David Picard

davidpicard.eurosky.social

21 October 2026 20:48

🚨 New preprint: "Dino Forcing Flow Models: Do not denoise what you can predict" @arrijitghosh.bsky.social @lucasdegeorge.bsky.social P. Couairon, A.A. Efros, @vickykalogeiton.bsky.social and me 📜 arxiv.org/abs/2610.11751 🖥️ arijit-hub.github.io/projects/din... 🤖 github.com/arijit-hub/d... 🧵👇

Sophia Sirko-Galouchenko 🇺🇦

ssirko.bsky.social

05 October 2026 14:08

1/n 🚀 New paper 𝚆𝚑𝚎𝚛𝚎-𝙾𝙿𝙳 In on-policy self-distillation, the student learns from a privileged version of itself. In recent methods, privilege often comes from a better view of the image. What if, instead of a better view, the teacher knew where to look? 👀

David Picard

davidpicard.eurosky.social

14 September 2026 22:56

New year, new semester, new course, new textbook: davidpicard.github.io/mldl/mldl-bo... 👀 Still in draft form, but not in a bad shape.

Vladan Stojnić

stojnicv.xyz

06 September 2026 21:49

Attending #ECCV2026? Want to know why your favorite vision models learn to encode camera acquisition and processing traces? Come meet our team! 👇 @eccv.bsky.social

Lucas Degeorge

lucasdegeorge.bsky.social

03 September 2026 14:13

🚀 New paper: Balancing Frequencies and Pixels in Flow Matching We tackle the low-frequency bias in pixel-space flow matching and train JiT up to 40% faster without any architectural changes. 📄 Read it here: arxiv.org/abs/2609.02748