Pith. sign in

Fine-tuning llms with singular value decomposition

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Transformer-Squared: Self-adaptive LLMs

cs.LG · 2025-01-09 · conditional · novelty 6.0

Transformer-Squared selectively rescales singular values of an LLM's weights with RL-trained expert vectors, then mixes these experts at inference to adapt to unseen tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Transformer-Squared: Self-adaptive LLMs cs.LG · 2025-01-09 · conditional · none · ref 6

    Transformer-Squared selectively rescales singular values of an LLM's weights with RL-trained expert vectors, then mixes these experts at inference to adapt to unseen tasks.