Archive - The AI Atlas

Nobody Understands AI

Why are we freaking out over DeepSeek?

Jan 28 •

June 2024

Sunday Paper: 8th Edition

Supercharging LLMs through KV Cache Compression

Jun 30, 2024 •

Sunday Paper: 7th Edition

Grokking and the Reasoning abilities of LLMs

Jun 25, 2024 •

Sunday Paper: 6th Edition

The Return of Recurrent Networks

Jun 24, 2024 •

Sunday Paper: 5th Edition

The Next Generation of Retrieval Augmented Generation

Jun 23, 2024 •

Sunday Paper: 4th Edition

Uncovering Big Contributions to RAG Processes

Jun 2, 2024 •

May 2024

Sunday Paper: 3rd Edition

Exploring Mixture of Experts and its Inspirations

May 26, 2024 •

Sunday Paper: 2nd Edition

Exploring Alternative Language Model Architectures

May 19, 2024 •

Sunday Paper: 1st Edition

Papers that explore data efficient training of LLMs

May 12, 2024 •

April 2024

The Unexpected Flaw in Ai21’s Jamba Model

Read about how Ai21 can improve the Jamba model by fixing a simple architecture error derived from Mamba research.

Apr 10, 2024 •

The Accidental Success of ChatGPT

The success of ChatGPT was a surprise to even OpenAI and revolutionized the field of AI, taking us from language models to automated language agents.

Apr 6, 2024 •

March 2024

Mamba Will Never Beat the Transformer

New research has improved Transformer Context Length, creating new models such as Gemini 1.5, solving a key weakness for Transformers.

Mar 25, 2024 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts