About | Haoran Hao

About Me

I am a second-year Master's in Robotics (MSR) student at Carnegie Mellon University's Robotics Institute, advised by Prof. Jeff Schneider and Prof. Jeffrey Ichnowski.
I obtained my bachelor's degree in Artificial Intelligence from Nanjing University in 2025. Previously, I had the privilege of working with Dr. Zhi Hou at Shanghai Artificial Intelligence Laboratory, Prof. Xiangyu Yue at MMLab@The Chinese University of Hong Kong, and Prof. Yu-Feng Li at Nanjing University.
I am open to discussions or collaboration opportunities. If you are interested in my work, feel free to reach out via email.
*NEW* I am currently seeking PhD and research opportunities in frontier AI and robotics research.

Research Interests

My research interests are broadly in Artificial Intelligence and Robotics, with a focus on Machine Learning, Multimodal Perception, and Robotic Manipulation. I am passionate about developing intelligent systems that can perceive, reason, and interact with the physical world.

Machine Learning: Improving the performance and data efficiency of machine learning methods for robotics.
Multimodal Perception: Enabling robots to perceive and understand environments through multimodal inputs.
Robotics: Developing intelligent robots that can perceive, reason, and interact with the physical world.

News

[2026.09] FAR and AHEAD have been accepted to CoRL 2026.
[2026.08] Gave a presentation at the 7th CMU Robot Learning Workshop. [Slides]
[2026.01] Vlaser has been accepted to ICLR 2026.
[2025.11] OC-VLA has been accepted to AAAI 2026.
[2025.02] I have been admitted to the Robotics Institute at Carnegie Mellon University!🎉🎓
[2025.02] RAP has been accepted to CVPR 2025.
[2024.11] ABIL has been accepted to KDD 2025.
[2024.10] Awarded BYD Scholarship (Ranked 2/102 in my grade).
[2024.05] Gave an oral presentation at the Robust Machine Learning in Open Environments Workshop at PAKDD 2024. [Slides]
[2023.12] Awarded National Scholarship (Ranked 1/102 in my grade).

Publications

(* denotes equal contribution)

FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement

Conference on Robot Learning (CoRL), 2026
Haoran Hao, Shahram Najam Syed, Jeffrey Ichnowski, Jeff Schneider
Paper

Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models

Preprint, 2026
Haoran Hao, Shahram Najam Syed, Jeff Schneider, Jeffrey Ichnowski
Paper | Project

Reason Twice: Segmentation via Candidate Discovery and Comparative Reasoning

Preprint, 2026
Xinyan Gao*, Haoran Hao*, Xiangyu Yue
Paper | Project | Code

Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation

Conference on Robot Learning (CoRL), 2026
Shahram Najam Syed, Arthur Jakobsson, Haoran Hao, Jeffrey Ichnowski
Paper

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Technical Report
InternVL Team
Paper | Project | Code

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

International Conference on Learning Representations (ICLR), 2026
Ganlin Yang*, Tianyi Zhang*, Haoran Hao*, Weiyun Wang, Weijie Su, Wengang Zhou,
Yu Qiao, Jifeng Dai, Jiangmiao Pang, Gen Luo, Wenhai Wang, Yao Mu, Zhi Hou
Paper | Project | Code

Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy

AAAI Conference on Artificial Intelligence (AAAI), 2026
Tianyi Zhang*, Haonan Duan*, Haoran Hao, Yu Qiao, Jifeng Dai, Zhi Hou
Paper | Project | Code

Multimodal Long Video Modeling Based on Temporal Dynamic Context

Preprint, 2025
Haoran Hao*, Jiaming Han*, Yiyuan Zhang, Xiangyu Yue
Paper | Project | Code

RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models

Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Haoran Hao*, Jiaming Han*, Changsheng Li, Yufeng Li, Xiangyu Yue
Paper | Project | Code

Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025 Oral
Robust Machine Learning in Open Environments Workshop at PAKDD 2024, Best Paper Award
Jiejing Shao*, Haoran Hao*, Xiaowen Yang, Yufeng Li
Paper | Project | Code