David Picard

davidpicard.eurosky.social

20 October 2026 09:02

🚨 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... 🧵👇

David Picard

davidpicard.eurosky.social

03 September 2026 14:04

It's a cool paper, both old school and new school. There's an Easter egg: I designed a game for the teaser. Did you get it right? I tried it in my ML course and almost nobody got it.

David Picard

davidpicard.eurosky.social

03 June 2026 08:30

🚨 arxiv.org/abs/2604.06129 PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer This paper is the result of doing a lab-wide hackathon on an idea I've had for some time. Probably the paper with the highest number of authors I've ever done. It's a CVPR Findings 26. Thread 🧵👇

David Picard

davidpicard.eurosky.social

21 May 2026 17:38

👏 Folks! If you are curious about the Generative Modeling via Drifting paper, but you find it difficult to understand → I wrote a different interpretation of it. It's called: "An Expectation-Maximization interpretation of Generative Modeling via Drifting" davidpicard.github.io/pdf/An_Expec...

Nicolas Dufour

nicolasdufour.bsky.social

21 May 2026 07:23

Thrilled to share that MIRO is accepted to ICML 2026 @icmlconf.bsky.social ! 🎉 By training on the reward scores, we can simply condition the model on high rewards at inference time to guarantee top-tier, aligned outputs. We’ve updated our paper with some additional results!