I just added the code for a sequence of tasks! Check it out @ github.com/GuyTevet/CLoSD and make your own sequences🕺💃

[1/5] Rethinking SVGs, the implicit way — meet NeuralSVG! 🎨✨ An implicit neural representation for generating layered SVGs from text prompts. 💧 Powered by SDS and nested-dropout for ordered shapes 🖌️ Enables inference-time editing like color palette & aspect ratio Read more on

CLoSD meets Two Minute Papers—what an honor! 🤩 Thank you, Dr. Károly Zsolnai-Fehér, for making dreams come true! 🙏 guytevet.github.io/CLoSD-page/

We're back! 🚶‍♀️🕺 The Human Motion Generation Workshop returns to #CVPR2025 with an amazing lineup of speakers from academia and industry. 🎤✨ 📢 Call for Papers and details: humogen.github.io Daniel Holden Ziwei Liu Yuting Ye, and Taku Komura.

We invite you to submit your Motion Generation papers to the HuMoGen #CVPR2025 workshop! The deadline is on March 12 More details @ humogen.github.io

Our latest release brings new features for MDM users too! 🚀 ✅ Improved text encoding ✅ Model averaging ✅ Better training monitoring Make sure to pull the update! 👇 github.com/GuyTevet/motio…

True😅🥸 Don't miss the deadline on March 12!

The deadline is in one week!

One week before the HuMoGen deadline. The submission portal is open at: openreview.net/group?id=thecv…

📢 Deadline extended! 📢 You now have an extra week to submit! New deadline: March 19. Want to submit? Find all the details here: humogen.github.io 🚀

Ever stared at a set of shapes and thought: 'These could be something… but what?' Designed for visual ideation, PiT takes a set of concepts and interprets them as parts within a target domain, assembling them together while also sampling missing parts. eladrich.github.io/PiT/

So thrilled to share “Generative Motion Infilling From Imprecisely Timed Keyframes”, to be presented at #Eurographics2025 (1/4) Website: purvigoel.github.io/imprecise-timi… Paper: arxiv.org/abs/2503.01016 Video: youtube.com/watch?v=izbbt1…

Excited to be in Singapore for #ICLR2025! 🇸🇬 If you're into motion and animation, please feel free to reach out! Catch our spotlight poster: #CLoSD: Closing the Loop between Simulation and Diffusion 🗓️ Fri, Apr 25 | ⏰ 10:00–12:30 🔗 iclr.cc/virtual/2025/p…

🔔Excited to announce that #AnyTop has been accepted to #SIGGRAPH2025!🥳 ✅ A diffusion model that generates motion for arbitrary skeletons ✅ Using only a skeletal structure as input ✅ Learns semantic correspondences across diverse skeletons 🌐 Project: anytop2025.github.io/Anytop-page

🎉 The #CVPR HuMoGen Workshop is happening TODAY afternoon! We’ll be featuring an exciting lineup of invited talks and poster presentations covering cutting-edge work in generative modeling of 3D and 2D human motion. If you’re working in this space, you won’t want to miss it!

What a fantastic workshop! 🚀 Huge thanks to our amazing speakers, insightful poster presenters, dedicated reviewers, and the engaged audience who stayed with us throughout the day. We couldn't have asked for a better community! see you next time! 🙌 #CVPR2025 #HumanMotion

To the entire Tel Aviv University community: This morning, a missile launched from Iran struck near the Tel Aviv University campus. As a result of the impact, secondary damage occurred – mainly shattered glass – in several buildings and dormitories. Fortunately, none of our