Huihan Liu

Huihan Liu

I am a final-year Ph.D. student in Computer Science at the University of Texas at Austin. I am fortunate to be advised by Professor Yuke Zhu, and I am a member of the Robot Perception and Learning Lab.

I build embodied agents that can continually learn from human interactions in open-world environments. I develop algorithms that facilitate robot learning on the job via human-AI partnership, and build scalable, trustworthy agentic systems for long-term deployment.

I previously did my undergraduate in Computer Science at UC Berkeley, affiliated with BAIR, working with Sergey Levine and Costas Spanos.

I'm currently on the job market! Feel free to email me if there is a fit, and check out my CV here.

News & Highlights

Publications

Continual VLA

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

arXiv preprint, 2026
@article{liu2026continualvla,
  title={Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning},
  author={Liu, Huihan and Kim, Changyeon and Liu, Bo and Liu, Minghuan and Zhu, Yuke},
  journal={arXiv preprint},
  year={2026}
}
SCIZOR

SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning

IEEE International Conference on Robotics and Automation (ICRA), 2026
*, †: equal contribution
@misc{zhang2025scizorselfsupervisedapproachdata,
  title={SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning},
  author={Yu Zhang and Yuqi Xie and Huihan Liu and Rutav Shah and Michael Wan and Linxi Fan and Yuke Zhu},
  year={2025},
  eprint={2505.22626},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2505.22626},
}
Casper

Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models

Conference on Robot Learning (CoRL), 2025
@misc{liu2025casperinferringdiverseintents,
  title={Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models},
  author={Huihan Liu and Rutav Shah and Shuijing Liu and Jack Pittenger and Mingyo Seo and Yuchen Cui and Yonatan Bisk and Roberto Martín-Martín and Yuke Zhu},
  year={2025},
  eprint={2506.14727},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2506.14727},
}
Sirius-Fleet

Multi-Task Interactive Robot Fleet Learning with Visual World Models

Conference on Robot Learning (CoRL), 2024
@inproceedings{liumulti,
  title={Multi-Task Interactive Robot Fleet Learning with Visual World Models},
  author={Liu, Huihan and Zhang, Yu and Betala, Vaarij and Zhang, Evan and Liu, James and Ding, Crystal and Zhu, Yuke},
  booktitle={8th Annual Conference on Robot Learning}
}
Sirius (IJRR)

Robot Learning on the Job: Human-in-the-Loop Manipulation and Learning During Deployment (Extended Version)

Huihan Liu, Soroush Nasiriany, Lance Zhang, Zhiyao Bao, Yuke Zhu
The International Journal of Robotics Research (IJRR), 2024
@article{liu2024robot,
  title={Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment},
  author={Huihan Liu and Soroush Nasiriany and Lance Zhang and Zhiyao Bao and Yuke Zhu},
  journal={The International Journal of Robotics Research},
  year={2024}
}
PRIME

PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning

IEEE Robotics and Automation Letters (RA-L), 2024
@misc{gao2024prime,
  title={PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning},
  author={Tian Gao and Soroush Nasiriany and Huihan Liu and Quantao Yang and Yuke Zhu},
  year={2024},
  eprint={2403.00929},
  archivePrefix={arXiv},
  primaryClass={cs.RO}
}
Runtime Monitor

Model-Based Runtime Monitoring with Interactive Imitation Learning

IEEE International Conference on Robotics and Automation (ICRA), 2024
@misc{liu2023modelbased,
  title={Model-Based Runtime Monitoring with Interactive Imitation Learning},
  author={Huihan Liu and Shivin Dass and Roberto Martín-Martín and Yuke Zhu},
  year={2023},
  eprint={2310.17552},
  archivePrefix={arXiv},
  primaryClass={cs.RO}
}
OLAF

Interactive Robot Learning from Verbal Correction

CoRL Workshop on Language and Robot Learning (LangRob), 2023
@misc{liu2023interactive,
  title={Interactive Robot Learning from Verbal Correction},
  author={Huihan Liu and Alice Chen and Yuke Zhu and Adith Swaminathan and Andrey Kolobov and Ching-An Cheng},
  year={2023},
  eprint={2310.17555},
  archivePrefix={arXiv},
  primaryClass={cs.RO}
}
Sirius (RSS)

Robot Learning on the Job: Human-in-the-Loop Manipulation and Learning During Deployment

Huihan Liu, Soroush Nasiriany, Lance Zhang, Zhiyao Bao, Yuke Zhu
Robotics: Science and Systems (RSS), 2023
🏆 Best Paper Award Finalist
@inproceedings{liu2022robot,
  title={Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment},
  author={Huihan Liu and Soroush Nasiriany and Lance Zhang and Zhiyao Bao and Yuke Zhu},
  booktitle={Robotics: Science and Systems (RSS)},
  year={2023}
}
MAPLE

Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks

IEEE International Conference on Robotics and Automation (ICRA), 2022
🏆 Outstanding Learning Paper
@misc{nasiriany2021augmenting,
  title={Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks},
  author={Soroush Nasiriany and Huihan Liu and Yuke Zhu},
  year={2021},
  eprint={2110.03655},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}
Parrot

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

International Conference on Learning Representations (ICLR), 2021
Oral Presentation (top 1.8% of submissions)
@misc{singh2020parrot,
  title={Parrot: Data-Driven Behavioral Priors for Reinforcement Learning},
  author={Avi Singh and Huihan Liu and Gaoyue Zhou and Albert Yu and Nicholas Rhinehart and Sergey Levine},
  year={2020},
  eprint={2011.10024},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}
Continual VLA

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

arXiv preprint, 2026
@article{liu2026continualvla,
  title={Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning},
  author={Liu, Huihan and Kim, Changyeon and Liu, Bo and Liu, Minghuan and Zhu, Yuke},
  journal={arXiv preprint},
  year={2026}
}
SCIZOR

SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning

IEEE International Conference on Robotics and Automation (ICRA), 2026
*, †: equal contribution
@misc{zhang2025scizorselfsupervisedapproachdata,
  title={SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning},
  author={Yu Zhang and Yuqi Xie and Huihan Liu and Rutav Shah and Michael Wan and Linxi Fan and Yuke Zhu},
  year={2025},
  eprint={2505.22626},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2505.22626},
}
Casper

Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models

Conference on Robot Learning (CoRL), 2025
@misc{liu2025casperinferringdiverseintents,
  title={Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models},
  author={Huihan Liu and Rutav Shah and Shuijing Liu and Jack Pittenger and Mingyo Seo and Yuchen Cui and Yonatan Bisk and Roberto Martín-Martín and Yuke Zhu},
  year={2025},
  eprint={2506.14727},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2506.14727},
}
Sirius-Fleet

Multi-Task Interactive Robot Fleet Learning with Visual World Models

Conference on Robot Learning (CoRL), 2024
@inproceedings{liumulti,
  title={Multi-Task Interactive Robot Fleet Learning with Visual World Models},
  author={Liu, Huihan and Zhang, Yu and Betala, Vaarij and Zhang, Evan and Liu, James and Ding, Crystal and Zhu, Yuke},
  booktitle={8th Annual Conference on Robot Learning}
}
Sirius (IJRR)

Robot Learning on the Job: Human-in-the-Loop Manipulation and Learning During Deployment (Extended Version)

Huihan Liu, Soroush Nasiriany, Lance Zhang, Zhiyao Bao, Yuke Zhu
The International Journal of Robotics Research (IJRR), 2024
@article{liu2024robot,
  title={Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment},
  author={Huihan Liu and Soroush Nasiriany and Lance Zhang and Zhiyao Bao and Yuke Zhu},
  journal={The International Journal of Robotics Research},
  year={2024}
}
PRIME

PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning

IEEE Robotics and Automation Letters (RA-L), 2024
@misc{gao2024prime,
  title={PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning},
  author={Tian Gao and Soroush Nasiriany and Huihan Liu and Quantao Yang and Yuke Zhu},
  year={2024},
  eprint={2403.00929},
  archivePrefix={arXiv},
  primaryClass={cs.RO}
}
Runtime Monitor

Model-Based Runtime Monitoring with Interactive Imitation Learning

IEEE International Conference on Robotics and Automation (ICRA), 2024
@misc{liu2023modelbased,
  title={Model-Based Runtime Monitoring with Interactive Imitation Learning},
  author={Huihan Liu and Shivin Dass and Roberto Martín-Martín and Yuke Zhu},
  year={2023},
  eprint={2310.17552},
  archivePrefix={arXiv},
  primaryClass={cs.RO}
}
OLAF

Interactive Robot Learning from Verbal Correction

CoRL Workshop on Language and Robot Learning (LangRob), 2023
@misc{liu2023interactive,
  title={Interactive Robot Learning from Verbal Correction},
  author={Huihan Liu and Alice Chen and Yuke Zhu and Adith Swaminathan and Andrey Kolobov and Ching-An Cheng},
  year={2023},
  eprint={2310.17555},
  archivePrefix={arXiv},
  primaryClass={cs.RO}
}
Sirius (RSS)

Robot Learning on the Job: Human-in-the-Loop Manipulation and Learning During Deployment

Huihan Liu, Soroush Nasiriany, Lance Zhang, Zhiyao Bao, Yuke Zhu
Robotics: Science and Systems (RSS), 2023
🏆 Best Paper Award Finalist
@inproceedings{liu2022robot,
  title={Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment},
  author={Huihan Liu and Soroush Nasiriany and Lance Zhang and Zhiyao Bao and Yuke Zhu},
  booktitle={Robotics: Science and Systems (RSS)},
  year={2023}
}
MAPLE

Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks

IEEE International Conference on Robotics and Automation (ICRA), 2022
🏆 Outstanding Learning Paper
@misc{nasiriany2021augmenting,
  title={Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks},
  author={Soroush Nasiriany and Huihan Liu and Yuke Zhu},
  year={2021},
  eprint={2110.03655},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}
Parrot

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

International Conference on Learning Representations (ICLR), 2021
Oral Presentation (top 1.8% of submissions)
@misc{singh2020parrot,
  title={Parrot: Data-Driven Behavioral Priors for Reinforcement Learning},
  author={Avi Singh and Huihan Liu and Gaoyue Zhou and Albert Yu and Nicholas Rhinehart and Sergey Levine},
  year={2020},
  eprint={2011.10024},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}
CADA

Consensus Adversarial Domain Adaptation

AAAI Conference on Artificial Intelligence, 2019
@inproceedings{Zou2019ConsensusAD,
  title={Consensus Adversarial Domain Adaptation},
  author={Han Zou and Yuxun Zhou and Jianfei Yang and Huihan Liu and H. Das and C. Spanos},
  booktitle={AAAI},
  year={2019}
}
WiFi+Vision

WiFi and Vision Multimodal Learning for Accurate and Robust Device-Free Human Activity Recognition

MULA Workshop, CVPR, 2019
@InProceedings{Zou_2019_CVPR_Workshops,
  author={Zou, Han and Yang, Jianfei and Prasanna Das, Hari and Liu, Huihan and Zhou, Yuxun and Spanos, Costas J.},
  title={WiFi and Vision Multimodal Learning for Accurate and Robust Device-Free Human Activity Recognition},
  booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month={June},
  year={2019}
}
Energy+DL

A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University

Ioannis Konstantakopoulos, Andrew R. Barkan, Shiying He, Tanya Veeravalli, Huihan Liu, Costas J. Spanos
Applied Energy Journal, Volume 237, 2019
@misc{konstantakopoulos2018deep,
  title={A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University},
  author={Ioannis C. Konstantakopoulos and Andrew R. Barkan and Shiying He and Tanya Veeravalli and Huihan Liu and Costas Spanos},
  year={2018},
  eprint={1809.05142},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}