FALCON: Few-step Accurate Likelihoods for Continuous Flows

ICLROral2026

Authors: Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong
Affiliation: Mila - Quebec Artificial Intelligence Institute
Venue: ICLR 2026
Track: Oral

TL;DR

Few-step Flow Matching with Accurate Likelihoods for Scalable Boltzmann Generators…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

flow matching

← All ICLR 2026 Oral papers · Browse the whole archive