2026 顶会论文
8作者位次 #4/8ICML 2026Poster· Optimization / Everything Else
OptMaster: A DAG-Based Framework for Formulation and Heuristic Discovery in Optimization
Hang Lin · Yuanpeng Gao · Yuzhi Zhang · Kun Yuan · Gang Yan · Siheng Chen · Linfeng Zhang · Weinan E
作者位次 #5/5ICML 2026Poster· Deep Learning / Large Language Models
Grouter: Decoupling Routing from Representation for Accelerated MoE Training
Yuqi Xu · Rizhen Hu · zihan liu · Mou Sun · Kun Yuan
作者位次 #5/5ICML 2026Poster· Deep Learning / Large Language Models
Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization
Rizhen Hu · Yuan Cao · Boao Kong · Mou Sun · Kun Yuan
作者位次 #4/5ICML 2026Poster
Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
Ran Xin · Zeyu Zheng · Yanchen Nie · Kun Yuan · Xia Xiao
作者位次 #4/4ICML 2026Poster· Deep Learning / Attention Mechanisms
DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
Jie Hu · Zixiang Gao · Yutong He · Kun Yuan
作者位次 #4/5ICML 2026Poster· Optimization / Large Scale, Parallel and Distributed
Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
Bing Liu · Boao Kong · Limin Lu · Kun Yuan · Chengcheng Zhao
作者位次 #5/5ICML 2026Poster· Applications / Computer Vision
Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
Yuxi Liu · Yipeng Hu · Zekun Zhang · Kunze Jiang · Kun Yuan
作者位次 #5/6ICML 2026Poster· Deep Learning / Large Language Models
OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
Chenyi Li · Yanchen Nie · Zhenyu Ming · Gong Zhang · Kun Yuan · Zaiwen Wen