Things worth writing down

Featured

ML Research

What Cloud Segmentation Taught Us About Vision-Language Models

We tested whether prompt engineering can adapt vision-language models to satellite imagery. Across 60 prompt variants on cloud segmentation, every one underperformed the zero-shot baseline. But fine-tuning with just 8 labeled images beat them all, and the choice between LoRA and full fine-tuning turned out to be about task structure, not compute.

Read post