highlighted work
Recent projects and highlighted work from the lab.
Here are a few recent projects that reflect our current directions and collaborations.
Constraint-Aware Diffusion for Scientific Applications
Teaching diffusion models to obey physics, geometry, and safety constraints — without retraining.
Learn more
Constrained Discrete Diffusion for Language, Chemistry, and Code
Enforcing hard constraints on tokens, molecules, and programs — training-free, inside the denoising loop.
Learn more
Differential Privacy in Artificial Intelligence Book
The most comprehensive and up-to-date resource on differential privacy for AI.
Learn more
Massively Speeding up LLM inference with Speculative Diffusion Decoding
Faster LLM inference with discrete diffusion drafting and alignment.
Learn more