α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Haifeng Zhang
Haifeng Zhang
8
papers
254
total citations
papers (8)
Token-level Direct Preference Optimization
ICML 2024
arXiv
120
citations
Settling the Variance of Multi-Agent Policy Gradients
NEURIPS 2021
arXiv
95
citations
Efficient Reinforcement Learning with Large Language Model Priors
ICLR 2025
arXiv
21
citations
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
NEURIPS 2022
arXiv
12
citations
EconGym: A Scalable AI Testbed with Diverse Economic Tasks
NEURIPS 2025
arXiv
4
citations
Self-Verifying Reflection Helps Transformers with CoT Reasoning
NEURIPS 2025
arXiv
2
citations
An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination
NEURIPS 2023
0
citations
Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network
CVPR 2025
0
citations