gradient-free methods 1in-context learning 1multimodal retrieval 1on-device inference 1task-conditioned retrieval 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning
Xinyu Luo, Hui Liu, Yihua Shao +3
The paper introduces Conditional Retrieval Alignment (CoRA), a gradient‑free method that turns a frozen encoder into a task‑conditioned retriever for on‑device in‑context learning,…
cs.LG2026
Efficient Test-Time Adaptation through Latent Subspace Coefficients Search
Xinyu Luo, Jie Liu, Kecheng Chen +4
Real-world deployment often exposes models to distribution shifts, making test-time adaptation (TTA) critical for robustness. Yet most TTA methods are unfriendly to edge deployment…