Junyu Zhang

papers

393

total citations

papers (10)

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

NEURIPS 2020arXiv

154

citations

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

ICML 2025arXiv

citations

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

NEURIPS 2021arXiv

citations

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

AAAI 2025arXiv

citations

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

ICML 2024arXiv

citations

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

ICML 2024arXiv

citations

Contrastive Sampling Chains in Diffusion Models

NEURIPS 2023

citations

Junyu Zhang

papers (10)

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

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

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

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

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

Anti-Exposure Bias in Diffusion Models

Residual Learning in Diffusion Models

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

Contrastive Sampling Chains in Diffusion Models

papers (10)

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

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

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

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

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

Anti-Exposure Bias in Diffusion Models

Residual Learning in Diffusion Models

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

Contrastive Sampling Chains in Diffusion Models