This is Wei, a researcher at Morgan Stanley. I’m currently focused on sequential sampling for the scaling, guidance and steering of diffusion models, language models, and volatility models.

Feel free to contact me at: firstnamelastname056@gmail.com

• Scholar
• Github
• Twitter
• Thesis

News

Apr, 2025. Invited Talk at Practitioners’ Seminar 2025 at Columbia University.

Jan, 2025. 2 AISTATS on diffusion generative models are accpeted!

Nov, 2024. Invited Talk at Learning Meets Geometry, Graphs, and Networks , NY

Jun, 2024. 1 JCGS is accpeted. Federated HMC can be faster than Federated Langevin dynamics.

Apr, 2024. Variational Schrödinger Diffusion Models is accepted by ICML’24! Schrödinger diffusion is scalable now by linearizing the forward scores. Simulation-free property is all we need for scalability.

Apr, 2024. Reflected Schrödinger Bridge is accepted by UAI’24 as Oral. Reflected Schrödinger has the linear convergence of couplings via entropic optimal transport on bounded domains.

Apr, 2024. 2 ICML, 2 UAI (+1 Oral) and 1 AISTAT are accpeted!

Feb, 2024. Invited Talk at Statistics Colloquium at UConn

Dec, 2023. Participate Transport, Diffusion, and Sampling Workshop at Flatiron Institute.

Nov, 2023. Invited Talk at Financial Mathematics Seminar at FSU

Apr, 2023. One ICML on diffusion Schrodinger bridge with transformers is accepted!

Dec, 2022. The Contour Sampler is implemented in BlackJAX!

Feb, 2022. Invited Talk at Opt and ML Seminar at HKU

Oct, 2021. I have defended my thesis!

Oct, 2020. Invited Talk at ML + X Seminar at Brown University