pith. sign in

Dynamic rank adjustment for accurate and efficient neural network training.arXiv preprint arXiv:2508.08625, 2025

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

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Efficient Pre-Training of LLMs through Truncated SVD Layers

cs.LG · 2026-05-27 · unverdicted · novelty 5.0

TSVD framework maintains low-rank orthonormal weights during LLM pretraining via truncated SVD, adaptive spectral rank selection, and caching to reduce compute while matching baseline performance.

citing papers explorer

Showing 1 of 1 citing paper.

  • Efficient Pre-Training of LLMs through Truncated SVD Layers cs.LG · 2026-05-27 · unverdicted · none · ref 35

    TSVD framework maintains low-rank orthonormal weights during LLM pretraining via truncated SVD, adaptive spectral rank selection, and caching to reduce compute while matching baseline performance.