Shaohui Li

From Observations to Events: Event-Aware World Models for Reinforcement Learning

Multi-dimensional game-theoretic capability evaluation under environmental shifts

On Disentangled Training for Nonlinear Transform in Learned Image Compression

Visual Representation Learning for World Models by Predicting Fine-Grained Motion

GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection