Yi Wu

Affiliations

Tsinghua University

papers

573

total citations

papers (13)

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

ICML 2024arXiv

253

citations

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

ICML 2024arXiv

136

citations

SaccadeNet: A Fast and Accurate Object Detector

CVPR 2020arXiv

citations

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems

NEURIPS 2021arXiv

citations

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning

AAAI 2024arXiv

citations

Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations

ICML 2024

citations

Uncertainty-Based Spatial-Temporal Attention for Online Action Detection

ECCV 2022

citations

NovelD: A Simple yet Effective Exploration Criterion

NEURIPS 2021

citations

Yi Wu

Affiliations

papers (13)

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

SaccadeNet: A Fast and Accurate Object Detector

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems

Learning Efficient Multi-agent Cooperative Visual Exploration

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

SOAR: Scene-debiasing Open-set Action Recognition

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning

Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations

Uncertainty-Based Spatial-Temporal Attention for Online Action Detection

NovelD: A Simple yet Effective Exploration Criterion

papers (13)

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

SaccadeNet: A Fast and Accurate Object Detector

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems

Learning Efficient Multi-agent Cooperative Visual Exploration

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

SOAR: Scene-debiasing Open-set Action Recognition

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning

Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations

Uncertainty-Based Spatial-Temporal Attention for Online Action Detection

NovelD: A Simple yet Effective Exploration Criterion