| Sep 25, 2026 | Our paper Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss is online! A continual learner repeatedly faces three questions: what to learn from, what an update may disrupt, and whether future learning remains effective. We connect all three through the same token-level interaction. |
| May 04, 2026 | Two papers are accepted by ICML 2026: one on training collapse in multi-turn reinforcement learning, and the other on mitigating attention distraction in vision-language models. Many thanks to all my collaborators for their support and contributions! |
| Apr 08, 2026 | Out For-Value is accepted by ACL Main 2026, where we delve into the learning dynamics of SFT and introduce a forward-only data valuation framework that enables scalable and efficient value estimation for both LLMs and VLMs. Code avaliable at github. |