Zongqing Lu

26

Papers

157

Total Citations

Papers (26)

Cradle: Empowering Foundation Agents towards General Computer Control

Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning

Cross-Embodiment Dexterous Grasping with Reinforcement Learning

Reinforcement Learning Friendly Vision-Language Model for Minecraft

Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

Unified Multimodal Understanding via Byte-Pair Visual Encoding

Learning Multi-Object Positional Relationships via Emergent Communication

Multi-Agent Automated Machine Learning

MotionCtrl: A Real-time Controllable Vision-Language-Motion Model

VideoOrion: Tokenizing Object Dynamics in Videos

Cross-Domain Policy Adaptation by Capturing Representation Mismatch

Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation

ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo

Learning Attentional Communication for Multi-Agent Cooperation

Learning Fairness in Multi-Agent Systems

Learning Individually Inferred Communication for Multi-Agent Cooperation

Mildly Conservative Q-Learning for Offline Reinforcement Learning

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

Learning to Share in Networked Multi-Agent Reinforcement Learning

I2Q: A Fully Decentralized Q-Learning Algorithm

Model-Based Opponent Modeling

Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination

Mutual-Information Regularized Multi-Agent Policy Iteration

Learning from Visual Observation via Offline Pretrained State-to-Go Transformer