Oncel Tuzel

Check out the code, models, and demo iOS/macOS app using MLX for our fast vision-language models, FastVLM:
github.com/apple/ml-fas...

Paper: "FastVLM: Efficient Vision Encoding for Vision Language Models", Anasosalu et al., CVPR 2025
arxiv.org/abs/2412.13303

#CVPR2025 #Apple #research

Today is a great day for optimal transport 🎉! Lots of gratitude 🙏 for all folks who contributed to ott-jax.readthedocs.io and pushed for the MOSCOT (now @ nature!) paper, from visionaries @dominik1klein.bsky.social, G. Palla, Z. Piran to the magician, Michal Klein! ❤️

www.nature.com/articles/s41...

FastVLM: Efficient Vision Encoding for Vision Language Models Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders su...

For more, check out our paper on arxiv: arxiv.org/abs/2412.13303

With the amazing people: @pavankumarvasu.bsky.social , Fartash Faghri, Chun-Liang Li, Hadi Pouransari, Nate True, Albert Antony, Gokul Santhanam, James Gabriel, Peter Grasch, and @onceltuzel.bsky.social

WVD Pipeline

🤔Image-to-3D, monocular depth estimation, camera pose estimation, …, can we achieve all of this with just ONE model easily?

🚀Our answer is Yes -- Excited to introduce our latest work: World-consistent Video Diffusion (WVD) with Explicit 3D Modeling!

arxiv.org/abs/2412.01821