Xudong Yan | Beijing Jiaotong University

About Me

👋Hi there! This is Xudong Yan (闫旭东). I am currently a Ph.D. student at Beijing Jiaotong University, supervised by Prof. Songhe Feng. Before transferring to the doctoral program, I pursued my master’s studies at BJTU. Prior to that, I received my B.Eng. degree from Qingdao University.

My research interests focus on the application of vision-language models (VLM) in the real world, including their use in zero-shot and few-shot learning, multimodal retrieval, and test-time adaptation. If you are interested in our works or would like to explore potential collaboration, please feel very free to contact me via Email or WeChat🙌.

Research Interests

Computer Vision: compositional zero-shot learning, few-shot learning, composed image retrieval, test-time adaptation of VLMs.

News

[Oct. 2026] Our paper about multimodal information extraction is submitted to WWW.
[Oct. 2026] Our paper about compositional zero-shot learning is accepted to IJCV!
[Jun. 2026] Our paper about compositional zero-shot learning is submitted to IEEE TIP.
[Jun. 2026] I am honored to receive the international exchange fellowship from BJTU. I will be visiting the University of Trento (Sept. – Nov. 2026), working under the supervision of Prof. Massimiliano Mancini.
[May. 2026] Our paper about few-shot class-incremental learning is accepted to Neural Network!
[Feb. 2026] Our paper about compositional zero-shot learning is accepted to CVPR 2026!
[Sep. 2025] Our paper about compositional zero-shot learning is accepted to NeurIPS 2025!
[Apr. 2025] Our paper about compositional zero-shot learning is accepted to IJCAI 2025!

Publications

IJCV

WARM-CAT: Warm-Started Test-Time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning

Xudong Yan, Jiaxin Wang, Xin Su, Songhe Feng*.

International Journal of Computer Vision, 2026.

NeurIPS

TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning

Xudong Yan, Songhe Feng*.

Conference on Neural Information Processing Systems (NeurIPS), 2025.

Paper arXiv Code

IJCAI

Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning

Xudong Yan, Songhe Feng*, Yang Zhang, Jian Yang, Yueguan Lin, Haojun Fei.

International Joint Conference on Artificial Intelligence (IJCAI), 2025.

Paper arXiv Code

CVPR

Bridging the Modality Gap in Compositional Zero-Shot Learning via Sparse Alignment and Unimodal Memory Bank

Yang Zhang, Zhixiang Chi, Xudong Yan, Yang Wang, Songhe Feng*.

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2026.

Paper

NN

Learning forward-compatible and domain-invariant representations for cross-domain few-shot class-incremental learning

Weidong Shi, Xudong Yan, Jiajun Yuan, Hong Lu, Songhe Feng*.

Neural Networks (NN), October 2026.

Paper

Services

Conference Reviewers

Experience

[Sep. 2025 - Now] Ph.D Student, Beijing Jiaotong University, supervised by Prof. Songhe Feng
[Sep. 2023 - Jun. 2025] Graduate Student, Beijing Jiaotong University, supervised by Prof. Songhe Feng
[Sep. 2019 - Jun. 2023] B.E. in Software Engineering, Qingdao University, supervised by Prof.Peijian Zhang.

Teaching

[Fall 2025] Teaching Assistant, C Programming.
[Fall 2024] Teaching Assistant, C Programming.

Honors and Awards

[Jun. 2023] Excellent Graduate of Shandong Province, Government of Shandong province.
[Jul. 2025] Graduate Student Innovation Project of the Fundamental Research Funds for the Central Universities.
[Jun. 2026] Global Research Scholarship for Outstanding Students, Beijing Jiaotong University. Selected to be the visiting Ph.D at the University of Trento (Sept. – Nov. 2026) under the supervision of Prof. Massimiliano Mancini.