# Sequential Attention: Making AI models leaner and faster without sacrificing accuracy

DevFeed: [Sequential Attention: Making AI models leaner and faster without sacrificing accuracy](<https://devfeed.tech/articles/sequential-attention-making-ai-models-leaner-and-faster-without-sacrificing-accuracy-6872.md>)

Original publisher: [Read original article](<https://research.google/blog/sequential-attention-making-ai-models-leaner-and-faster-without-sacrificing-accuracy/>)

Published: 2026-02-04T15:14:00Z

Content type: article

Language: en

Sources: [The latest research from Google](<https://devfeed.tech/sources/the-latest-research-from-google.md>)

Topics: [Algorithms & Theory](<https://devfeed.tech/topics/algorithms-theory.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [algorithms-theory](<https://devfeed.tech/tags/algorithms-theory.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [features](<https://devfeed.tech/tags/features.md>), [google](<https://devfeed.tech/tags/google.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [research](<https://devfeed.tech/tags/research.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

Google Research presents Sequential Attention, a greedy and adaptive subset-selection method for making large-scale machine-learning and deep-learning models more efficient. The approach selects useful components such as features, layers, blocks, embedding chunks, or weight entries during a single training run, reducing redundancy while preserving accuracy and limiting additional training cost.

## Source excerpt

Algorithms & Theory