1 | PAIR Lab: PKU Alignment and Interaction Research Labhttps://pair-lab.ai/publication-type/1/1Hugo Blox Builder (https://hugoblox.com)en-usThu, 03 Jul 2025 00:00:00 +0000https://pair-lab.ai/media/icon_hu4f2a7092ab9dace538e8dee71ba34a1a_30036_512x512_fill_lanczos_center_3.png1https://pair-lab.ai/publication-type/1/Benchmarking Multi-national Value Alignment for Large Language Modelshttps://pair-lab.ai/publication/acl_2025_2/Thu, 03 Jul 2025 00:00:00 +0000https://pair-lab.ai/publication/acl_2025_2/PKU-safeRLHF: Towards Multi-level Safety Alignment for LLMs with Human Preferencehttps://pair-lab.ai/publication/acl_2025_3/Thu, 03 Jul 2025 00:00:00 +0000https://pair-lab.ai/publication/acl_2025_3/Differentiable Information Enhanced Model-Based Reinforcement Learninghttps://pair-lab.ai/publication/aaai_2025/Thu, 03 Apr 2025 00:00:00 +0000https://pair-lab.ai/publication/aaai_2025/Distributed Policy Space Response Oracles in Two-Player Zero-Sum Gameshttps://pair-lab.ai/publication/ieee_2025/Thu, 03 Apr 2025 00:00:00 +0000https://pair-lab.ai/publication/ieee_2025/Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignmenthttps://pair-lab.ai/publication/iclr_2025_2/Thu, 03 Apr 2025 00:00:00 +0000https://pair-lab.ai/publication/iclr_2025_2/Rat: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviorshttps://pair-lab.ai/publication/aaai_2025_3/Thu, 03 Apr 2025 00:00:00 +0000https://pair-lab.ai/publication/aaai_2025_3/Towards Efficient Collaboration Via Graph Modeling In Reinforcement Learninghttps://pair-lab.ai/publication/aaai_2025_2/Thu, 03 Apr 2025 00:00:00 +0000https://pair-lab.ai/publication/aaai_2025_2/Differentiable Information Enhanced Model-Based Reinforcement Learninghttps://pair-lab.ai/publication/aaai_2025_oral_1/Mon, 03 Mar 2025 00:00:00 +0000https://pair-lab.ai/publication/aaai_2025_oral_1/Falcon: Fast Visuomotor Policies via Partial Denoisinghttps://pair-lab.ai/publication/icml_2025/Mon, 03 Mar 2025 00:00:00 +0000https://pair-lab.ai/publication/icml_2025/Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedbackhttps://pair-lab.ai/publication/aaai_2025_oral_2/Mon, 03 Mar 2025 00:00:00 +0000https://pair-lab.ai/publication/aaai_2025_oral_2/Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMshttps://pair-lab.ai/publication/iclr_2025/Wed, 26 Feb 2025 00:00:00 +0000https://pair-lab.ai/publication/iclr_2025/SAE-V: Interpreting Multimodal Models for Enhanced Alignmenthttps://pair-lab.ai/publication/icml_2025_2/Mon, 03 Feb 2025 00:00:00 +0000https://pair-lab.ai/publication/icml_2025_2/Stream Aligner: Efficient Sentence-Level Alignment via Distribution Inductionhttps://pair-lab.ai/publication/aaai_2025_alignment/Thu, 09 Jan 2025 00:00:00 +0000https://pair-lab.ai/publication/aaai_2025_alignment/Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularizationhttps://pair-lab.ai/publication/iclr_2025_3/Fri, 03 Jan 2025 00:00:00 +0000https://pair-lab.ai/publication/iclr_2025_3/Safesora: Towards Safety Alignment of Text2video Generation via a Human Preference Datasethttps://pair-lab.ai/publication/nips_2025_2/Fri, 03 Jan 2025 00:00:00 +0000https://pair-lab.ai/publication/nips_2025_2/Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learninghttps://pair-lab.ai/publication/nips_2025/Fri, 03 Jan 2025 00:00:00 +0000https://pair-lab.ai/publication/nips_2025/JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelshttps://pair-lab.ai/publication/pami/Thu, 05 Dec 2024 00:00:00 +0000https://pair-lab.ai/publication/pami/Aligner: Efficient Alignment by Learning to Correcthttps://pair-lab.ai/publication/nips_2024_oral/Thu, 26 Sep 2024 00:00:00 +0000https://pair-lab.ai/publication/nips_2024_oral/Panacea: Pareto Alignment via Preference Adaptation for LLMshttps://pair-lab.ai/publication/nips_2024/Thu, 26 Sep 2024 00:00:00 +0000https://pair-lab.ai/publication/nips_2024/Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Graspinghttps://pair-lab.ai/publication/corl_2024/Fri, 06 Sep 2024 00:00:00 +0000https://pair-lab.ai/publication/corl_2024/Off-Agent Trust Region Policy Optimizationhttps://pair-lab.ai/publication/ijcai_2024/Sat, 03 Aug 2024 00:00:00 +0000https://pair-lab.ai/publication/ijcai_2024/ProgressGym: Alignment with a Millennium of Moral Progresshttps://pair-lab.ai/publication/nips_2024_db_spotlight/Sat, 03 Aug 2024 00:00:00 +0000https://pair-lab.ai/publication/nips_2024_db_spotlight/Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planninghttps://pair-lab.ai/publication/icml_2024_2/Fri, 12 Jul 2024 00:00:00 +0000https://pair-lab.ai/publication/icml_2024_2/In-Context Editing: Learning Knowledge from Self-Induced Distributionshttps://pair-lab.ai/publication/iclr_2025_4/Mon, 03 Jun 2024 00:00:00 +0000https://pair-lab.ai/publication/iclr_2025_4/Language models resist alignment: Evidence from data compressionhttps://pair-lab.ai/publication/acl_2025_best_paper/Mon, 03 Jun 2024 00:00:00 +0000https://pair-lab.ai/publication/acl_2025_best_paper/Remember the Past for Better Future: Memory-Augmented Offline RLhttps://pair-lab.ai/publication/ieee_2024/Mon, 03 Jun 2024 00:00:00 +0000https://pair-lab.ai/publication/ieee_2024/Anyskill: Learning Open-Vocabulary Physical Skill for Interactive Agentshttps://pair-lab.ai/publication/cvpr_2024/Sun, 19 May 2024 00:00:00 +0000https://pair-lab.ai/publication/cvpr_2024/End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanationshttps://pair-lab.ai/publication/icml_2024_1/Thu, 02 May 2024 00:00:00 +0000https://pair-lab.ai/publication/icml_2024_1/A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learninghttps://pair-lab.ai/publication/aaai_2024_2/Wed, 06 Mar 2024 00:00:00 +0000https://pair-lab.ai/publication/aaai_2024_2/Grasp Multiple Objects with One Handhttps://pair-lab.ai/publication/ral_2024/Wed, 06 Mar 2024 00:00:00 +0000https://pair-lab.ai/publication/ral_2024/ProAgent: Building Proactive Cooperative Agents with Large Language Modelshttps://pair-lab.ai/publication/aaai_2024_oral/Sun, 03 Mar 2024 00:00:00 +0000https://pair-lab.ai/publication/aaai_2024_oral/STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learninghttps://pair-lab.ai/publication/aaai_2024_1/Tue, 06 Feb 2024 00:00:00 +0000https://pair-lab.ai/publication/aaai_2024_1/CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agentshttps://pair-lab.ai/publication/iclr24_spotlight_2/Mon, 01 Jan 2024 00:00:00 +0000https://pair-lab.ai/publication/iclr24_spotlight_2/Maximum Entropy Heterogeneous-Agent Reinforcement Learninghttps://pair-lab.ai/publication/iclr24_spotlight/Mon, 01 Jan 2024 00:00:00 +0000https://pair-lab.ai/publication/iclr24_spotlight/BeaverTails: A Human-Preference Dataset for LLM Harmlessness Alignmenthttps://pair-lab.ai/publication/neurips23db_2/Tue, 30 May 2023 00:00:00 +0000https://pair-lab.ai/publication/neurips23db_2/Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmarkhttps://pair-lab.ai/publication/neurips23db_1/Tue, 30 May 2023 00:00:00 +0000https://pair-lab.ai/publication/neurips23db_1/Unidexgrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learninghttps://pair-lab.ai/publication/iccv23/Thu, 04 May 2023 00:00:00 +0000https://pair-lab.ai/publication/iccv23/GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Modelshttps://pair-lab.ai/publication/icml_2023_4/Tue, 25 Apr 2023 00:00:00 +0000https://pair-lab.ai/publication/icml_2023_4/A Game-Theoretic Framework for Managing Risk in Multi-Agent Systemshttps://pair-lab.ai/publication/icml_2023_3/Mon, 24 Apr 2023 00:00:00 +0000https://pair-lab.ai/publication/icml_2023_3/Regret-Minimizing Double Oracle for Extensive-Form Gameshttps://pair-lab.ai/publication/icml_2023_1/Thu, 20 Apr 2023 00:00:00 +0000https://pair-lab.ai/publication/icml_2023_1/MANSA: Learning Fast and Slow in Multi-Agent Systemshttps://pair-lab.ai/publication/icml_2023_2/Sun, 12 Feb 2023 00:00:00 +0000https://pair-lab.ai/publication/icml_2023_2/Learning to Shape Rewards using a Game of Two Partnershttps://pair-lab.ai/publication/aaai_2023_1/Mon, 06 Feb 2023 00:00:00 +0000https://pair-lab.ai/publication/aaai_2023_1/Quality-Similar Diversity via Population Based Reinforcement Learninghttps://pair-lab.ai/publication/iclr_2023/Thu, 02 Feb 2023 00:00:00 +0000https://pair-lab.ai/publication/iclr_2023/A Game-Theoretic Approach to Multi-agent Trust Region Optimizationhttps://pair-lab.ai/publication/dai/Thu, 15 Dec 2022 00:00:00 +0000https://pair-lab.ai/publication/dai/ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependencyhttps://pair-lab.ai/publication/aaai_2023_2/Tue, 29 Nov 2022 00:00:00 +0000https://pair-lab.ai/publication/aaai_2023_2/Contextual Transformer for Offline Meta Reinforcement Learninghttps://pair-lab.ai/publication/nips_workshop_2/Tue, 15 Nov 2022 00:00:00 +0000https://pair-lab.ai/publication/nips_workshop_2/TorchOpt: An Efficient Library for Differentiable Optimizationhttps://pair-lab.ai/publication/nips_workshop_1/Sun, 13 Nov 2022 00:00:00 +0000https://pair-lab.ai/publication/nips_workshop_1/Scalable Model-based Policy Optimization for Decentralized Networked Systemshttps://pair-lab.ai/publication/iros_2022/Sun, 23 Oct 2022 00:00:00 +0000https://pair-lab.ai/publication/iros_2022/GenDexGrasp: Generalizable Dexterous Graspinghttps://pair-lab.ai/publication/icra_2023_2/Mon, 03 Oct 2022 00:00:00 +0000https://pair-lab.ai/publication/icra_2023_2/A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learninghttps://pair-lab.ai/publication/neurips_2022_2/Wed, 28 Sep 2022 00:00:00 +0000https://pair-lab.ai/publication/neurips_2022_2/A Unified Diversity Measure for Multiagent Reinforcement Learninghttps://pair-lab.ai/publication/neurips_2022_5/Wed, 28 Sep 2022 00:00:00 +0000https://pair-lab.ai/publication/neurips_2022_5/Constrained Update Projection Approach to Safe Policy Optimizationhttps://pair-lab.ai/publication/neurips_2022_3/Wed, 28 Sep 2022 00:00:00 +0000https://pair-lab.ai/publication/neurips_2022_3/MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Controlhttps://pair-lab.ai/publication/neurips_2022_7/Wed, 28 Sep 2022 00:00:00 +0000https://pair-lab.ai/publication/neurips_2022_7/Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learninghttps://pair-lab.ai/publication/neurips_2022_1/Wed, 28 Sep 2022 00:00:00 +0000https://pair-lab.ai/publication/neurips_2022_1/Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learninghttps://pair-lab.ai/publication/neurips_2022_6/Wed, 28 Sep 2022 00:00:00 +0000https://pair-lab.ai/publication/neurips_2022_6/End-to-End Affordance Learning for Robotic Manipulationhttps://pair-lab.ai/publication/icra_2023_1/Mon, 26 Sep 2022 00:00:00 +0000https://pair-lab.ai/publication/icra_2023_1/Debias the Black-Box: A Fair Ranking Framework via Knowledge Distillationhttps://pair-lab.ai/publication/wise_2022/Wed, 24 Aug 2022 00:00:00 +0000https://pair-lab.ai/publication/wise_2022/Multi-Agent Reinforcement Learning is a Sequence Modeling Problemhttps://pair-lab.ai/publication/neurips_2022_4/Mon, 30 May 2022 00:00:00 +0000https://pair-lab.ai/publication/neurips_2022_4/On the Convergence of Fictitious Play: A Decomposition Approachhttps://pair-lab.ai/publication/ijcai_2021/Tue, 03 May 2022 00:00:00 +0000https://pair-lab.ai/publication/ijcai_2021/Neural Auto-Curricula in Two-Player Zero-Sum Gameshttps://pair-lab.ai/publication/neurips2021_1/Mon, 06 Dec 2021 00:00:00 +0000https://pair-lab.ai/publication/neurips2021_1/LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learninghttps://pair-lab.ai/publication/iclr_2022_1/Sun, 05 Dec 2021 00:00:00 +0000https://pair-lab.ai/publication/iclr_2022_1/Trust Region Policy Optimisation in Multi-Agent Reinforcement Learninghttps://pair-lab.ai/publication/iclr_2022_2/Thu, 23 Sep 2021 00:00:00 +0000https://pair-lab.ai/publication/iclr_2022_2/Settling the Variance of Multi-Agent Policy Gradientshttps://pair-lab.ai/publication/neurips2021_3/Thu, 19 Aug 2021 00:00:00 +0000https://pair-lab.ai/publication/neurips2021_3/Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Gameshttps://pair-lab.ai/publication/neurips2021_2/Wed, 09 Jun 2021 00:00:00 +0000https://pair-lab.ai/publication/neurips2021_2/