news

Jun 01, 2026 Two accepted papers: the paper, CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization, has been accepted to ICML 2026 AdaptFM Workshop, and the paper, DCDP: Decoupled Data Consistency via Diffusion Purification for Solving General Inverse Problems, has been accepted to ICCP 2026.
May 28, 2026 I successfully defended my PhD thesis! Special thanks to my advisors Qing Qu and Laura Balzano.
May 07, 2026 Our paper, Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective, won the best paper award at the AISTATS 2026 Workshop for Causality in the Age of AI Scaling!