Chenfei Liao
I am an M.Phil. student in the Red Bird Program (Artificial Intelligence) at the Hong Kong University of Science and Technology (Guangzhou), supervised by Prof. Xuming Hu and Prof. Yangqiu Song. I am currently a remote research intern at KAUST with Prof. Mohamed Elhoseiny.
My research focuses on the panoramic world, exploring the potential of panoramas as a new bridge towards real embodied intelligence and world models. I also work on robust multi-modal perception and efficient MLLMs. I work closely with Prof. Xu Zheng (GBU), Prof. Linfeng Zhang (SJTU), and Prof. Nicu Sebe (UniTrento).
I am looking for a PhD position starting in 2027.
Find me on Google Scholar GitHub LinkedIn Email CV
What's New?
- [Experience] Jul 2026
Started a remote research internship at KAUST with Prof. Mohamed Elhoseiny.
- [Award] 2026
Received the Lizhi Innovative Talent Scholarship (Top 3 in HKUST(GZ)).
Selected Publications
C = Conference, P = Preprint, T = Technical Report, * = Equal Contribution, † = Project Lead
[C.1] Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu , "Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods," in ACL Main, 2026. [paper]
[C.2] Zixin Zhang*, Chenfei Liao*, Hongfei Zhang, Harold Haodong Chen, Kanghao Chen, Zichen Wen, Litao Guo, Bin Ren, Xu Zheng, Yinchuan Li, Xuming Hu, Nicu Sebe, Ying-Cong Chen , "Panoramic Affordance Prediction," in ECCV, 2026. [paper]
[C.3] Haocong He*, Chenfei Liao*†, Zichen Wen, Zihao Dongfang, Xu Zheng, Bin Ren, Chang Su, Zixin Zhang, Harold Haodong Chen, Hongfei Zhang, Weijia Li, Kailun Yang, Conghui He, Xuming Hu, Nicu Sebe, Linfeng Zhang , "OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning," in ECCV, 2026. [paper] [data]
[C.4] Chenfei Liao*†, Kaiyu Lei*, Xu Zheng, Junha Moon, Zhixiong Wang, Yixuan Wang, Danda Pani Paudel, Luc Van Gool, Xuming Hu , "Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness," in CVPR Workshop: TMM-OpenWorld, 2025. [Best Paper Award][Oral] [paper]
[C.5] Hongfei Zhang*, Harold Haodong Chen*, Chenfei Liao*, Jing He*, Zixin Zhang, Haodong Li, Yihao Liang, Kanghao Chen, Bin Ren, Xu Zheng, Shuai Yang, Kun Zhou, Yinchuan Li, Nicu Sebe, Ying-Cong Chen , "DVD: Deterministic Video Depth Estimation with Generative Priors," in ICML Workshop: Foundations of Deep Generative Models, 2026. [Spotlight][300+ GitHub Stars] [paper]
[C.6] Xu Zheng*, Chenfei Liao*, Yuqian Fu, Kaiyu Lei, Yuanhuiyi Lyu, Lutao Jiang, Bin Ren, Jialei Chen, Jiawen Wang, Chengxin Li, Linfeng Zhang, Danda Pani Paudel, Xuanjing Huang, Yu-Gang Jiang, Nicu Sebe, Dacheng Tao, Luc Van Gool, Xuming Hu , "MLLMs are Deeply Affected by Modality Bias," in ICLR Workshop: MM-Intelligence, 2026. [paper]
[P.1] Chenfei Liao, Xu Zheng, Yuanhuiyi Lyu, Haiwei Xue, Yihong Cao, Jiawen Wang, Kailun Yang, Xuming Hu , "MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation," in arXiv, 2025. [paper]
[T.1] Zichen Wen*, Yiyu Wang*, Chenfei Liao*, Boxue Yang*, Junxian Li*, Weifeng Liu*, Haocong He, Bolong Feng, Xuyang Liu, Yuanhuiyi Lyu, Xu Zheng, Xuming Hu, Linfeng Zhang , "AI for Service: Proactive Assistance with AI Glasses," in Technical Report, 2025. [paper]
Education
- The Hong Kong University of Science and Technology (Guangzhou) Sep. 2024 – Oct. 2026M.Phil. in Red Bird Program (Artificial Intelligence), supervised by Prof. Xuming Hu & Prof. Yangqiu Song Guangzhou, China· Lizhi Innovative Talent Scholarship (Top 3 in HKUST(GZ))
- China University of Mining and Technology (Beijing) Sep. 2020 – Jun. 2024B.S. in Information Engineering, supervised by Prof. Kehu Yang Beijing, China· GPA: 3.83/4.00, National Scholarship of China (Top 1%)
Experience
- King Abdullah University of Science and Technology Jul. 2026 – PresentResearch Intern, advised by Prof. Mohamed Elhoseiny Remote
- Shanghai Jiao Tong University Jun. 2025 – Sep. 2025Research Intern, advised by Prof. Linfeng Zhang Shanghai, China
Awards
- 2026 Lizhi Innovative Talent Scholarship (Top 3 in HKUST(GZ))
- 2024 Outstanding Bachelor's Thesis in Beijing, China
- 2021 National Scholarship of China (Top 1%)
Academic Services
- CVPR Workshop (TMM-OpenWorld) 2025
- ICCV Workshop (MIRA) 2025
- ICASSP 2026
- ICME 2026
- ICLR Workshop (MM-Intelligence) 2026
- IJCNN 2027
- ICASSP 2027
- ACL Rolling Review (ARR) October 2026
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Image Processing (TIP)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- IEEE Transactions on Robot Learning (T-RL)