8 papers
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…
BLADE: Bayesian Langevin Active Discovery with Replica Exchange for Identification of Complex Systems
Cindy Xiangrui Kong, Haoyang Zheng, Guang Lin
Traditional methods for system discovery frequently struggle with efficient data usage and uncertainty quantification. Identifying the governing equations of complex dynamical syst…
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,…
Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
Weixin Wang, Haoyang Zheng, Guang Lin +2
Most existing approximate Thompson Sampling (TS) algorithms for multi-armed bandits use Stochastic Gradient Langevin Dynamics (SGLD) or its variants in each round to sample from th…
ProTDyn: a foundation Protein language model for Thermodynamics and Dynamics generation
Yikai Liu, Haoyang Zheng, Lining Mao +3
Molecular dynamics (MD) simulation has long been the principal computational tool for exploring protein conformational landscapes and dynamics, but its application is limited by hi…