Zongqing Lu

13

Papers

157

Total Citations

Papers (13)

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

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

Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing

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

VideoOrion: Tokenizing Object Dynamics in Videos

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

Cross-Domain Policy Adaptation by Capturing Representation Mismatch

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