Picture for Junpeng Yue

Junpeng Yue

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

Add code
Oct 04, 2024
Viaarxiv icon

Egocentric Vision Language Planning

Add code
Aug 11, 2024
Viaarxiv icon

Towards General Computer Control: A Multimodal Agent for Red Dead Redemption II as a Case Study

Add code
Mar 07, 2024
Viaarxiv icon

CLIP4MC: An RL-Friendly Vision-Language Model for Minecraft

Add code
Mar 19, 2023
Viaarxiv icon

Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning

Add code
Oct 25, 2022
Viaarxiv icon