6 papers
Unbiased Diffusion Variational Inversion via Principled Posterior Matching
Weimin Bai, Yuxuan Gu, Yifei Wang +2
Existing score-based methods for inverse problems often resort to approximate minimization of the KL divergence between the inversion distribution and the Bayesian posterior. Such…
Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
Junyi Wu, Weijian Luo, Haoyang Zheng +2
Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step g…
Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct
Haoyang Zheng, Xinyang Liu, Cindy Xiangrui Kong +5
Fast and high-quality language generation is the holy grail that people pursue in the age of AI. In this work, we introduce Discrete Diffusion Divergence Instruct (DiDi-Instruct),…
Ultra Fast PDE Solving via Physics Guided Few-step Diffusion
Cindy Xiangrui Kong, Yueqi Wang, Haoyang Zheng +2
Diffusion-based models have demonstrated impressive accuracy and generalization in solving partial differential equations (PDEs). However, they still face significant limitations,…
SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
Shuchen Xue, Mingyang Yi, Weijian Luo +4
Diffusion Probabilistic Models (DPMs) have achieved considerable success in generation tasks. As sampling from DPMs is equivalent to solving diffusion SDE or ODE which is time-cons…
Variational Schrödinger Diffusion Models
Wei Deng, Weijian Luo, Yixin Tan +4
Schrödinger bridge (SB) has emerged as the go-to method for optimizing transportation plans in diffusion models. However, SB requires estimating the intractable forward score func…