#ICML2025 Yes, Chebyshev is back here🚛, showing its power in graph wavelet design! Welcome to my poster at East Exhibition Hall A-B #E-2912 at Wed 4:30 p.m. PDT — 7 p.m. PDT. See you all!

🎶Can a robot learn to play music? YES! — by teaching itself, one beat at a time 🎼 🥁Introducing Robot Drummer: Learning Rhythmic Skills for Humanoid Drumming 🤖 🔍 For details, check out: robotdrummer.github.io

VLMs often struggle with physical reasoning tasks such as spatial reasoning. Excited to share how we can use world models + test-time search to zero-shot improve spatial reasoning in VLMs!

Thrilled to finally release this study! 🚀 We view (discrete) diffusion models as implicitly doing data augmentation over autoregressive. Through this lens, we find that diffusion outperforms AR in data-constrained settings, but it requires larger models and way more epochs to

🇨🇳 An engineering student in China made a prototype of a sword that levitates towards you and flies around on command.

World models for robotics should learn, act, and evaluate in one loop. We're releasing Genie Envisioner (GE): a unified, video‑generative platform that integrates prediction, policy learning, and neural simulation together.

I start to believe that there is some subtle difference between compression (common for all intelligence) and abstraction (unique for artificial intelligence of human). They are definitely related, but different in a fundamental way. This shall be our next major quest for AI.

Want to achieve extreme performance in motion tracking—and go beyond it? Our preprint tech report is now online, with open-source code available!

Wow 🤯 DINO v3 features aren’t just good at multi-view consistency and objectness… they even capture shadows and cloth folds!

DINOv3 seems very good at matching objects across environments as well

🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-second reaction, human-like strikes.

What is even more despairing is that there are actually candidates who meet the criteria.

🚀 Want to build a 3D-aware manipulation policy, but troubled by the noisy depth perception? Want to train your manipulation policy in simulation, but tired of bridging the sim2real gap by degenerating geometric perception, like adding noise? Now these notorious problems are gone