×-shaped variable-width transformers outperform parameter-matched uniform baselines on language modeling loss with 22% fewer FLOPs and 15% smaller KV cache.
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 2years
2026 2representative citing papers
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.
citing papers explorer
-
Variable-Width Transformers
×-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
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.