Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Density estimation with LLMs: a geometric investigation of in-context learning trajectories
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-511
LLaMA-2, Gemma, and Mistral all perform in-context density estimation via an adaptive kernel-like process, as revealed by their similar low-dimensional INPCA trajectories bounded between the geodesic and the Gaussian submanifold