Steer2Adapt: data-efficient inference-time LLM adaptation by composing steering vectors via Bayesian optimization over a semantic prior subspace.
-
Updated
Jun 30, 2026 - Python
Steer2Adapt: data-efficient inference-time LLM adaptation by composing steering vectors via Bayesian optimization over a semantic prior subspace.
Master's thesis repository
Add a description, image, and links to the llm-adaptation topic page so that developers can more easily learn about it.
To associate your repository with the llm-adaptation topic, visit your repo's landing page and select "manage topics."