Nathan Lambert's picture

Nathan Lambert

natolambert

·

https://www.natolambert.com/

AI & ML interests

Reinforcement learning, Ethics, Robotics, Dynamics Models

Recent Activity

updated a model 3 days ago

allenai/Olmo-3-32B-Think-DPO

updated a model 3 days ago

allenai/Olmo-3-32B-Think-SFT

updated a model 3 days ago

allenai/Olmo-3-7B-Think

View all activity

Organizations

upvoted a collection 27 days ago

Olmo 3.1

The latest members of the Olmo 3 family: another 3 weeks of RL for 32B Think, the 32B Instruct model, large post-training research datasets... • 9 items • Updated 16 days ago • 43

upvoted a paper about 1 month ago

olmOCR 2: Unit Test Rewards for Document OCR

Paper • 2510.19817 • Published Oct 22, 2025 • 15

upvoted a collection about 2 months ago

Olmo 3 Post-training

All artifacts for post-training Olmo 3. Datasets follow the model that resulted from training on them. • 32 items • Updated 16 days ago • 46

upvoted a collection 3 months ago

Olmo 3

Artifacts for the Olmo 3 release. • 9 items • Updated 16 days ago • 159

upvoted an article 5 months ago

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

+3

Jul 29, 2025

•

206

upvoted a paper 6 months ago

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy

Paper • 2507.01352 • Published Jul 2, 2025 • 56

upvoted a collection 6 months ago

Reward Models 06-2025

Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge • 8 items • Updated 16 days ago • 23

upvoted 2 collections 7 months ago

Reward Bench 2

Datasets, spaces, and models for Reward Bench 2 benchmark and paper! • 11 items • Updated 16 days ago • 16

Common Pile v0.1

All resources related to Common Pile v0.1, an 8TB dataset of public domain and openly licensed text • 4 items • Updated Jun 6, 2025 • 39

upvoted 2 collections 8 months ago

OpenVision

27 items • Updated Aug 15, 2025 • 33

Qwen3

84 items • Updated 8 days ago • 1.55k

upvoted a paper 9 months ago

Reinforcement Learning from Human Feedback

Paper • 2504.12501 • Published Apr 16, 2025 • 4

upvoted a collection 11 months ago

OLMoE (January 2025)

Improved OLMoE for iOS app. Read more: https://allenai.org/blog/olmoe-app • 10 items • Updated 16 days ago • 16

upvoted an article 12 months ago

Article

Putting RL back in RLHF

Jun 12, 2024

•

109

upvoted a collection about 1 year ago

2024 Interconnects Artifacts

Models & datasets mentioned in the bottom section of posts! • 280 items • Updated Jan 2, 2025 • 6

upvoted a paper about 1 year ago

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published Dec 13, 2024 • 147

upvoted 4 collections about 1 year ago

PixMo

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 10 items • Updated 16 days ago • 85

OLMo 2

Artifacts for the OLMo 2 release. • 35 items • Updated 16 days ago • 151

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated 16 days ago • 103

Tulu 3 Datasets

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 33 items • Updated 16 days ago • 96