2 papers
cs.CL2026
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
Jihoon Kwon, Jiwon Choi, Jy-yong Sohn
In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks through demonstrations, yet it suffers from escalating inference costs as context length increas…
cs.LG2026
Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
Juil Koo, Mingue Park, Jiwon Choi +2
We propose Drifting Field Policy (DFP), a non-ODE one-step generative policy built on the drifting model paradigm. We frame the policy update as a reverse-KL Wasserstein-2 gradient…