Junyu Zhang

11

Papers

33

Total Citations

Papers (11)

DiffuseHigh: Training-Free Progressive High-Resolution Image Synthesis Through Structure Guidance

Anti-Exposure Bias in Diffusion Models

Residual Learning in Diffusion Models

An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control

Contrastive Sampling Chains in Diffusion Models

A Composite Randomized Incremental Gradient Method

A Stochastic Composite Gradient Method with Incremental Variance Reduction

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method

A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP