Search Know Your ML

Search across AI research reports and briefs. Results load instantly — no JavaScript required.

Fig. 02 / Field notesFind your way to the source
A citation index with a magnifying lens locating a source.
Follow the index from a question to its original research.

7 results for “attention”

AI research reports

Mamba: Selective State Spaces

AI-generated review · 5 min read

Mamba replaces attention with selective state spaces that scale linearly in sequence length — matching transformers at several times the inference speed.

mamba state-space-models long-context Read report

The Transformer: Attention Without Recurrence

AI-generated review · 5 min read

The Transformer replaced recurrence with self-attention, enabling massively parallel training — the architecture behind GPT, BERT and modern LLMs.

transformers attention self-attention Read report

AI briefs

The Transformer architecture: attention without recurrence

AI-generated brief · Cited sources below

Introduces a sequence-to-sequence model that replaces recurrence and convolution entirely with self-attention, enabling highly parallelizable training and establishing the foundation for modern large language models.

Sources: arXiv:1706.03762