Have you ever wondered what makes two models different?
We all know the ViT-Large performs better than the Resnet-50, but what visual concepts drive this difference? Our new ICLR 2025 paper addresses this question! nkondapa.github.io/rsvc-page/

❓How can we predict where a species may be found when observations are limited?

✨Introducing Le-SINR: A text to range map model that can enable scientists to produce more accurate range maps with fewer observations.

Thread 🧵

Heading to #AGU24 in DC tomorrow. Giving a poster in "Advances in Remote Sensing for Monitoring Biodiversity Change: Integrating Data and Models Across Scales and Technologies" session on Thursday aft. Excited to see where others are at on this topic and catch up on new remote sensing products.

🎯 How can we empower scientific discovery in millions of nature photos?

Introducing INQUIRE: A benchmark testing if AI vision-language models can help scientists find biodiversity patterns- from disease symptoms to rare behaviors- hidden in vast image collections.

Thread👇🧵

Glenn and I just deployed Audiomoths, Wildlife Acoustics Micro 2s, and some Micro 1s in the same place in the Amazon - happy to send sample files from each so you can compare the audio quality. The micro 2s were so much easier to configure and check on in the field