Baoxiang Wang

7

Papers

16

Total Citations

Papers (7)

Learning to Communicate Through Implicit Communication Channels

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling

Last-iterate Convergence in Regularized Graphon Mean Field Game

The adaptive complexity of parallelized log-concave sampling

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning

NeurIPS 2025arXiv

Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions

Relative Policy-Transition Optimization for Fast Policy Transfer