pith. sign in

Crown, frame, reverse: Layer-wise scaling variants for llm pre-training

Andrei Baroian, Kasper Notebomer · 2025 · arXiv 2509.06518

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

2 Pith papers citing it
read on arXiv browse 2 citing papers

fields

cs.CL 1 cs.LG 1

years

2026 2

verdicts

CONDITIONAL 1 UNVERDICTED 1

representative citing papers

Tapered Language Models

cs.LG · 2026-06-22 · unverdicted · novelty 7.0

Tapered Language Models monotonically decrease MLP width across depth with a cosine schedule, yielding better perplexity and downstream performance than uniform-width baselines across multiple architectures and scales at no extra cost.

Variable-Width Transformers

cs.CL · 2026-06-16 · conditional · novelty 6.0

×-shaped variable-width transformers outperform parameter-matched uniform baselines on language modeling loss with 22% fewer FLOPs and 15% smaller KV cache.

citing papers explorer

Showing 2 of 2 citing papers.

  • Tapered Language Models cs.LG · 2026-06-22 · unverdicted · none · ref 2

    Tapered Language Models monotonically decrease MLP width across depth with a cosine schedule, yielding better perplexity and downstream performance than uniform-width baselines across multiple architectures and scales at no extra cost.

  • Variable-Width Transformers cs.CL · 2026-06-16 · conditional · none · ref 1

    ×-shaped variable-width transformers outperform parameter-matched uniform baselines on language modeling loss with 22% fewer FLOPs and 15% smaller KV cache.