0

Don't Pay Attention

Avey, a new neural architecture combining a ranker and an autoregressive processor, demonstrates superior performance over the Transformer in processing long-range dependencies and has competitive short-range capabilities.

Year
2025
Venue
arXiv 2025
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2506.11305ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

The Transformer has become the de facto standard for large language models and a wide range of downstream tasks across various domains. Despite its numerous advantages like inherent training parallelism, the Transformer still faces key challenges due to its inability to effectively process sequences beyond a fixed context window and the quadratic complexity of its attention mechanism. These challenges have renewed interest in RNN-like architectures, which offer linear scaling with sequence length and improved handling of long-range dependencies, albeit with limited parallelism due to their inherently recurrent nature. In this paper, we propose Avey, a new neural foundational architecture that breaks away from both attention and recurrence. Avey comprises a ranker and an autoregressive neural processor, which collaboratively identify and contextualize only the most relevant tokens for any given token, regardless of their positions in the sequence. Specifically, Avey decouples sequence length from context width, thus enabling effective processing of arbitrarily long sequences. Experimental results show that Avey compares favorably to the Transformer across a variety of standard short-range NLP benchmarks, while notably excelling at capturing long-range dependencies.

Authors

2