Preprint

FALCON: Few-step Accurate Likelihoods for Continuous Flows
Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann …
Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alex Tong
PDF Cite
OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction
Accurately predicting experimentally-realizable 3D molecular crystal structures from their 2D chemical graphs is a long-standing open …
Emily Jin*, Andrei Cristian Nica*, Mikhail Galkin, Jarrid Rector-Brooks, Kin Long Kelvin Lee, Santiago Miret, Frances H. Arnold, Michael Bronstein, Avishek Joey Bose, Alex Tong, Chenghao Liu
PDF Cite Blog
Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction
Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and …
Vincent Pauline, Tobias Höppe, Kirill Neklyudov, Alex Tong, Stefan Bauer, Andrea Dittadi
PDF Cite
Planner Aware Path Learning in Diffusion Language Models Training
Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through flexible and …
Fred Zhangzhi Peng*, Zachary Bezemek*, Jarrid Rector-Brooks, Shuibai Zhang, Anru R. Zhang, Michael Bronstein, Avishek Joey Bose*, Alex Tong*
PDF Cite
Branched Schrödinger Bridge Matching
Predicting the intermediate trajectories between an initial and target distribution is a central problem in generative modeling. …
Sophia Tang, Yinuo Zhang, Alex Tong, Pranam Chatterjee
PDF Cite