MIT researcher builds Molmo2Fish: open Molmo 2 tracks salmon and fixes errors via language
allen_ai · x · 2026-10-14
Ai2 highlights Molmo2Fish, a prototype by MIT '25 grad Kai Van Brunt (Sara Beery's BeeryLab) built on the open vision-language model Molmo 2. It tracks salmon in underwater sonar video — far outside Molmo 2's training domain — to support population monitoring and fisheries management. Van Brunt fine-tuned Molmo 2 on sonar footage, then trained it on examples of tracking errors, instructions, and corrections, letting researchers fix mistakes like two fish assigned the same track via natural-language guidance instead of frame-by-frame edits. The project showcases how open models, code, and data enable domain-specific research.
Related event: MIT Researchers Build Molmo2Fish to Track Salmon in Sonar Video(4 posts)→
More from Research
- Economist compiles 100+ free social science datasets on GitHub — _akpiper · 2026-10-14
- New ISQ article asks why policymakers wait to regulate disruptive tech like AI — mchorowitz · 2026-10-14
- MIT professor's ten predictions for AI for science, from executable papers to compiled matter — ProfBuehlerMIT · 2026-10-14
- Sweden spends hundreds of millions of kronor on printed textbooks as 2.8M-child study links screens to lower grades — Eric520CC · 2026-10-14
- Self-evolving red-team search finds 1.77x more harmful tool-call paths in personal agents — lulzxdxdxd · 2026-10-14
- Google researcher: general capabilities plus tool use are displacing domain-specific medical AI — davidstutz92 · 2026-10-14