Not all tokens are meant to be forgotten (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Not all tokens are meant to be forgotten

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: Multi-Token Attention

Multi-Token Attention (arxiv.org)

131 points by fzliu 1 year ago | 35 comments

Screenshot of arxiv.org: Physics in Next-Token Prediction

Physics in Next-Token Prediction (arxiv.org)

17 points by Anon84 1 year ago | 3 comments

Screenshot of arxiv.org: Auto-Regressive Next-Token Predictors Are Universal Learners

Auto-Regressive Next-Token Predictors Are Universal Learners (arxiv.org)

65 points by dataminer 3 years ago | 9 comments

Screenshot of arxiv.org: TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters (arxiv.org)

170 points by og_kalu 2 years ago | 28 comments

Screenshot of arxiv.org: Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation

Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation (arxiv.org)

158 points by fheinsen 8 months ago | 87 comments

Screenshot of arxiv.org: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering (arxiv.org)

162 points by Anon84 4 months ago | 66 comments