Pei Xu
13 papers · 2022–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (21) 🌍 Conference Polyglot · Silver 🌈 Renaissance Researcher (5) 💎 Century Club · Bronze
🗃️
Keyword Collector
(53)
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Reinforcement Learning
(6)
Methods
(6)
Machine Learning
(2)
Robotics
(2)
Computer Science
(1)
Computer Vision
(1)
Applications · Robotics
(1)
Applications · Computer Science
(1)
Capabilities
(1)
Core Methods
(1)
Domain-Specific
(1)
Learning Paradigms
(1)
Learning Types
(1)
Keywords
multi-agent reinforcement learning
(4)
sparse reward
(3)
motion planning
(1)
reinforcement learning
(1)
continual learning
(1)
robotic manipulation
(1)
embedding learning
(1)
counterfactual regret minimization
(1)
diverse exploration
(1)
autonomous driving
(1)
human-object interaction
(1)
motion capture
(1)
parameter sharing
(1)
dynamic parameters
(1)
reward function
(1)
game theory
(1)
3d object detection
(1)
skill learning
(1)
vision-language model
(1)
deep reinforcement learning
(1)
Papers
AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
CVPR 2026
No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained Embedding
AAAI 2026
Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
CVPR 2026
Push-and-Step: From RL-Based Balance Recovery to Physical Simulation of Dense Crowds
CVPR 2026
RefRea: Reference-Guided Reasoning with Meta-Cognition for Accurate Language Model Agents
AAAI 2026
Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity
IJCAI 2025
Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching
CoRL 2025
Human-Object Interaction from Human-Level Instructions
ICCV 2025
ADMN: Agent-Driven Modular Network for Dynamic Parameter Sharing in Cooperative Multi-Agent Reinforcement Learning
IJCAI 2024
Population-Based Diverse Exploration for Sparse-Reward Multi-Agent Tasks
IJCAI 2024
Exploration via Joint Policy Diversity for Sparse-Reward Multi-Agent Tasks
IJCAI 2023
Subspace-Aware Exploration for Sparse-Reward Multi-Agent Tasks
AAAI 2023
SocialVAE: Human Trajectory Prediction Using Timewise Latents
ECCV 2022