ICML全称为国际机器学习会议（International Conference on Machine Learning）是机器学习与人工智能领域的国际顶级学术会议，该会议是机器学习领域历史最悠久的、规模最大、影响最广的顶级学术会议之一，也是中国计算机学会CCF推荐的A类会议。2026年将于7月6-11日在韩国首尔举行。吉林大学人工智能学院的老师和同学作为主要作者有16篇论文被该会议接收。
论文题目：RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
第一作者：国露（2024级博士生）
通讯作者：龙婷，常毅
论文题目：EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
第一作者：迟浩天
指导教师：陈贺昌，常毅
论文题目：Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation
共同一作：张鉴坤（吉林大学，2024级直博生），Shenglai Zeng（密歇根州立大学）
指导教师：常毅
论文题目：Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning
第一作者：赵家兴（2025级硕士生）
指导教师：宋轩
论文题目：FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects
第一作者：朱星宇（2024级博士生）
指导教师：高一星
论文题目：Trajectory-Aware Spiking DiTs Conversion via Membrane Potential Error-Feedback
主要作者：Haoran Fang, Jinjie Fang, Tianxing Man, Wanli Shi, Xingchen Li
论文题目：Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
共同一作：段志斌，荣国伟
指导教师：郭丹丹
论文题目：Trajectory-Aware Spiking DiTs Conversion via Membrane Potential Error-Feedback
主要作者：Haoran Fang, Jinjie Fang, Tianxing Man, Wanli Shi, Xingchen Li
论文题目：LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
主要作者：Jinjie Fang, Chengxun Jin, Tianxing Man, Yi Chang
论文题目：FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
主要作者：Senmao Li, Kai Wang, Salman Khan, Fahad Shahbaz Khan, Jian Yang, Yaxing Wang
论文题目：Boost the Identity-Preserving Embedding for Consistent Visual Generation
主要作者：Zixun Xia, Shuyu Guo, Boqian Li, Jian Yang, Kai Wang, Yaxing Wang
论文题目：From Retrieval to Translation: Translating Query into Graph-level Clues for Retrieval-Augmented Generation
主要作者：Qichuan Liu, Chenfeng Zheng, Yuxuan Hu, Zerui Chen, Chentao Zhang, Qinggang Zhang, Zhihong Zhang.
论文题目：PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
主要作者：Rufeng Chen, Yue Chang, Xiaqiang Tang, Hechang Chen, Sihong Xie
论文题目：Lookahead-GCG: Improving Multi-Model Gradient-Based Jailbreaking Attacks via Nesterov Momentum
主要作者：Rong Feng, Haohan Zhao, Shiqin Tang, Geng Liu, Song Lai, Meng Wang, Shuxin Zhuang, Yuqi Zha, Changyi Ma, Runsheng Yu
论文题目：Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
主要作者：Song Lai, Haohan Zhao, Rong Feng, Changyi Ma, Wenzhuo Liu, Hongbo Zhao, Xi Lin, Dong Yi, Qingfu Zhang, Hongbin Liu, Gaofeng Meng, Fei Zhu
论文题目：SMAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection
主要作者：Xuelin Zhang, Hong Chen, Yingjie Wang, Tieliang Gong
论文题目：Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
主要作者：Xinzhe Yuan, Xiang Pen
