Chao Zhang

Convergence Theory of Decentralized Diffusion Models via Pseudo-Non-Markov Analysis

Provably Safe Representation Learning in CMDPs: A Primal-Dual Approach

Optimistic Value Iteration with Representation Learning for Low-Rank POMGs

Incremental Learning of Vision-Language Models via Task Subspace Projection and Dynamic LoRA

Rebalancing Return Coverage for Conditional Sequence Modeling in Offline Reinforcement Learning

Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

LW2G: Learning Whether to Grow for Prompt-based Continual Learning

Gradient-Free Analytical Fisher Information of Diffused Distributions

DC-DPM: A Divide-and-Conquer Approach for Diffusion Reverse Process