News
JUL 2026
One paper is accepted by TPAMI
JUN 2026
One paper is accepted by ECCV
MAY 2026
One paper is accepted by ICML
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
Email: oceanhao@ustc.edu
|
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. AI research works often 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.
In the Year of 2025:
In the Year of 2024:
Image captured at Yamdrok Lake, Tibet, China
Image captured at IROS2025, HangZhou, China
Image captured at Qaidam Basin, Qinghai, China
Publication
In the Year of 2026: |
LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning
Haihong Hao, Lei Chen, Mingfei Han, Changlin Li, Dong An, Yuqiang Yang, Zhihui Li, Xiaojun Chang
ECCV 2026 projectpage: https://abdd.top/latentpilot/ |
|
GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning
Ruiheng Liu, Haihong Hao, Mingfei Han, Xin Gu, Kecheng Zhang, Changlin Li, Xiaojun Chang
ICML 2026 |
|
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 |
|
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 |
|
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 |
|
|
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 · |
|
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 |
|
CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
Haihong Hao, Mingfei Han, Changlin Li, Zhihui Li, Xiaojun Chang TPAMI |
|
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 |
|
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
| Algorithm Development @ HONOR New Industry Incubation Dept., Humanoid Robot Mobile Manipulation, JUN 2026 - Present |
| Research @ Chery HuiYin Motor Finance Service Co.,Ltd, Dec 2022 - Apr 2024 |
Webpage template borrows from Prof. Xiangnan He.