Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Towards Evaluating Generalist Agents: An Automated Benchmark in Open World
Published in Preprint, 2023
MineCraft Universe (MCU) benchmark for evaluating generalist agents in open-world environments.
Recommended citation: X. Zheng, H. Lin, K. He, Z. Wang, Z. Zheng, Q. Fu, H. Fu, and Y. Liang. (2023). "Towards Evaluating Generalist Agents: An Automated Benchmark in Open World." Preprint.
Hyperbolic Pre-Trained Language Model
Published in IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024.
Recommended citation: W. Chen, X. Han, Y. Lin, K. He, R. Xie, J. Zhou, Z. Liu, and M. Sun. (2024). "Hyperbolic Pre-Trained Language Model." IEEE/ACM Transactions on Audio, Speech, and Language Processing.
Training Open-ended Policies to follow Video-prompt Instructions with Reinforcement Learning
Published in OpenReview preprint, 2024
OpenReview preprint on training open-ended policies with video-prompt instructions and reinforcement learning.
Recommended citation: K. He, B. Zhang, Z. Wang, S. Cai, Q. Fu, H. Fu, A. Liu, and Y. Liang. (2024). "Training Open-ended Policies to follow Video-prompt Instructions with Reinforcement Learning." OpenReview preprint.
Minestudio: A streamlined package for minecraft ai agent development
Published in arXiv preprint arXiv:2412.18293, 2024
arXiv preprint arXiv:2412.18293. Cited by 2.
Recommended citation: S. Cai, Z. Mu, K. He, B. Zhang, X. Zheng, A. Liu, and Y. Liang. (2024). "Minestudio: A streamlined package for minecraft ai agent development." arXiv preprint arXiv:2412.18293.
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
Published in Findings of the Association for Computational Linguistics (ACL Findings), 2025
ACL Findings 2025.
Recommended citation: M. Li, Z. Wang, K. He, X. Ma, and Y. Liang. (2025). "JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse." Findings of the Association for Computational Linguistics (ACL Findings).
MCU: An evaluation framework for open-ended game agents
Published in International Conference on Machine Learning (ICML), 2025
ICML 2025 Spotlight.
Recommended citation: X. Zheng, H. Lin, K. He, Z. Wang, Q. Fu, H. Fu, Z. Zheng, and Y. Liang. (2025). "MCU: An Evaluation Framework for Open-Ended Game Agents." International Conference on Machine Learning (ICML). Spotlight.
OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
Published in International Conference on Machine Learning (ICML), 2026
ICML 2026.
Recommended citation: Z. Wang, M. Li, K. He, X. Wang, Z. Mu, M. Liu, A. Liu, and Y. Liang. (2026). "OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft." International Conference on Machine Learning (ICML).
DeepHA: Scaling Action Chains Elicits Deep Hierarchical Agents
Published in International Conference on Machine Learning (ICML), 2026
ICML 2026.
Recommended citation: Z. Wang, M. Li, K. He, H. Lin, X. Ma, A. Liu, and Y. Liang. (2026). "DeepHA: Scaling Action Chains Elicits Deep Hierarchical Agents." International Conference on Machine Learning (ICML).
CrossAgent: Bridging Cross-level Actions into One Agentic Model via Reinforcement Learning
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
CVPR 2026 Highlight.
Recommended citation: K. He, Z. Wang, M. Li, A. Liu, and Y. Liang. (2026). "CrossAgent: Bridging Cross-level Actions into One Agentic Model via Reinforcement Learning." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Highlight.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.