News

The researchers found that VLMs need much more domain-specific training data to process difficult queries. By familiarizing with more informative data, the models could one day be great research assistants to ecologists, biologists, and other nature scientists (Credit: Alex Shipps/MIT CSAIL).

Ecologists find computer vision models’ blind spots in retrieving wildlife images

Left to right: Gabriele Corso, Jeremy Wohlwend, and Saro Passaro (Credit: Alex Ouyang, MIT Jameel Clinic).

MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures

To help robots execute open-ended tasks safely, MIT researchers used vision models to see what’s near the machine and model its constraints. Their “PRoC3S” strategy has an LLM sketch up an action plan that’s checked in a simulator to ensure it’ll work in the real world (Credit: Mike Grimmett/MIT CSAIL).

Teaching a robot its limits to complete open-ended tasks safely

Spotlighted News

Ecologists find computer vision models’ blind spots in retrieving wildlife images

MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures

Teaching a robot its limits to complete open-ended tasks safely