Please consider submitting your paper to our ICCV workshop!

🎉New preprint!🎉 Extremely excited to share CryoBoltz❄️⚡️, led by superstar Rishwanth Raghu! We develop a multiscale guidance recipe to steer structure prediction models (e.g. AlphaFold3 / Boltz-1) towards experimental cryo-EM density maps, including heterogeneous,

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: kyleleey.github.io/WonderPlay/ 🧵1/7

Solving challenging inverse problems for science is tough, but worthwhile! My student Axel Levy led the efforts on developing the SOTA ab initio method for cryo-EM reconstruction of biomolecules with heterogeneous conformations. Congrats on the Nature Methods paper to the team!

Long and consistent video generation has been a major challenge in genAI. This paper shows how to achieve minute-long video generation with impressive consistency using computationally efficient sparse attention. Fantastic work!!

Some random thoughts I've been having about video world model/long video generation since working on Mixture of Contexts (whose title could also be "Learnable Sparse Attention for Long Video Generation"): 🚨Semi-long Post Alert🚨 1. Learnable sparse attention is still underrated