Xiuying Wang

BSc Engineering · AI Research

Xiuying Wang

王修荧

Profile

About

Xiuying Wang

I am currently pursuing a Bachelor of Science (Engineering) at Queen Mary University of London and Beijing University of Posts and Telecommunications.

I have been fortunate to receive kind and valuable guidance from Yichen Li and Dr. Jingkang Yang. With Yichen, I work on federated learning and continual learning. With Dr. Yang, I explore egocentric AI and multimodal learning.

I also had a valuable time at Synvo.ai, building VLM-powered agent systems for real-world retail scenarios, and I am currently working with Action Intelligence on scalable egocentric data collection for embodied AI.

My research lies in Multimodality, Egocentric AI, Agentic Memory, Federated Learning, and Continual Learning. Feel free to reach out for collaborations, questions, or just to chat.

Updates

News

Started as a Research Engineer Intern at Action Intelligence, working on scalable egocentric data collection for embodied AI.

Lightweight Federated Incremental Learning via Decoupled Replay, my first paper as first author, was accepted to ICML 2026. Grateful to Yichen Li for his guidance.

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning was accepted to IEEE TPAMI.

Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning, my first paper, was accepted to NeurIPS 2025. Grateful to Yichen Li for his guidance.

Started as a Research Engineer Intern at Synvo.ai, working on VLM-powered agent systems for retail scenarios.

View older news Hide older news

Began working with Dr. Jingkang Yang on egocentric AI.

Began working with Yichen Li on federated learning research.

Selected Work

Publications

Lightweight federated incremental learning thumbnail

Lightweight Federated Incremental Learning via Decoupled Replay.

Xiuying Wang, Yichen Li, Hang Su, Gaozhuo Liu, Shiwei Li, Chuang Zhao, Jiangming Shi, Imran Razzak

ICML 2026
Long egocentric video reasoning thumbnail

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning.

S. Tian, R. Wang, H. Guo, P. Wu, Y. Dong, Xiuying Wang, Jingkang Yang, Hao Zhang, Hongyuan Zhu, Ziwei Liu

TPAMI
Feature distillation federated learning thumbnail

Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning.

Yichen Li, Xiuying Wang, Wenchao Xu, Haozhao Wang, Yining Qi, Jiahua Dong, Ruixuan Li

NeurIPS 2025

Global Reach

Visitors

A live view of where visitors to this website come from.

Get in Touch

Contact

For collaborations, research discussions, or just to say hello, feel free to reach out.

WeChat WANGXYwsx