3 papers
cs.LG2026
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
Jinkyu Kim, Jinyoung Choi, Bohyung Han
We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with respect to timestep schedules and classifier-free g…
cs.LG2026
Score-Repellent Monte Carlo: Toward Efficient Non-Markovian Sampler with Constant Memory in General State Spaces
Jie Hu, Lingyun Chen, Geeho Kim +3
History-dependent sampling can reduce long-run Monte Carlo variance by discouraging redundant revisits, but existing schemes typically encode history through empirical measure on f…
cs.CV2024
FIFO-Diffusion: Generating Infinite Videos from Text without Training
Jihwan Kim, Junoh Kang, Jinyoung Choi +1
We propose a novel inference technique based on a pretrained diffusion model for text-conditional video generation. Our approach, called FIFO-Diffusion, is conceptually capable of…