Wei Ni

BOLT: Decision‑Aligned Distillation and Budget-Aware Routing for Constrained Multimodal QA on Robots

Bridging Interpretability and Optimization: Provably Attribution-Weighted Actor–Critic in Reproducing-Kernel Hilbert Spaces

Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning

RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control

Sample Efficient Robust Offline Self-Play for Model-based Reinforcement Learning

Provable Causal State Representation under Asynchronous Diffusion Model for POMDPs