Wenjia Wang

Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

TSI-Bench: Benchmarking Time Series Imputation

Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model

D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning

Elucidating the design space of classifier-guided diffusion generation