Thank you Thibaud Zamora, for covering our work! Please see the following thread for more information! x.com/mehsaygin/stat…

Thank you Robert Scoble, for covering our work! Check out Diffuse2Choose, a virtual try-all model that allows users to try on any e-commerce item in any setting! 📜: arxiv.org/abs/2401.13795 🌎: diffuse2choose.github.io Thread: x.com/mehsaygin/stat… Stay tuned for more!

Excited to share that Quilt-LLaVA has been accepted at #CVPR2026! As promised, we are making our model, datasets, and training scripts available to the community: quilt-llava.github.io See you all in Seattle! ɪᴋᴇᴢᴏɢᴡᴏ ᴡɪsᴅᴏᴍ ᴏ. Fatemeh Ghezloo Ranjay Krishna Linda Shapiro

Excited to be giving an invited talk about diffuse2choose.github.io at "The First Workshop on Virtual Try-On" #CVPR2026 (Monday 4:40 pm, Room Arch 309)! Details: vto-cvpr24.github.io Looking forward to seeing all those who attend in person!

We are organizing "The First Workshop on the Evaluation of Generative Foundation Models" #CVPR2026 next Tuesday (Summit 433, 1-6:30 pm). For details, please see evgenfm.github.io See you all in Seattle! #CVPR24

Excited to present Quilt-LLaVA quilt-llava.github.io with my co-leads ɪᴋᴇᴢᴏɢᴡᴏ ᴡɪsᴅᴏᴍ ᴏ. and Fatemeh Ghezloo #CVPR2026 tomorrow! Join us at the poster session from 10 AM to 12 PM in ARCH 4A-E #342

Just presented Quilt-LLaVA #CVPR2026 with ɪᴋᴇᴢᴏɢᴡᴏ ᴡɪsᴅᴏᴍ ᴏ. and Fatemeh Ghezloo! Huge thanks to everyone who stopped by to chat with us!

How much GPU VRAM do I need to be able to serve Llama 70B? Clean formulae

Check out Pathfinder! We’ve imitated human doctors’ diagnostic process in whole slide images using a multi-agent framework. Pathfinder not only surpasses the state of the art AI models in skin cancer detection but also outperforms human experts! Code, data and model coming soon!

A new LLM benchmark just dropped.

Thanks for the profile pic guys Google

“LLMs can’t reason like humans do” Yeah, planes also cannot flap wings but they still fly don’t they?

how diffusion models work