Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Axis-LoRA: Probing and Adapting Embedding Models for Personal-Memory Retrieval
Dohoon Kim, Junho Park, Hyunwoong Bae +2
As LLMs are increasingly asked questions about a user's personal experiences, retrieval must distinguish memories by time, place, person, and event. Current personal-memory pipelin…
cs.CL2026
PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation
Junho Park, Dohoon Kim, Taesup Moon
Large language model (LLM) personalization aims to adapt general-purpose models to individual users. Most existing methods, however, are developed under data-rich and resource-abun…