Iris Li

Jia Li (Iris)

I work as an algorithm engineer in JD.com, Inc. Before that, I graduated as a master student at Institute of Information Engineering [IIE], University of Chinese Academy of Sciences [UCAS]. I completed my B.E. in CS from [WHUT] (2017-2021). Also I had a great experience of one year as a remote intern in PRADA Lab with Professor Wang and Lijie Hu (2023-2024).

My research interests lie around AIGC and AI application in our real world. I am deeply motivated to explore how AI technology can be developed and deployed in a safe way to align with human values.

Additionally, I love game programming.

Email / Github / ZhiHu

Research

	Tackling Noisy Clients in Federated Learning with End-to-end Label Correction Xuefeng Jiang, Sheng Sun, Jia Li, Jingjing Xue, Runhan Li, Zhiyuan Wu, Gang Xu, Yuwei Wang and Min Liu ACM CIKM 2024 To refine the noisy labels of noisy clients via an end-to-end Optimization framework in the scenario of distributed learning.
	Text Guided Image Editing with Automatic Concept Locating and Forgetting Jia Li, Lijie Hu, Zhixian He, Jingfeng Zhang, Tianhang Zheng and Di Wang Arxiv In our paper, we propose a novl method called Locate and Forget (LaF), which effectively locates potential target concepts in the image for modification by comparing the syntactic trees of the target prompt and scene descriptions in the input image, intending to forget their existence clues in the generated image.
	Fair Text-to-image Diffusion via Fair Mapping Jia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng, Hua Zhang and Di Wang Arxiv In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions. To overcome this challenge, we propose Fair Mapping, a general, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image model by controlling the prompt to achieve fair image generation.
	SA-SVD: Mitigating Bias in Face Recognition by Fair Representation Learning Jia Li, Hua Zhang IEEE CSCWD 2024 In this paper, to enhance the representation space utilization and reduce disparities among different demographic groups, we introduce SA-SVD, a regularization method orthogonal to existing face recognition methods. It has potential to capture the intricate patterns and subtle differences in face features across individuals within certain demographic groups.
	Improve Fairness In Face Recognition via Causal Inference Jia Li, Hua Zhang Under Reviewed In this paper, we conduct an exploration of homogeneity bias in face recognition by structual causal model and propose a novel fairness model learning method via causal intervention for face recognition. Specifically, we use four different metrics to evalutate our results.

Experience

	University of Chinese Academy of Sciences M.S., Computer Vision, Current GPA: 3.77/4.0.
	King Abdullah University of Science & Technology Remote Intern
	Wuhan University of Technology B.S., Computer Science and Technology, Current GPA: 4.0/4.0.

Non-academic

I also have a fever in game programming.

乾陵为囚（Imprisoned in Qianling）

I'm the lead programmer for this project. It tells a story about a maid(player)'s journey to unravel the mystery of the tomb's occupant.

relative tags: #Ancient;#History;#2d;#Puzzle;#Plot

Ship Cockpit Monitoring System Based on Deep Vision

We use the movements data from ship monitor including the position information data rather than video in a more lightweight way to recreat the crew action in virtual 3d cockpit software.

thanks for the web template.