Yaodong Yang
Peking University assistant professor leading the PKU-Alignment group; known for Safe-RLHF, multi-agent RL, and large-scale alignment datasets.
- Role
- professor
- Currently at
- Peking University
- twitter.com/yaodongyang
- GitHub
- github.com/PKU-Alignment
- Scholar
- scholar.google.com/citations
- Papers
- 18
Cite
Notes
Only stored in your browser.
Authored papers
18ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking
arXiv 2026
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
arXiv 2025
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
arXiv 2025
A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
arXiv 2025
Risk-aware Direct Preference Optimization under Nested Risk Measure
arXiv 2025
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
arXiv 2025
Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny
arXiv 2025
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
arXiv 2024
Language Models Resist Alignment: Evidence From Data Compression
arXiv 2024
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
arXiv 2024
In-Context Editing: Learning Knowledge from Self-Induced Distributions
arXiv 2024
ProgressGym: Alignment with a Millennium of Moral Progress
arXiv 2024
BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
NeurIPS
SafeDreamer: Safe Reinforcement Learning with World Models
arXiv 2023
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
arXiv 2023
Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
arXiv 2023
Safe RLHF: Safe Reinforcement Learning from Human Feedback
arXiv 2023
Regret-Minimizing Double Oracle for Extensive-Form Games
arXiv 2023
Tool contributions
1Affiliations
Frequent co-authors
10from 18 papers