Lune

Profiles2021-2026

Yaodong Yang

Peking University

40Papers
22Last author
40Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers40

  1. DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous GraspingAuthor 11 of 12AAAI 2026 · 89 citations
  2. VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action ModelsAuthor 11 of 11ICML 2026 · 25 citations
  3. Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language ModelsAuthor 8 of 9ICML 2026
  4. SafeLab: An Interactive High-Fidelity Benchmark for Embodied Safety in Scientific RoboticsAuthor 12 of 14ICML 2026
  5. SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead ReasoningAuthor 6 of 7ACL 2026
  6. Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement LearningAuthor 13 of 15ICML 2026
  7. SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained LearningAuthor 8 of 8NeurIPS 2025 · 84 citations
  8. Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human FeedbackAuthor 14 of 14NeurIPS 2025 · 28 citations
  9. Generative RLHF-V: Learning Principles from Multi-modal Human PreferenceAuthor 9 of 9NeurIPS 2025 · 17 citations
  10. RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted BehaviorsAuthor 5 of 5AAAI 2025 · 15 citations
  11. DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous ManipulationAuthor 9 of 11NeurIPS 2025 · 8 citations
  12. Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement LearningAuthor 14 of 16NeurIPS 2025 · 2 citations
  13. Falcon: Fast Visuomotor Policies via Partial DenoisingAuthor 11 of 11ICML 2025
  14. Language Models Resist Alignment: Evidence From Data CompressionAuthor 10 of 10ACL 2025
  15. Mitigating Reward Over-Optimization in RLHF via Behavior-Supported RegularizationAuthor 3 of 5ICLR 2025
  16. PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human PreferenceAuthor 13 of 13ACL 2025
  17. SAE-V: Interpreting Multimodal Models for Enhanced AlignmentAuthor 4 of 4ICML 2025
  18. Towards Efficient Collaboration via Graph Modeling in Reinforcement LearningAuthor 5 of 6AAAI 2025
  19. Safe RLHF: Safe Reinforcement Learning from Human FeedbackAuthor 8 of 8ICLR 2024 · 656 citations
  20. ProAgent: Building Proactive Cooperative Agents with Large Language ModelsAuthor 15 of 15AAAI 2024 · 141 citations
  21. Aligner: Efficient Alignment by Learning to CorrectAuthor 9 of 11NeurIPS 2024 · 115 citations
  22. Panacea: Pareto Alignment via Preference Adaptation for LLMsAuthor 8 of 8NeurIPS 2024 · 89 citations
  23. SafeDreamer: Safe Reinforcement Learning with World ModelsAuthor 5 of 5ICLR 2024 · 46 citations
  24. Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian GameAuthor 8 of 9ICLR 2024 · 30 citations
  25. A Perspective of Q-value Estimation on Offline-to-Online Reinforcement LearningAuthor 5 of 7AAAI 2024 · 28 citations
  26. Maximum Entropy Heterogeneous-Agent Reinforcement LearningAuthor 7 of 7ICLR 2024 · 27 citations
  27. STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement LearningAuthor 3 of 4AAAI 2024 · 11 citations
  28. ACE: Cooperative Multi-Agent Q-learning with Bidirectional Action-DependencyAuthor 6 of 8AAAI 2023 · 38 citations
  29. Hierarchical Multi-Agent Skill DiscoveryAuthor 2 of 5NeurIPS 2023 · 34 citations
  30. Subspace-Aware Exploration for Sparse-Reward Multi-Agent TasksAuthor 5 of 6AAAI 2023 · 15 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines