🔘 Open Research Position: Machine Unlearning × Model Quantization
We are looking for motivated students to join a research project exploring the intersection of machine unlearning and neural network quantization.
🔍 Project Description
Machine unlearning aims to remove the influence of specific training data or learned concepts from a trained model without retraining it from scratch. At the same time, quantization is widely used to compress neural networks and enable efficient deployment.
This project investigates the interaction between unlearning and quantization, including questions such as whether quantization can weaken, reverse, or otherwise affect the effectiveness of unlearning methods, and how unlearning techniques can be designed to remain robust under low-precision deployment.
The project is motivated by recent work including:
📄 Catastrophic Failure of LLM Unlearning via Quantization
https://arxiv.org/abs/2410.16454
📄 RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models
http://arxiv.org/abs/2603.14819
🔹 Requirements
Strong Python programming skills
Solid understanding of deep learning
Hands-on experience with PyTorch
Familiarity with model quantization and/or machine unlearning
Ability to read, understand, and implement ideas from recent research papers
Experience with LLMs, Vision Transformers, diffusion models, or model compression is a plus.
📌 How to Apply
If you are interested, send your CV to @kp_gfe on Telegram.