Going to be attending ICLR in Brazil this week to present our work on Energy-Weighted Flow Matching at the DeLTa workshop. We reformulate flow matching via importance sampling to train CNFs for Boltzmann sampling from energy evaluations.
Happy to connect! π§π·
Pretraining diffusion/flow-matching is simple and scales: noise a clean sample, regress against a closed-form target.
RL post-training can be made just as simple.
Reinforce Adjoint Matching (RAM) matches Flow-GRPO on SD3.5M in 50Γ fewer steps. Highest reward, no reward hacking.
Joint work with @NiclasDern, Sebastian Pfister, @MarcelKollovieh, @ludke_david, and @guennemann. Genuinely grateful for this team π
π https://t.co/MpGerW5ogr
π Mon Apr 27, 10:10β11:00, DeLTa workshop
Going to be attending ICLR in Brazil this week to present our work on Energy-Weighted Flow Matching at the DeLTa workshop. We reformulate flow matching via importance sampling to train CNFs for Boltzmann sampling from energy evaluations.
Happy to connect! π§π·