Researcher, Microsoft Research
3 papers at NeurIPS 2025
We propose Hierarchical Diffusion Language Models, which is a discrete diffusion with a general time-varying next semantic scale prediction process for language modeling.
We extend a new RL-based gradient-informed finetuning method to the task of reward finetuning/alignment for 3D native diffusion models.
We propose a value gradient matching formulation for reward finetuning/alignment for flow matching models with the theory of optimal control, and empirically verify our method on the popular text-to-image flow matching model StableDiffusion3
