3 papers
cs.CV2026
Lethe: How Hard Is It to Forget? A Benchmark for Federated Unlearning in Medical Imaging
Shengchao Chen, Ting Shu
Federated learning enables medical-imaging models to be trained across hospitals, and privacy law, most explicitly the GDPR ``right to be forgotten'', turns removing a hospital's,…
cs.CV2026
FM: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imaging
Shengchao Chen, Ting Shu
Building foundation models for medical imaging requires pooling data across institutions, yet privacy regulations prohibit centralized aggregation. Existing Federated Foundation Mo…
cs.CL2026
Learning Design Skills as Memory Policies for Agentic Photonic Inverse Design
Shengchao Chen, Ting Shu, Sufen Ren
Photonic crystal fiber (PCF) inverse design remains challenging because candidate geometries must satisfy coupled optical targets under expensive electromagnetic simulation. Existi…