TLDRocket
Sign in

Evolving New Foundation Models: Unleashing the Power of Automating Model Development

Sakana AI Covered by 2 sources

Sakana AI published a paper in Nature Machine Intelligence describing Evolutionary Model Merge, a method that uses evolutionary algorithms to automatically combine existing open-source AI models into new foundation models optimized for specific tasks. The company created three Japanese foundation models (EvoLLM-JP, EvoVLM-JP, and EvoSDXL-JP) where their 7B-parameter Japanese math LLM matched the performance of previous 70B-parameter models without requiring gradient-based training. This approach enables automated foundation model development with minimal compute resources by systematically discovering effective model combinations that human experts might not intuitively discover.

Also covered by

Related stories

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads 60+ sources, removes duplicate coverage, and summarises the day in two minutes. Free, no spam, unsubscribe anytime.