Paul Vicol
paulvicol.bsky.social
Research Scientist at Google DeepMind. Working on Gemini reasoning models. PhD from UofT and Vector Institute www.paulvicol.com
👤 Joined on 14 November 2024
744
Followers
170
Following
38
Total Posts
📜 Kullanıcı Geçmişi
- 14 Kas 2024, 04:40
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@paulvicol.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
🌐 Check out TMLR Beyond PDF at tmlr-beyond-pdf.org! 💻 Submissions are made on OpenReview just like standard TMLR submissions. 🎨 Create your TMLR Beyond PDF submission today!
Show Post🚀 Introducing TMLR Beyond PDF! 🎬 This is a new, HTML-based submission format for TMLR, that supports interactive figures and videos, along with the usual LaTeX and images. 🎉 Thanks to TMLR Editors in Chief: Hugo Larochelle, @gautamkamath.com, Naila Murray, Nihar B. Shah, and Laurent Charlin!
Show Post🚀 All this and more in our paper! arXiv: arxiv.org/abs/2509.20328 By @thwiedemer.bsky.social, Yuxuan Li, @paulvicol.bsky.social, @nmatares.bsky.social, Been Kim, Kevin Swersky, Priyank Jaini, and Robert Geirhos.
Show PostVeo 3 understands material properties, including buoyancy, reflections, flammability, and soft body physics.
Show PostVeo 3 can understand which objects fit in a backpack, and can categorize objects (putting all the toys in a bucket). Veo 3 can also draw, and understands the effects of gravity and air resistance on falling objects.
Show Post