Ke Wang
k.wang@epfl.ch
Hi! 👋
I am a PhD student at at EPFL 🇨🇭 (Swiss Federal Institute of Technology in Lausanne), under the supervision of Prof. Pascal Frossard.
My research interests are centered around model post-training topics such as model merging, model editing, and model fine-tuning. You can check out my research from my Scholar page.
Before starting my PhD, I completed my MSc from EPFL, and my BSc from University of Electronic Science and Technology of China.
During my study, I was also an intern in Oracle Labs and Google Deepmind.
I am from Chengdu, Sichuan in Southwest China (hometown to the pandas 🐼). In my free time, I like football ⚽️, spicy food 🌶️, hiking 🏔️ and skiing 🎿.
selected publications
-
-
MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMsIn NeurIPS , 2025 - LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model MergingIn International Conference on Learning Representations (ICLR) , 2025
- Localizing Task Information for Improved Model Merging and CompressionIn International Conference on Machine Learning (ICML) , 2024
- Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy LabelsIn International Conference on Machine Learning (ICML) , 2024