Skip to content
conftrace_

multi-head softmax attention

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

anisotropic covariates (1) gradient descent predictor (1) bayesian optimality (1) linear regression (1) in-context learning (1)

Papers

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention ICML 2025