PLUME

Researchers propose PLUME (Personalized Low-Rank Adaptation through User Modulation and Shared Subspace), a lightweight framework for personalizing large language models (LLMs) that reduces per-user p…

Researchers propose ReLoop-UME, a universal multimodal embedding model that recurrently reuses a parameter-shared retrieval-forming block with Learnable Retrieval Registers, improving retrieval on MME…