ArXiv TLDR

Jun Huang

2 papers · Latest:

EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure

EASE is a new framework for federated multimodal unlearning, effectively removing forgotten data by addressing cross-modal and subspace entanglement.

2605.00733
Machine Learning

Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems

A lifecycle-aware FCL framework for mobile autonomous systems uses dual-timescale strategies to prevent immediate forgetting and recover from long-term drift.

2604.20745

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.