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.
On the resurgence of recurrent models for long sequences: Survey and research opportunities in the transformer era
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Titans combine attention for current context with a learnable neural memory for long-term history, achieving better performance and scaling to over 2M-token contexts on language, reasoning, genomics, and time-series tasks.
citing papers explorer
-
Tapered Language Models
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.
-
Titans: Learning to Memorize at Test Time
Titans combine attention for current context with a learnable neural memory for long-term history, achieving better performance and scaling to over 2M-token contexts on language, reasoning, genomics, and time-series tasks.