Showing 2025Show all
3 papers · 1 filter
cs.LG2025
One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow
Zeyuan Wang, Da Li, Yulin Chen +4
We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with…
cs.CV2025
A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control
Mokai Pan, Kaizhen Zhu, Yuexin Ma +4
Recent advances in diffusion bridge models leverage Doob's -transform to establish fixed endpoints between distributions, demonstrating promising results in image translation an…
cs.CV2025
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
Kaizhen Zhu, Mokai Pan, Yuexin Ma +4
Recent advances in diffusion bridge models leverage Doob's -transform to establish fixed endpoints between distributions, demonstrating promising results in image translation an…