I am a senior student at School of Artificial Intelligence, Nanjing University. I am also a member of LAMDA Group led by Prof. Zhi-Hua Zhou, where I work with Prof. Yu-Feng Li.
Currently, I work as a research intern at MMLab@The Chinese University of Hong Kong with Prof. Xiangyu Yue.
*NEW* I am an incoming MSR student at Carnegie Mellon University, Robotics Institute, and I am currently seeking a research position. If you are interested in my work or have opportunities for collaboration, please feel free to contact me via email.

My research interests mainly include Artificial Intelligence and Robotics. Specifically, I am interested in Multimodal Learning, Computer Vision and Embodied AI. I am passionate about developing intelligent system with capabilities across multiple dimensions.

• Multimodal Learning: Bridging the gap between different modalities, such as vision, language, audio.
• Computer Vision: Enhancing models' ability to perceive, understand, and interpret visual data.
• Embodied AI: Developing an intelligent system with perception, reasoning, and action capabilities to solve real-world tasks.

• [2025.2] I have been admitted to the Robotics Institute at Carnegie Mellon University!🎉🎓
• [2025.2] RAP is accepted by CVPR 2025.
• [2024.11] ABIL is accepted by KDD 2025.
• [2024.10] Awarded BYD Scholarship (Ranked 2/102 in my grade).
• [2024.6] I'm glad to participate in LAMDA & RIKEN-AIP Joint Workshop on Machine Learning.
• [2024.5] Give an oral presentation at Robust Machine Learning in Open Environments Workshop at PAKDD 2024. [Slides]
• [2023.12] Awarded National Scholarship (Ranked 1/102 in my grade).

Multimodal Long Video Modeling Based on Temporal Dynamic Context
Preprint
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
Jiejing Shao*, Haoran Hao*, Xiaowen Yang, Yufeng Li
Paper | Project | Code