Junyi Zhu (朱俊屹)
Senior researcher at Samsung Electronics R&D Institute UK (SRUK). Focusing on advanced AI research..
I’m currently working at SRUK with a focus on advanced AI research. I’ve done my PhD studies at KU Leuven in the Processing Speech and Images Center under the guidance of Prof. Matthew Blaschko, and I’m about to complete the PhD defense in November, 2024. With great passion and inexhaustible curiosty for AI technologies, I have contribued to many domains, including image generative models, large language models, distributed learning and privacy-preserving machine learning. Engaging in AI research brings me immense joy, and I strive to utilize this technology to enhance industry or our daily lives. I look forward to the day when AGI becomes a reality.
Before my PhD, I earned my Master’s degree from the Karlsruhe Institute of Technology in Germany, specializing in information technologies and vehicle engineering. During my Master’s program, I worked on several research projects addressing autonomous driving problems using AI at the Institute of Measurement and Control Systems and the Research Center for Information Technology in Karlsruhe.
If you are interested in research collaboration, feel free to reach out!😊
news
Sep 16, 2024 | I’m exited to be joining Samsung Research UK! |
---|---|
Jun 01, 2024 | My dissertation is complete, and I’m looking forward to the defence! |
May 07, 2024 | I gave an oral presentation at ICLR for our work accepted in the Tiny Paper Track. |
Feb 25, 2024 | I’m working on an external collaboration with Institute for Advanced Algorithms Research in Shanghai. |
Nov 27, 2023 | I gave a talk on Leuven.AI Juniors Day. |
Oct 02, 2023 | I’m working on an external collaboration with Infinigence-AI. |
Aug 10, 2023 | I’m visiting NICS-EFC lab at Tsinghua University for two months. |
selected publications
- EMNLP Findings
- CVPRConfidence-aware Personalized Federated Learning via Variational Expectation Maximization2023* = equal contribution
- ICMLSurrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning2023
- arXivLinear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better2024* = equal contribution
- TMLRImplicit Neural Representations for Robust Joint Sparse-View CT Reconstruction2024* = equal contribution