Pith. sign in

Hierarchical transformers are more efficient language models

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

2 Pith papers citing it

fields

cs.CL 2

years

2026 2

representative citing papers

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.

  • Variable-Width Transformers cs.CL · 2026-06-16 · conditional · none · ref 28

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

  • Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction cs.CL · 2026-05-18 · unverdicted · none · ref 31

    GA-S2S integrates T5 with RGAT to jointly process text and k-hop subgraph topology for knowledge graph link prediction, reporting up to 19% relative accuracy gain over seq2seq baselines on CoDEx.