Tag
An open-source end-to-end machine learning platform for edge devices (MCUs) that simplifies data labeling and deployment, featuring an auto-labeler for time-series sensor data and a chatbot for data insights.
This paper introduces Minor Component Unlearning (MCU), a novel approach to LLM unlearning that targets minor components in representations to resist relearning attacks. It addresses the vulnerability of existing methods by focusing on robust directions within the model's spectral structure.