Less is More: Lean yet Powerful Vision-Language Model for Autonomous Driving
少即是多:一种高效而强大的视觉-语言模型用于自动驾驶
Sheng Yang, Tong Zhan, Guancheng Chen, Yanfeng Lu, Jian Wang
机构
*
School of Data Science, Fudan University Shanghai, China(复旦大学数据科学学院)
;
Institute of Automation, Chinese Academy of Sciences Beijing, China(中国科学院自动化研究所)
Physics-based phenomenological characterization of cross-modal bias in multimodal models
基于物理现象的多模态模型跨模态偏差表征
Hyeongmo Kim, Sohyun Kang, Yerin Choi, Seungyeon Ji, Junhyuk Woo, Hyunsuk Chung, Soyeon Caren Han, Kyungreem Han
机构
*
B rain Science Institute(脑科学研究院)
;
Korea Institute of Science and Technology(韩国科学技术院)
;
Department of Physics and Astronomy(物理与天文学系)
;
Department of Computer Science and Engineering(计算机科学与工程系)
;
University of Science and Technology KIST School(科学技术KIST学院)
专题命中
代码与定理证明
:reasoning(abstract);分类 cs.AI
AI总结
本文提出基于物理现象的多模态模型跨模态偏差表征方法,揭示多模态输入可能强化模态主导性。
CommentsBest Paper Award at BiasinAI track in AAAI2026
Comments144 pages, 7 color images. Submission to First Proof February 2026 (arxiv:2602.05192, https://1stproof.org/), uploaded 20:07 Friday, 13 February 2026 Pacific Time (PT)
Automated Proof Generation for Rust Code via Self-Evolution
通过自我进化实现Rust代码的自动证明生成
Tianyu Chen, Shuai Lu, Shan Lu, Yeyun Gong, Chenyuan Yang, Xuheng Li, Md Rakib Hossain Misu, Hao Yu, Nan Duan, Peng Cheng, Fan Yang, Shuvendu K Lahiri, Tao Xie, Lidong Zhou
机构
*
Peking University(北京大学)
;
Microsoft Research(微软研究院)
;
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
;
Columbia University(哥伦比亚大学)
;
University of California Irvine(加州大学 Irvine 分校)
SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges
SKATE,一种可扩展的锦标赛评估:较弱的LLM通过可验证的挑战区分更强的LLM
Dewi S. W. Gould, Bruno Mlodozeniec, Samuel F. Brown
机构
*
The Alan Turing Institute(阿尔文·图灵研究所)
;
University of Cambridge(剑桥大学)
;
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
;
Independent(独立研究者)
机构
*
Peking University(北京大学)
;
University of Michigan(密歇根大学)
;
Shanghai Jiao Tong University(上海交通大学)
;
Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)
;
Tencent(腾讯)
Evaluating Large Language Models on Solved and Unsolved Problems in Graph Theory: Implications for Computing Education
在图论中解决和未解决的问题上评估大语言模型:对计算教育的启示
Adithya Kulkarni, Mohna Chakraborty, Jay Bagga
机构
*
Department of Computer Science(计算机科学系)
;
Ball State University(巴尔的摩州立大学)
;
School of Artificial Intelligence and Data Science(人工智能与数据科学学院)
;
Jio Institute(乔研究所)
机构
*
Department of Engineering, King's College London, London, UK(伦敦大学金史密斯学院工程系)
;
Intelligent Networked Systems Institute (INSI), Northeastern University, Boston, MA, USA(东北大学智能网络系统研究所)
;
Intelligent Networked Systems Institute (INSI), Northeastern University, London, UK(伦敦大学东北大学智能网络系统研究所)
Neural Theorem Proving for Verification Conditions: A Real-World Benchmark
为验证条件进行神经定理证明:一个现实世界的基准测试
Qiyuan Xu, Xiaokun Luan, Renxi Wang, Joshua Ong Jun Leang, Peixin Wang, Haonan Li, Wenda Li, Conrad Watt
机构
*
Nanyang Technological University(南洋理工大学)
;
Peking University(北京大学)
;
MBZUAI
;
Imperial College London(帝国理工学院)
;
East China Normal University(华东师范大学)
;
University of Edinburgh(爱丁堡大学)
Decompose-and-Formalise: Recursively Verifiable Natural Language Inference
分解与形式化:可递归验证的自然语言推理
Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
机构
*
Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系)
;
School of Computer Science, University of Sheffield(谢菲尔德大学计算机科学学院)
;
Idiap Research Institute(Idiap研究 institute)
;
National Biomarker Centre, CRUK-MI, University of Manchester(曼彻斯特大学国家生物标记中心)