Full Professor, GM Lab
4 papers at NeurIPS 2025
A robust watermarking scheme for intellectual property protection in diffusion models.
We presents Reward Dithering, a technique that enhances reinforcement learning in large language models by adding random perturbations to reward signals, improving training efficiency and convergence speed while maintaining performance.
We propose Safe-Sora, the first framework that integrates graphical watermarks directly into the video generation process.
