Publications
Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
Guangyu Zhao, Kewei Lian, Haoxuan Ru, Borong Zhang, Haowei Lin, Zhancun Mu, Haobo Fu, Qiang Fu, Shaofei Cai, Zihao Wang, Yitao Liang
ICML 2026 [Project] [Paper] [Code]
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
Muyao Li, Zihao Wang, Kaichen He, Xiaojian Ma, Yitao Liang
ACL 2025 [Project] [Paper] [Code]
MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft
Xinyue Zheng, Haowei Lin, Kaichen He, Zihao Wang, Zilong Zheng, Yitao Liang
ICML 2025 (Spotlight) [Project] [Paper] [Code]
ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting
Shaofei Cai, Zihao Wang, Kewei Lian, Zhancun Mu, Xiaojian Ma, Anji Liu, Yitao Liang
CVPR 2025 [Project] [Paper] [Code]
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
Zihao Wang, Shaofei Cai, Zhancun Mu, Haowei Lin, Ceyao Zhang, Xuejie Liu, Qing Li, Anji Liu, Xiaojian Ma, Yitao Liang
NeurIPS 2024 [Project] [Paper] [Code]
JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models
Zihao Wang, Shaofei Cai, Anji Liu, Yonggang Jin, Jinbing Hou, Bowei Zhang, Haowei Lin, Zhaofeng He, Zilong Zheng, Yaodong Yang, Xiaojian Ma, Yitao Liang
T-PAMI 2024 [Project] [Paper] [Code] [Twitter] [Media]
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
Zihao Wang, Shaofei Cai, Anji Liu, Xiaojian Ma, Yitao Liang
NeurIPS 2023 (ICML 2023 TEACH Best Paper Award) [Paper] [Code] [Twitter]
GROOT: Learning to Follow Instructions by Watching Gameplay Videos
Shaofei Cai, Bowei Zhang, Zihao Wang, Xiaojian Ma, Anji Liu, Yitao Liang
ICLR 2024 (Spotlight) [Project] [Paper] [Code] [Twitter] [Media]
Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
Shaofei Cai, Zihao Wang, Xiaojian Ma, Anji Liu, Yitao Liang
CVPR 2023 [Paper] [Code]