Hancheng Min
I am a Tenure-track Associate Professor at the Institute of Natural Sciences (INS) and the School of Mathematics (SMS), Shanghai Jiao Tong University. My research centers around building mathematical principles that facilitate the interplay between machine learning and dynamical systems. Recently, I am mainly interested in analyzing gradient-based optimization algorithms on overparametrized neural networks from a dynamical system perspective.
Recent Updates
[Oct, 21, 2026] Area Chair for ICLR/AISTATS/ICML 2027.
[Oct, 20, 2026] SJTU 2030 grant: Training Dynamics of Generative Models from a Feature Learning Perspective
[Sep, 25, 2026] Our paper A margin perspective on LoRA: Robustness to catastrophic forgetting and adapter merging (MaLoRA) is accepted to NeurIPS 2026 !
[Aug, 29, 2026] NSFC grant: Convergence Analysis of Muon Optimizer from a Feature Learning Perspective
[Jun, 18, 2026] Our paper Dynamic World Generation Made Efficient is accepted to ECCV 2026 !