🚀 New #CVPR2025 benchmark OmniMMI🔥. A comprehensive benchmark tailored for multi-modal interactions of #OmniLLMs in real-world streaming video contexts. 📹 🤖 First-ever benchmark for streaming video understanding & proactive reasoning 💡 Introducing M4: Multi-modal

Kuafu humanoids by Chinese company Leju Robotics moving totes at FAW's car factory.

ManipTrans is out on Hugging Face Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning

Hands up for Tengyu!😍

A joint effort between our lab and Leju Robotics. No video edits—just raw performance! A single 2-min shot isn’t perfect for validation, but it’s way better than a mashup of 5-sec clips. Show how the robot really operates! 🚀 #Robotics #AI

Really cool work by Haoran and folks!!! Check it out!!!

Coooooooool!!!!

Now the problem is: when will this van park in front of my house🥹

Finally a simulator for high-perf vision-based tactile🥹🥹🥹

Can language models be trained entirely on itself for reasoning tasks like AlphaZero (DeepMind, 2017) without relying on any external data? 🔥🔥Check out Absolute Zero! Training reasoning LLMs with ZERO DATA via RLVR! Q: What is Absolute Zero? A: A novel paradigm designed for

Coming soon, please stay tuned!🥰 #Unitree #AGI #EmbodiedAI #AI #HumanoidRobot #Bipedal #WorldModel

🤖 Ever dreamed of controlling a humanoid robot to perform complex, long-horizon tasks — using just a single Vision Pro? 🎉 Meet CLONE: a holistic, closed-loop, whole-body teleoperation system for long-horizon humanoid control! 🏃‍♂️🧍 CLONE enables rich and coordinated

#CVPR2025 is just around the corner!🔥🔥 Join us for the exciting roster of distinguished speakers at the 5th Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics. #3DSUN Mark: June 11th, starting from 8:45 AM in Room 106C! #CVPR2025 scene-understanding.com

Will be there through out the event! Come and have a chat on any topic😎

Happening now at Room 106C, come join the dance!😎

Really smooth!

This is the best content to ever hit the internet

🤖 Ever wished robots could learn new manipulation tasks with just a few demos — and still generalize? 🔥 Introducing **ControlVLA**: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models. 🦾🎯 From opening cabinets to folding clothes, pouring cubes,

ARK believes that if humanoids can achieve just 75% of human productivity, they pay for themselves. This thesis boils down to a simple economic argument: the cost equation fundamentally shifts in favor of robots. **Economic Analysis** Their NPV analysis shows that if Tesla hits

Unitree Introducing | Unitree A2 Stellar Hunter 🤩 Total weight: ~37kg | Unloaded range: ~20km Lighter, Stronger and Faster. Engineered for Industrial Applications.