Michael Dorkenwald

@mdorkenw.bsky.social

🇪🇺 ELLIS PhD @ University of Amsterdam 🤖 Vision-Language, Video Learning, SSL 🏡 www.mdorkenwald.com

Pretrained ViTs usually come in rigid sizes (S, B, L, H). But your hardware constraints don't We built a way to make DINO or CLIP fully elastic in <5 mins without any retraining ⚡️ Get the exact model size you need, not just what was released Find Walter at #NeurIPS Poster 4709 | Thu 4:30-7:30 PM

Bild

Fuck it, today we're open-sourcing the codebase used to train SmolVLM from scratch on 256 H100s 🔥 Inspired by our team's effort to open-source DeepSeek's R1, we are releasing the training and evaluation code on top of the weights 🫡 Now you can train any SmolVLM—or create your own custom VLMs!

Bild

🤔 Can you turn your vision-language model from a great zero-shot model into a great-at-any-shot generalist? Turns out you can, and here is how: arxiv.org/abs/2411.15099 Really excited to this work on multimodal pretraining for my first bluesky entry! 🧵 A short and hopefully informative thread:

BildBildBild