ICML, the International Conference on Machine Learning, is a premier international academic conference in machine learning and artificial intelligence. It is one of the field's longest-running, largest and most influential conferences, and is rated a Category A conference by the China Computer Federation (CCF). In 2026, it will be held from July 6 to 11 in Seoul, South Korea. Sixteen papers with faculty and students of the School of Artificial Intelligence, Jilin University as main authors
1. RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
First author: Lu Guo (PhD student, 2024 cohort) Corresponding authors: Ting Long, Yi Chang
2. EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
First author: Haotian Chi Supervising faculty: Hechang Chen, Yi Chang
3. Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation
Co-first authors: Jiankun Zhang (Jilin University, direct-entry PhD student, 2024 cohort), Shenglai Zeng (Michigan State University) Supervising faculty: Yi Chang
4. Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning
First author: Jiaxing Zhao (Master's student, 2025 cohort) Supervising faculty: Xuan Song
5. FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects
First author: Xingyu Zhu (PhD student, 2024 cohort) Supervising faculty: Yixing Gao
6. Trajectory-Aware Spiking DiTs Conversion via Membrane Potential Error-Feedback
Authors: Haoran Fang, Jinjie Fang, Tianxing Man, Wanli Shi, Xingchen Li
7. Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
Co-first authors: Zhibin Duan, Guowei Rong Supervising faculty: Dandan Guo
8. Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
Authors: Xinzhe Yuan, Xiang Pen
9. LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
Authors: Jinjie Fang, Chengxun Jin, Tianxing Man, Yi Chang
10. FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
Authors: Senmao Li, Kai Wang, Salman Khan, Fahad Shahbaz Khan, Jian Yang, Yaxing Wang
11. Boost the Identity-Preserving Embedding for Consistent Visual Generation
Authors: Zixun Xia, Shuyu Guo, Boqian Li, Jian Yang, Kai Wang, Yaxing Wang
12. From Retrieval to Translation: Translating Query into Graph-level Clues for Retrieval-Augmented Generation
Authors: Qichuan Liu, Chenfeng Zheng, Yuxuan Hu, Zerui Chen, Chentao Zhang, Qinggang Zhang, Zhihong Zhang
13. PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
Authors: Rufeng Chen, Yue Chang, Xiaqiang Tang, Hechang Chen, Sihong Xie
14. Lookahead-GCG: Improving Multi-Model Gradient-Based Jailbreaking Attacks via Nesterov Momentum
Authors: Rong Feng, Haohan Zhao, Shiqin Tang, Geng Liu, Song Lai, Meng Wang, Shuxin Zhuang, Yuqi Zha, Changyi Ma, Runsheng Yu
15. Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
Authors: Song Lai, Haohan Zhao, Rong Feng, Changyi Ma, Wenzhuo Liu, Hongbo Zhao, Xi Lin, Dong Yi, Qingfu Zhang, Hongbin Liu, Gaofeng Meng, Fei Zhu
16. SMAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection
Authors: Xuelin Zhang, Hong Chen, Yingjie Wang, Tieliang Gong
