Oumi's Blog

Lambda and Oumi partner for end-to-end custom model development

Enterprises can now build and deploy custom models for their specific use cases 100x faster, with 10x better cost efficiency, and superior accuracy

Feb 5 • Stefan Webb

6

2

3

January 2026

November 2025

Oumi v0.5.0: Data Synthesis, OpenEnv, Hyper-param Tuning

OpenEnv support, Hyperparameter Tuning, AWS Bedrock, and Advanced RL Training

Nov 20, 2025 • Stefan Webb and Oussama ELACHQAR

2

October 2025

DCVLR Competition Results: Data Curation for Vision-Language Reasoning

We are excited to present the results of the inaugural DCVLR (Data Curation for Vision-Language Reasoning) competition at NeurIPS 2025!

Oct 31, 2025 • Oussama ELACHQAR

4

Less (Data) is More for Fine-tuning

1000 Samples or Less for Amazing Fine-tuning

Oct 23, 2025 • Stefan Webb

8

1

2

Why Less is More for Fine-Tuning

What is the evidence for successful fine-tuning with small data?

Oct 21, 2025 • Stefan Webb

6

1

1:37

Small Fine-tuned Models are All You Need

But the devil is in the details—how can you get them right?

Oct 16, 2025 • Stefan Webb

11

2

1

Hours, Not Months – The Custom AI Era is Now

When we started Oumi, we set out to build a better future for AI – grounded in the benefits of open source.

Oct 9, 2025 • Manos Koukoumidis

9

5

September 2025

OpenAI Just Dropped Two Massive Open-weight Models — But How Do We Separate The Reality From The Hype?

Originally published Aug 9th, 2025

Sep 14, 2025 • Stefan Webb

2

Training Frontier Reasoning VLMs for the 2025 NeurIPS DCVLR Workshop with Oumi

Originally published July 31, 2025

Sep 14, 2025 • Stefan Webb

1

Compete to Curate Smarter Vision-Language Data—And Win Big at NeurIPS 2025

Originally posted June 18, 2025

Sep 14, 2025 • Stefan Webb

1

Run GRPO Training in Oumi Using the trl and verl Libraries

Originally published June 18th, 2025

Sep 14, 2025 • Stefan Webb and William Zeng

1