机构 * New York University(纽约大学) ; UC San Diego(圣地亚哥大学) ; Carnegie Mellon University(卡内基梅隆大学) ; Meta ; MBZUAI(马克斯·普朗克人工智能研究所)
机构 * Department of Cognitive Science University of California, San Diego(认知科学系,加州大学圣地亚哥分校)
Comments Accepted at EMNLP 2025 (camera-ready)
机构 * Department of Civil, Construction, and Environmental Engineering, San Diego State University, San Diego, CA, United States(土木、建设与环境工程系,圣地亚哥州立大学,美国圣地亚哥,加利福尼亚州) ; Department of Electrical and Computer Engineering, University of California, San Diego, San Diego, CA, United States(电气与计算机工程系,加州大学圣地亚哥分校,美国圣地亚哥,加利福尼亚州)
机构 * Department of Civil, Construction, and Environmental Engineering, San Diego State University, San Diego, CA, United States(土木、建设与环境工程系,圣地亚哥州立大学) ; Department of Electrical and Computer Engineering, University of California, San Diego, San Diego, CA, United States(电气与计算机工程系,加州大学圣地亚哥分校) ; Department of Mechanical and Aerospace Engineering, University of California, San Diego, San Diego, CA, United States(机械与航空航天工程系,加州大学圣地亚哥分校) ; Department of Computer Science, San Diego State University, San Diego, CA, United States(计算机科学系,圣地亚哥州立大学)
机构 * School of Computer Science and Technology, Xidian University(西安电子科技大学计算机科学与技术学院) ; School of Artificial Intelligence, Xidian University(西安电子科技大学人工智能学院) ; Department of Mathematics, University of California San Diego(加州大学圣地亚哥分校数学系)
机构 * University of California San Diego(加州大学圣地亚哥分校)
Comments The first three authors contributed equally. This work has been accepted for publication at the Conference on Robot Learning
机构 * The University of New South Wales(新南威尔士大学) ; UC San Diego(圣地亚哥大学) ; Adobe Research(Adobe研究院) ; CSIRO’s Data61(CSIRO数据61研究所) ; Macquarie University(麦考瑞大学)
机构 * Institute for High Energy Physics, Vienna(维也纳高等研究院) ; Lawrence Berkeley National Laboratory(伯克利国家实验室) ; Université Paris-Saclay, CNRS/IN2P3, IJCLab ChaLearn(巴黎-萨克雷大学,CNRS/IN2P3,IJCLab ChaLearn) ; University of Washington, Seattle(华盛顿大学,西雅图) ; University of California, Berkeley(加州大学伯克利分校) ; University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) ; University of California, San Diego(加州大学圣地亚哥分校) ; ChaLearn
Comments FAIR Universe HiggsML Uncertainty Challenge Competition, submitted to NeurIPS 2025, Benchmark and Datasets track
机构 * UC San Diego(加州大学圣地亚哥分校) ; Lambda, Inc(Lambda公司)
Comments Accepted to NeurIPS 2025 Dataset&Benchmark Track
机构 * University of Belgrade(贝尔格莱德大学) ; University of California San Diego(加州大学圣地亚哥分校)
Comments 8 pages, 1 figure
机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) ; University of California San Diego(加州大学圣地亚哥分校)
Comments The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) Findings
机构 * Laboratory for Emerging Intelligence(新兴智能实验室) ; University of California, San Diego(加州大学圣地亚哥分校)
Comments Published at EMNLP 2025 (Main)
机构 * Electrical and Computer Engineering University of California, San Diego(电气与计算机工程大学加州大学圣地亚哥分校) ; Halıcıoğlu Data Science Institute University of California, San Diego(Halıcıoğlu数据科学研究所大学加州大学圣地亚哥分校) ; Department of Cognitive Science, Department of Computer Science and Engineering University of California, San Diego(认知科学系计算机科学与工程系大学加州大学圣地亚哥分校)
机构 * Boston University(波士顿大学) ; University of California, San Diego(加州大学圣地亚哥分校)
Comments Accepted to EMNLP 2025 Findings
机构 * The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)) ; Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳人工智能与机器人研究院) ; University of California, San Diego(加州大学圣地亚哥分校)
机构 * UC San Diego(圣迭戈大学) ; Hillbot
Comments Project Page: https://gen-vla.github.io/
机构 * Carnegie Mellon University(卡内基梅隆大学) ; University of Michigan(密歇根大学) ; University of California, San Diego(加州大学圣地亚哥分校)
Comments 15 pages, 1 figure
机构 * University of California, San Diego(加州大学圣地亚哥分校) ; University of Pennsylvania(宾夕法尼亚大学)
Comments Published in CCN 2025 Proceedings (Talk & Poster), May 14, 2025
机构 * College of Design and Engineering National University of Singapore(设计与工程学院新加坡国立大学) ; Jacobs School of Engineering University of California San Diego(工程学院加州大学圣地亚哥分校) ; Massachusetts General Hospital Harvard University(麻省总医院哈佛大学) ; Faculty of Electrical Engineering, Mathematics and Computer Science Delft University of Technology(电子工程、数学和计算机科学学院代尔夫特技术大学) ; Faculty of Mechanical Engineering Delft University of Technology(机械工程学院代尔夫特技术大学)
机构 * University of California San Diego(加州大学圣地亚哥分校) ; Technical University of Darmstadt(达姆施塔特技术大学)
Comments Full version of CCS 2025 paper
机构 * Northeastern University(东北大学) ; UC San Diego(加州大学圣地亚哥分校) ; University of Massachusetts Amherst(马萨诸塞大学阿姆赫斯特分校)
Comments Camera-ready version for ICWSM 2026. First two authors contributed equally
机构 * Contextual Robotics Institute and the Department of Mechanical and Aerospace Engineering, UC San Diego(情境机器人研究所和机械与航空航天工程系,加州大学圣地亚哥分校) ; U.S. Army Combat Capabilities Development Command, Army Research Laboratory(美国陆军战斗能力发展司令部,陆军研究实验室)
Comments 10 pages, 5 figures
机构 * University of California, San Diego(加州大学圣地亚哥分校) ; Adobe Research(Adobe研究) ; The University of New South Wales(新南威尔士大学) ; CSIRO’s Data61(澳大利亚联邦科学与工业研究组织的数据61)
Comments 9 pages
机构 * University of Toronto(多伦多大学) ; University of California San Diego(加州大学圣地亚哥分校) ; Johns Hopkins University(约翰霍普金斯大学)
机构 * UC San Diego(加州大学圣迭戈分校) ; Adobe Research(Adobe研究)
Comments 10 pages
机构 * MIT(麻省理工学院) ; Harvard(哈佛大学) ; UCSD(加州大学圣地亚哥分校) ; UC Berkeley(加州大学伯克利分校)
机构 * Department of Electrical and Computer Engineering, University of California San Diego(电气与计算机工程系,加州大学圣地亚哥分校) ; Department of Electrical and Systems Engineering, University of Pennsylvania(电气与系统工程系,宾夕法尼亚大学)
机构 * UC San Diego(圣迭戈大学) ; Simon Fraser University(西蒙弗雷泽大学)
机构 * Henan University(河南大学) ; Department of Statistics, LMU Munich(慕尼黑大学统计系) ; Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心) ; CISPA Helmholtz Center for Information Security, Saarbrücken(萨尔布吕肯亥姆霍尔兹信息安全中心) ; University of California, San Diego(加州大学圣地亚哥分校)
Comments Accepted at Findings of the Association for Computational Linguistics: EMNLP 2025