ICML全称为国际机器学习会议(International Conference on Machine Learning)是机器学习领域的国际顶级(CCF-A类)学术会议。该会议每年举办一次,由国际机器学习协会(International Machine Learning Society)主办。吉林大学人工智能学院的老师和同学作为主要作者有8篇论文被该会议接收。
论文题目:Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification
第一作者:高金彤(2023级博士生)
指导教师:郭丹丹
论文题目:DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
第一作者:郭思源(2023级博士生)
指导教师:陈贺昌,常 毅
论文题目:Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
第一作者:苗睿(2020级硕士生)
指导教师:王 鑫
论文题目:DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching
第一作者:李光赫(三年级本科生)
指导教师:龙 婷
论文题目:In-Context Reinforcement Learning with Hierarchical Chain of Experience
第一作者:黄思理(2021级博士生)
指导教师:陈贺昌,杨 博
论文题目:An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series
第一作者:黄强(2020级博士生)
指导教师:常毅
论文题目:Double Momentum Method for Lower-Level Constrained Bilevel Optimization
主要作者:Wanli Shi, Yi Chang, Bin Gu
论文题目:NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks
主要作者:Haiyan Jiang, Giulia De Masi, Huan Xiong, Bin Gu