Ziqiao Wang
- CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
- MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering
- Neural-Driven Image Editing
- REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
- Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach