David Koes

Associate Professor, University of Pittsburgh

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation

#2110 · Rishal Aggarwal, Jacky Chen, Nicholas Matthew Boffi, David Koes

Learning likelihoods instead of calculating expensive jacobians on generative ODEs to calculate free energy differences and obtain the Boltzmann distribution.