I have been dreaming of this moment for a very long time. Our robot got good enough to play games with humans and win, whilst also being fun to play with. I am so so happy this is out & very grateful I got to work on this with so many wonderful & talented people. 👇 for details.

RT @ZhiSu22: 🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-se….

I've learned a lot from and been inspired by Alex's blog over the years. Thank you for writing Alex!.

RT @parada_car88104: It takes a village to build an awesome 🦾 🧠 . We are #hiring! Come transform robotics at Google DeepMind. I've receive….

RT @asurobot: I really like this video from our recent article on robot self-improvement @GoogleDeepMind . We (with @pannag_) describe how….

RT @GlenBerseth: At the next #CoRL we are hosting a generalist robot policy challenge! Train your most awesome policy and submit it for ind….

RT @ayzwah: We took a robot to RSS in LA running our new Gemini Robotics On-Device VLA model. People interacted with the model with new obj….

RT @parada_car88104: You can now also use our most powerful Gemini 2.5 for robotics and embodied intelligence - checkout our Google Develop….

RT @xiao_ted: Gemini 2.5's multimodal embodied reasoning capabilities are making a huge difference for many robotics researchers and indust….

RT @GoogleDeepMind: We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖. It’s our first vision-language-actio….

RT @kevin_zakka: We’re super thrilled to have received the Outstanding Demo Paper Award for MuJoCo Playground at RSS 2025!.Huge thanks to e….

RT @agarwl_: Giving my first ever invited talk at @CVPR , during the multimodal reasoning workshop:. The Bitter Lesson for RL: Verification….

Happening now!.

RT @xf1280: Excited that our work on Gemini Robotics and Gemini spatial understanding have just been featured on #GoogleIO stage! I believe….

Happening soon in room 302! 🤓🏓🤖.

(2) SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement.Talk: Wednesday 16:45 - 16:50, 311.Poster: Wednesday, 17:15 - 17:55.

(1) Achieving Human Level Competitive Robot Table Tennis 🏓.Talk: Tuesday 09:55-10:00, 302.Poster: Tuesday 10:30-11:05.

Headed to ICRA, stoked to learn about all the new research. We're presenting.(1) Achieving Human Level Competitive Robot Table Tennis 🏓 . (2) SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement 🤓. Come check them out. More details in 🧵.

I hugely admire Stephanie, she inspires me in multiple ways -- her intellect, technical rigour, curiosity, creativity, kindness & sense of fun. To name a few. It takes courage to share something like this. It's well worth a read, especially if you struggle with imposter syndrome.

RT @shreyasgite: Not many know that Gemini 2.5 or Flash can do zero-shot embodied reasoning (ER) for tasks like planning trajectories, gras….

RT @hardmaru: New Paper: Continuous Thought Machines 🧠. Neurons in brains use timing and synchronization in the way that they compute, but….