News


MAR 2026
One paper is accepted by TPAMI

MAR 2026
One paper is accepted by ICLR

Oct 2025
We are the Champion of VLN-PE in InternUtopia and Real World Challenge, IROS 2025

Jan 2025
One paper is accepted by International Journal of Machine Learning and Cybernetics

Haihong Hao 

PhD student

School of Information Science and Techonology
University of Science and Technology of China

Email: oceanhao@ustc.edu

Google Scholar

I am a PhD student at the USTC, Future Media Computing Laboratory, supervised by Prof. Xiaojun Chang and my senior brother Mingfei Han. Before that, I was advised by Prof. Xiangnan He in School of Data Science in USTC. My research interest lies in Vision-language navigation (VLN), 3D Large Language Models (3D-LLMs) and Multimodal-Large-Language-Models(MLLM). I am working hard to become an excellent researcher. If you have any good ideas or cooperation, please don't hesitate to contact me.

I love coding, and I feel really happy when I get lost in it and solve the bugs I come across. In some ways, I might be more suited to being an engineer than a researcher. Also, it really annoys me when I see a lot of research projects saying "code will be coming soon," but they never actually release it. I guess that's how AI research works—it's more about having a "good story" than actually "getting a task done." I'm working hard to make sure my work does both: tells a good story and gets the job done. I also used to be into photography and I'm a League of Legends (LOL) mobile player, ranked at the highest level, King. I bought this domain, "abdd.top" in 2022 because I thought it was fun and cool.

Publication


In the Year of 2026:


pdf
GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning Ruiheng Liu, Haihong Hao, Mingfei Han, Xin Gu, Kecheng Zhang, Changlin Li, Xiaojun Chang
arxiv   

pdf
Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos Mingfei Han, Haihong Hao, Liang Ma, Kamila Zhumakhanova, Ekaterina Radionova, Jingyi Zhang, Xiaojun Chang, Xiaodan Liang, Ivan Laptev
arxiv   

pdf
SELongVLM: Empowering Long Video Language Models with Self-Corrective Clip Selection Kecheng Zhang, Zongxin Yang, Mingfei Han, Yunzhi Zhuge, Haihong Hao, Changlin Li, Zhihui Li, Xiaojun Chang
TPAMI   

pdf
Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions Kecheng Zhang, Zongxin Yang, Mingfei Han, Haihong Hao, Yunzhi Zhuge, Changlin Li, Zhihui Li, Xiaojun Chang
ICLR   
In the Year of 2025:

pdf
pdf
Champion of VLN-PE in InternUtopia and Real World Challenge, IROS 2025
[VLN-PE Certificate]

Haihong Hao, Mingfei Han,Yi Xiang,Wei Ji,Xiaojun Chang
IROS 2025  · 

pdf
Self-Consistency as a Free Lunch: Reducing Hallucinations in Vision-Language Models via Self-Reflection
Mingfei Han, Haihong Hao, Jinxing Zhou, Zhihui Li, Yuhui Zheng, Xueqing Deng, Linjie Yang, Xiaojun Chang
arxiv   

pdf
CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
Haihong Hao, Mingfei Han, Changlin Li, Zhihui Li, Xiaojun Chang
arxiv   

pdf
Attribute encoding transformer on unattributed dynamic graphs for anomaly detection
Shang Wang, Haihong Hao, Yuan Gao, Xiang Wang, Xiangnan He
International Journal of Machine Learning and Cybernetics   
In the Year of 2024:


pdf
Hierarchical Space-Time Attention for Micro-Expression Recognition
Haihong Hao, Shuo Wang, Huixia Ben, Yanbin Hao, Yansong Wang, Weiwei Wang
arxiv   

Education

University of Science and Techonology of China (USTC)
PhD student in Computer Science                   Sep 2024 - Now, Hefei
Advisor: Prof. Xiaojun Chang and Mingfei Han
University of Science and Techonology of China (USTC)
Master in Computer Science      Sep 2022 - June 2024, Hefei
Advisor: Prof. Xiangnan He
Zhengzhou University (ZZU)
Bachelor in Computer Science      Sep 2018 - June 2022, Zhengzhou

Honors and Awards

2025, Champion of VLN-PE in InternUtopia and Real World Challenge, IROS 2025 ($11,500(80000¥))
2025,China Scholarship Council (CSC) Scholarship ($2,000(14000¥)/month*24)
2020,National Encouragement scholarship, China (¥10,000)

Skills

Programming: Python, MATLAB, C/C++, PyTorch, Embedded System
Embodied AI: Data preparation, Model training and evaluation, Sim2Real Transfer
Hardware Experience: Unitree G1, Unitree Go2, AgileX LIMO, Turtlebot4, Franka, UR, Mobile Manipulator

Experiences

Research @ Chery HuiYin Motor Finance Service Co.,Ltd, Dec 2022 - Apr 2024




Image captured at Yamdrok Lake, Tibet, China
Image captured at IROS2025, HangZhou, China
Image captured at Qaidam Basin, Qinghai, China




Webpage template borrows from Prof. Xiangnan He.