Zongqing Lu

papers

735

total citations

papers (24)

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

NEURIPS 2022arXiv

citations

Cross-Domain Policy Adaptation by Capturing Representation Mismatch

ICML 2024arXiv

citations

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

ICLR 2024

citations

Cross-Embodiment Dexterous Grasping with Reinforcement Learning

ICLR 2025arXiv

citations

Reinforcement Learning Friendly Vision-Language Model for Minecraft

ECCV 2024arXiv

citations

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

NEURIPS 2023arXiv

citations

VideoOrion: Tokenizing Object Dynamics in Videos

ICCV 2025arXiv

citations

Unified Multimodal Understanding via Byte-Pair Visual Encoding

ICCV 2025arXiv

citations

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

ICLR 2025arXiv

citations

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

ICCV 2025arXiv

citations

Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing

AAAI 2024arXiv

citations

Multi-Agent Automated Machine Learning

CVPR 2023arXiv

citations

Learning Multi-Object Positional Relationships via Emergent Communication

AAAI 2024arXiv

citations

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

ICML 2024arXiv

citations

Mutual-Information Regularized Multi-Agent Policy Iteration

NEURIPS 2023

citations

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

ICCV 2025

citations

I2Q: A Fully Decentralized Q-Learning Algorithm

NEURIPS 2022

citations

Learning to Share in Networked Multi-Agent Reinforcement Learning

NEURIPS 2022

citations

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

ICCV 2023

citations

Zongqing Lu

papers (24)

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

Mildly Conservative Q-Learning for Offline Reinforcement Learning

Learning Individually Inferred Communication for Multi-Agent Cooperation

Cradle: Empowering Foundation Agents towards General Computer Control

Model-Based Opponent Modeling

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

Cross-Domain Policy Adaptation by Capturing Representation Mismatch

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

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

VideoOrion: Tokenizing Object Dynamics in Videos

Unified Multimodal Understanding via Byte-Pair Visual Encoding

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

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

Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing

Multi-Agent Automated Machine Learning

Learning Multi-Object Positional Relationships via Emergent Communication

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

Mutual-Information Regularized Multi-Agent Policy Iteration

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

I2Q: A Fully Decentralized Q-Learning Algorithm

Learning to Share in Networked Multi-Agent Reinforcement Learning

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

papers (24)

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

Mildly Conservative Q-Learning for Offline Reinforcement Learning

Learning Individually Inferred Communication for Multi-Agent Cooperation

Cradle: Empowering Foundation Agents towards General Computer Control

Model-Based Opponent Modeling

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

Cross-Domain Policy Adaptation by Capturing Representation Mismatch

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

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

VideoOrion: Tokenizing Object Dynamics in Videos

Unified Multimodal Understanding via Byte-Pair Visual Encoding

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

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

Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing

Multi-Agent Automated Machine Learning

Learning Multi-Object Positional Relationships via Emergent Communication

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

Mutual-Information Regularized Multi-Agent Policy Iteration

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

I2Q: A Fully Decentralized Q-Learning Algorithm

Learning to Share in Networked Multi-Agent Reinforcement Learning

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