Chenfei Liao

MPhil Student
AI Thrust, Information Hub,
the Hong Kong University of Science and Technology (Guangzhou)

No.1 Du Xue Rd, Nansha District, Guangzhou

cliao127@connect.hkust-gz.edu.cn

About Me

I am a 1st-year MPhil student in AI Thrust at the Hong Kong University of Science and Technology, Guangzhou under the supervision of Prof. Xuming HU @ HKUST(GZ), Prof. Li CHEN @ HKUST(GZ) and Prof. Yangqiu SONG @ HKUST. I completed my undergraduate studies at the China University of Mining and Technology, Beijing with the supervision of Prof. Kehu YANG @ CUMTB. Currently, I work closely with Xu ZHENG @ HKUST(GZ) & INSAIT, Jiawen WANG @ CUMTB, Prof. Linfeng ZHANG @ SJTU, and Prof. Kailun YANG @ HNU.

Education

MPhil in Artificial Intelligence, the Hong Kong University of Science and Technology, Guangzhou (2024 - 2026)
Bachelor in Information Engineering, the China University of Mining and Technology, Beijing (2020 - 2024)

Research Interests

Multi-modal Large Language Model: balanced MLLM, efficient MLLM
Multi-modal Perception: multi-modal semantic segmentation, multi-modal robustness
Underground Mine Perception: semantic segmentation, object detection, key point detection

Awards

[2024.10] Outstanding Bachelor’s Thesis in Beijing, China
[2021.09] National Scholarship of China

Services

Reviewer of: @CVPRWorkshop (TMM-OpenWorld) 2025, @Journal of Breath Research

News

[2025.04] Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness has been accepted by the CVPRWorkshop (TMM-OpenWorld) 2025 as an oral presentation paper (top 6 papers)!
[2024.12] UMSSS: A Visual Scene Semantic Segmentation Dataset for Underground Mines has been accepted by the ICASSP 2025!
[2024.12] An Efficient Large Kernel Convolution Network Designed for Neural Processing Unit has been accepted by the Engineering Applications of Artificial Intelligence!
[2024.10] My Bachelor Thesis has won the Outstanding Bachelor’s Thesis in Beijing, China!

Publications and Projects

CVPRW 2025 (Oral)

Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness

Chenfei Liao*, Kaiyu Lei*, Xu Zheng, Junha Moon, Zhixiong Wang, Yixuan Wang, Danda Pani Paudel, Luc Van Gool, Xuming Hu

CVPR Workshop 2025: TMM-OpenWorld, Jun. 2025.

PDF GitHub
ICASSP 2025

UMSSS: A Visual Scene Semantic Segmentation Dataset for Underground Mines

Jiawen Wang, Chenfei Liao, Zhongqi Zhao, Lianghui Li, Xuan Gao, Suna Pan, Fangzhen Shi, Yudong Wang, Weijie Zhou, Kehu Yang

ICASSP 2025, Apr. 2025.

PDF Project Page
EAAI

An Efficient Large Kernel Convolution Network Designed for Neural Processing Unit

Jiawen Wang, Chenfei Liao, Dewei Li, Zhongqi Zhao, Jingchuan Chen, Kehu Yang

Engineering Applications of Artificial Intelligence, Feb. 2025.

PDF
ArXiv 2025

MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation

Chenfei Liao, Xu Zheng, Yuanhuiyi Lyu, Haiwei Xue, Yihong Cao, Jiawen Wang, Kailun Yang, Xuming Hu

ArXiv, Mar. 2025.

PDF GitHub
ArXiv 2025

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation

Ding Zhong*, Xu Zheng*, Chenfei Liao, Yuanhuiyi Lyu, Jialei Chen, Shengyang Wu, Linfeng Zhang, Xuming Hu

ArXiv, Mar. 2025.

PDF