Sublime
An inspiration engine for ideas
Introducing new models for research & development of health applications: MedGemma 27B Multimodal, for complex multimodal & longitudinal EHR interpretation, and MedSigLIP, a lightweight image & text encoder for classification, search, & related tasks. → https://t.co/I318jVmsYD https://t.co/LlpL269Poa
The chineese are striking again - few days after Runway release Act one X-Portrait 2 release a super expressive Video to Video model.
Link in first comment https://t.co/mqUqd00i7R
Teodora P Lx.comIt was as if he wanted to catalog the world—not by any formal means, and not even for any particular reason, but simply because he found joy in the process.
Fei-Fei Li • The Worlds I See: Curiosity, Exploration, and Discovery at the Dawn of AI
Cool to see a 500M param model I trained myself do better than Google cloud vision, Claude, and GPT-4V on this task. (look at the thread for the results)
It's a relatively narrow one (OCR), but feels nice to see that small open source models still have a place.
Vik Paruchurix.com
