BLAST RADIUS

Open-weight & owned stack · Training tuning

Researchers Develop Reusable Zeroth-Order LLM Fine-Tuner

Sep 11, 2026

Researchers developed ZO-Finetuner, a learned zeroth-order optimizer reusable across datasets for the same or derivative language models.

Read the original at lacuna.tiptreesystems.comOpens the publisher's site in a new tab

More in Open-weight & owned stack