Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
神经网络的部分融合:集成与权重聚合之间的高效权衡
Fabian Morelli, Stephan Eckstein
机构
*
Department of Mathematics, University of Tübingen, Germany(图宾根大学数学系,德国)
;
Department of Computer Science, University of Tübingen, Germany(图宾根大学计算机科学系,德国)
Understanding Self-Supervised Learning via Latent Distribution Matching
通过潜在分布匹配理解自监督学习
Fabian A Mikulasch, Friedemann Zenke
机构
*
Friedrich Miescher Institute for Biomedical Research, 4056 Basel, Switzerland(弗里德里希·迈斯彻生物医学研究所)
;
Faculty of Science, University of Basel, 4033 Basel, Switzerland(巴塞尔大学科学学院)
Large Language Models Explore by Latent Distilling
通过潜在蒸馏探索大语言模型
Yuanhao Zeng, Ao Lu, Lufei Li, Zheng Zhang, Yexin Li, Kan Ren
机构
*
State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China(人工智能通用基础理论国家重点实验室,BIGAI,北京,中国)
;
School of Information Science and Technology, ShanghaiTech University, Shanghai, China(信息科学与技术学院,上海交通大学,上海,中国)
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
反向思维链生成中的事后合理化测量与缓解
Guangyue Peng, Zongchao Chen, Wen Luo, Yuntao Wen, Wei Li, Ruixiang Feng, Ran Le, Chen Yang, Zhenwei An, Yang Song, Tao Zhang, Houfeng Wang
机构
*
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(信息处理国家重点实验室,计算机科学学院,北京大学)
;
University of Electronic Science and Technology of China(电子科技大学)
;
Nanbeige Lab, BOSS Zhipin(纳贝格实验室,BOSS智联)
机构
*
Guangzhou University(广州大学)
;
Institue of Automation Chinese Academy of Sciences(中国科学院自动化研究所)
;
ByteDance Inc.(字节跳动公司)
;
University of Science and Technology Beijing(北京科技大学)
机构
*
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China(香港中文大学(深圳)数据科学学院)
;
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China(香港中文大学(深圳)科学与工程学院)
;
School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China(香港中文大学(深圳)人工智能学院)
;
COSCO SHIPPING Advanced Technology Institute, Shanghai, China(中远海运技术研究院)
机构
*
School of Information Science/National Key Laboratory of Deep Space Exploration University of Science and Technology of China(中国科学技术大学信息科学学院/深空探测国家实验室)
机构
*
University of Science and Technology of China(中国科学技术大学)
;
SenseTime Research(商汤科技研究院)
;
National University of Singapore(新加坡国立大学)
;
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)
机构
*
The Chinese University of Hong Kong(香港中文大学)
;
Shanghai Jiao Tong University(上海交通大学)
;
Nanyang Technological University(南洋理工大学)
;
Qwen Team, Alibaba Group(阿里巴巴集团Qwen团队)
CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities
CyberGym-E2E:面向AI代理端到端网络安全能力的可扩展真实世界基准
Tianneng Shi, Robin Rheem, Dongwei Jiang, Mona Wang, Francisco De La Riega, Zhun Wang, Jingzhi Jiang, Alexander Cheung, Sean Tai, Jonah Cha, Jianhong Tu, Gabriel Han, Chenguang Wang, Jingxuan He, Wenbo Guo, Dawn Song
Structure-Induced Information for Rerooting Levin Tree Search
结构信息用于重定根莱文树搜索
Jake Tuero, Michael Buro, Laurent Orseau, Levi H. S. Lelis
机构
*
Department of Computing Science, University of Alberta, Edmonton, Canada.
;
Alberta Machine Intelligence Institute (Amii), Edmonton, Canada.
;
Google DeepMind, London, United Kingdom.
Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
基于子模重放的根吸收前缀轨迹平衡用于GFlowNet训练
Xi Wang, Wenbo Lu, Shengjie Wang
机构
*
Courant Institute School of Mathematics, Computing, and Data Science, New York University(纽约大学Courant研究所数学、计算与数据科学学院)
;
Courant Institute School of Mathematics, Computing(纽约大学Courant研究所数学、计算与数据科学学院)
;
Data Science, New York University(纽约大学数据科学学院)
机构
*
School of Artificial Intelligence, Beihang University, Beijing, China(北京航空航天大学人工智能学院)
;
School of Computer Science and Engineering, Beihang University, Beijing, China(北京航空航天大学计算机科学与工程学院)
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
OMAC:一种面向基于大语言模型的多智能体协作的综合优化框架
Shijun Li, Hilaf Hasson, Joydeep Ghosh
机构
*
Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, United States(得克萨斯大学奥斯汀分校电子与计算机工程系)
;
Intuit AI Research, Mountain View, United States(Intuit AI研究)
CommentsWarning: This paper may contain unfiltered and potentially offensive jailbreaking examples. Accepted at the Second Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD) at ICML 2026