Skip to main content ->
Ai2

Latest research

January 30, 2025

Scaling the Tülu 3 post-training recipes to surpass the performance of DeepSeek V3

Meet Tülu 3 405B, the first application of fully open post-training recipes to the largest open-weight models.
Read post
January 21, 2025

Introducing Ai2 ScholarQA

Ai2 ScholarQA gives in-depth, detailed, and contextual answers to help with literature review.
Read post
December 10, 2024

The Ai2 Climate Emulator

The Ai2 Climate Emulator: Fast, accurate AI-based atmospheric simulation for historical and future climates.
Read post
November 26, 2024

OLMo 2: The best fully open language model to date

Our next generation of fully-open base and instruct models sit at the Pareto frontier of performance and training efficiency. Check out our [paper](https://arxiv.org/abs/2501.00656) to learn more, or keep reading for a summary.
Read post
November 21, 2024

Tülu 3 opens language model post-training up to more tasks and more people

Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes.
Read post
November 21, 2024

Tülu 3: The next era in open post-training

A technical deep-dive into Tülu 3, with the model "recipe", data, and more.
Read post
November 19, 2024

Scientific literature synthesis with retrieval-augmented language models

Ai2’s & UW’s new retrieval-augmented LM helps scientists navigate and synthesize scientific literature.
Read post
November 12, 2024

How many Van Goghs does it take to Van Gogh? Finding the imitation threshold

Meet MIMETIC^2: Finding the number of images required by text-to-image models for imitation of a concept.
Read post
October 28, 2024

Hybrid preferences: Learning to route instances for human vs. AI feedback

We introduce a routing framework that combines inputs from humans and LMs to achieve better annotation quality.
Read post