Jiayi Shen (沈佳怡)

I am a final year ELLIS PhD candidate at MultiX Lab, University of Amsterdam. I am grateful to be supervised by Prof. Dr. Marcel Worring and Dr. Nanne van Noord. I also received valuable guidance from Dr. Xiantong Zhen. Prior to that, I obtained my Master's and Bachelor's degrees from Beihang University.

I am currently looking for two master students from UvA to explore some interesting research topics about multi-task learning with me. Feel free to drop your resume to my email.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

[Sep. 2023] One paper was accepted by NeurIPS 2023 as spotlight ⭐!

[June 2023] One paper was accepted by CoLLAs, 2023.

[April 2023] I will attend the ICVSS2023, hosted in Punta Sampieri - Scicli (Ragusa), Sicily 9-15 July 2023.

[April 2023] I am a reviewer of ICCV2023 and Neurips2023.

[March 2023] I just finished my 36-month evaluation.

[March 2023] One paper was accepted by CVPR 2023.

I'm interested in Machine Learning, Bayesian Models, and Meta-Learning. Much of my research is to address challenging problems in multi-task learning.

This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training set-up.

We propose SuperDisco to discover super-class representations for long-tailed recognition using a graph model.

We propose a new MTL setting which suffers from category shifts from training to test data.

We propose a Neighbor Transformer Network, or NFormer, which explicitly models interactions across all input images.

We propose variational multi-task learning (VMTL), a general probabilistic inference framework for learning multiple related tasks.

To better explore domain invariant learning, we introduce weight uncertainty to the model by leveraging variational Bayesian inference.