4 papers · 1 filter
WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps
Abbas Mammadov, Jerry Y. Huang, Justin Lin +5
Reward fine-tuning aims to update a pre-trained flow-based generative model to improve the downstream reward of its generated samples. Existing methods typically formulate this pro…
Exact Posterior Score Estimation for Solving Linear Inverse Problems
Abbas Mammadov, Ozgur Kara, Kaan Oktay +5
Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption. To use this prior to solve a linear inverse problem, one needs to…
Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
Abbas Mammadov, So Takao, Bohan Chen +4
Flow maps enable high-quality image generation in a single forward pass. However, unlike iterative diffusion models, their lack of an explicit sampling trajectory impedes incorpora…
Meta Flow Maps enable scalable reward alignment
Peter Potaptchik, Adhi Saravanan, Abbas Mammadov +3
Controlling generative models is computationally expensive. This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires e…