pith. sign in

Training dynamics of multi-head softmax attention for in-context learning: Emergence, convergence, and optimality

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

Learning to Adapt: In-Context Learning Beyond Stationarity

cs.LG · 2026-04-13 · unverdicted · novelty 6.0

Gated linear attention enables lower training and test errors in non-stationary in-context learning by adaptively modulating past inputs through a learnable recency bias under an autoregressive model of task evolution.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • Agentic Transformers Provably Learn to Search via Reinforcement Learning cs.LG · 2026-05-29 · unverdicted · none · ref 45

    In a stochastic k-ary tree, a two-head transformer learns randomized DFS via policy gradient under depth-wise curriculum, generalizes to deeper trees, and adapts to imbalanced goals via discounting.

  • Learning to Adapt: In-Context Learning Beyond Stationarity cs.LG · 2026-04-13 · unverdicted · none · ref 11

    Gated linear attention enables lower training and test errors in non-stationary in-context learning by adaptively modulating past inputs through a learnable recency bias under an autoregressive model of task evolution.