3 papers
cs.CL2026
CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion
Zheling Tan, Jin Gao, Dequan Wang
As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant evidence through a bounded mem…
cs.CV2026
LU-500: A Logo Benchmark for Concept Unlearning
Keyu Li, Jin Gao, Jialing Zhang +1
Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations, however, mostly study target…
cs.LG2025
MedForge: Building Medical Foundation Models Like Open Source Software Development
Zheling Tan, Kexin Ding, Jin Gao +4
Foundational models (FMs) have made significant strides in the healthcare domain. Yet the data silo challenge and privacy concern remain in healthcare systems, hindering safe medic…