Hugo Caselles-Dupré (@casellesdupre) header
Hugo Caselles-Dupré (@casellesdupre) profile picture

Artist at Obvious @obv_ious. Research Director at @obv_research, in partnership with Sorbonne University. PhD in Machine Learning. Forbes 30 under 30.

Paris, Ile-de-France
Joined March 2017
Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)Photo by Hugo Caselles-Dupré (@casellesdupre)
Honored to have been selected among the Forbes 30 under 30 with my fellows at @obv_ious 🎉🚀🙏 forbes.com/profile/obvious/?…
2
21
Hugo Caselles-Dupré retweeted
🚨 We got a **best paper award** at ECCV @eccvconf workshop 2026 ! Paper: arxiv.org/abs/2603.17555 We are artists that strive to create art using science. This is a proof that it’s possible. Such a great feeling to get this recognition.
2
1
9
467
my first best paper award! 🏆 > at ECCV 2026 MUCG workshop. FrescoDiffusion allows to create arbitrarily large videos. arxiv: arxiv.org/abs/2603.17555 thanks to our team for the great work.
4
286
Molière Ex Machina sur CNN!
Quand l'intelligence artificielle rencontre Molière : @MelissaBellCNN était à l'opéra Royal de Versailles pour découvrir “L’Astrologue ou le faux présage”, une pièce de théâtre unique pensée par des spécialistes de Molière de la Sorbonne.
3
132
Our latest exhibition and digital art drop.
Aaaand it's a wrap! The 100 editions have been minted. Stay tuned for the reveal!
3
53
A strong pattern is emerging across recent video generation papers. Different methods, same direction: video models are becoming real-time, autoregressive, and interactive. A quick thread on how this space is blooming. 📸: Rolling Forcing method.
1
1
3
704
Portal runs around 50 FPS and has been deployed live at Parc des Princes, at the AI Summit in the Grand Palais, and other public venues. It’s not a clip you play, it is a video that lives and reacts.
1
62
Seeing these ideas converging across labs (academia and industry) confirms something we felt early: interactive generative video will reshape art, games, simulation, and how we think about creation in time.
50
Je serai en direct sur RFI aujourd'hui à 18h30 pour le débat du jour sur la création artistique avec l'IA. Suivez le lien pour écouter en direct ! rfi.fr/fr/direct-monde
1
1
305
Jean Zay est un ordinateur iconique pour les chercheurs en IA, que j'utilise personnellement depuis des années. Avec Obvious, on est fiers de présenter cette oeuvre-hommage qui sert de covering à la quatrième extension de la machine.
We had the honor of creating the artistic covering of Jean Zay, France’s national AI supercomputer. An artwork about AI algorithms on the very machine that trains them!
108
Large-scale composite images experiments
95