Russell Mendonca (@mendonca

Russell Mendonca

170 posts

Russell Mendonca

@mendonca_rl

World models for robotics @GoogleDeepMind Prev - Optimus AI @Tesla, PhD student @CMU_Robotics

Joined February 2020

Pinned
Russell Mendonca
@mendonca_rl
May 19
Excited for the potential of this paradigm for robotics!
Google DeepMind
@GoogleDeepMind
May 19
We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video. It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵
00:00
1K
Russell Mendonca
@mendonca_rl
May 14, 2025
The sim2real RL pipeline we’ve built scales to many different challenging motions. This tech will soon be extended to useful manipulation tasks.
Tesla Optimus
@Tesla_Optimus
May 14, 2025
Was just getting warmed up
00:00
56K
Russell Mendonca
@mendonca_rl
Oct 7, 2025
Many of these model improvements will be directly useful for Optimus as well as we unify architectures. Both robots need to very efficiently compress video context to make decisions.
Ashok Elluswamy
@aelluswamy
Oct 7, 2025
FSD 14.1, the first in the v14 series, has officially started rolling out to customers! Many follow up releases, with significant improvements, are in the works. These should ship through the rest of this year. Enjoy, and looking forward to your feedback!
121K
Russell Mendonca
@mendonca_rl
May 21, 2025
A single neural net has learned all these interaction skills, primarily from video. It has been very exciting to push on this effort for generalist models over the past few months as part of the team (shoutout to @Yi__Li and @ashishkr9311 ). We’re going to see continued
Tesla Optimus
@Tesla_Optimus
May 21, 2025
I’m not just dancing all day, ok
00:00
49K
Russell Mendonca
@mendonca_rl
May 13, 2025
Agility with RL!
Elon Musk
@elonmusk
May 13, 2025
🕺
00:00
25K
Russell Mendonca
@mendonca_rl
Apr 2, 2025
We're continuing to leverage RL for Optimus, coming soon for manipulation tasks as well! Come join us to build towards generalist robots, utilizing simulation and videos.
Elon Musk
@elonmusk
Apr 2, 2025
Accurate actuators accelerate automation
00:00
29K
Russell Mendonca
@mendonca_rl
Oct 1, 2024
Our CoRL 2024 paper shows Reinforcement Learning can allow robots to learn skills via real-world practice, without any demonstrations or simulation engineering. Rewards are provided using language/vision models, and mobility of robots enables autonomous exploration. 1/N
00:00
40K
Russell Mendonca
@mendonca_rl
Jun 6, 2025
Replying to @_milankovac_
Your passion was infectious. Learned a great deal from your holistic approach to building a humanoid product, with attention to detail on all parts of the stack. We will carry the mission forward!
15K
Russell Mendonca
@mendonca_rl
Dec 9, 2024
Was really rewarding pushing on getting Optimus to confidently walk outside the lab on challenging terrain, in my first couple of months! I am blown away by the drive, ambition, vision and resources of the team @Tesla_Optimus. Come join us to make robot learning sci-fi dreams a
Tesla Optimus
@Tesla_Optimus
Dec 9, 2024
Daily walks help clear your mind
00:00
15K
Russell Mendonca
@mendonca_rl
Aug 29, 2023
World models are promising for enabling general-purpose robots. But how do we train them since robot data is limited? Our solution: Shared world models on human videos and robots using affordances as the joint action space. Pre-train on human video, then fine-tune to robot tasks!
00:00
27K
Russell Mendonca
@mendonca_rl
Nov 28, 2024
These hands balance high controllability, reactivity and power, without blowing up design size. Very exciting ! In personal news, I recently completed my PhD from CMU, and have joined Optimus AI ! Would like to thank @pathak2206 for his guidance and mentorship.
Tesla Optimus
@Tesla_Optimus
Nov 28, 2024
Got a new hand for Black Friday
00:00
8.6K
Russell Mendonca
@mendonca_rl
Apr 22, 2025
Early steps in building a legion for the next level of data scaling !
Tesla Optimus
@Tesla_Optimus
Apr 22, 2025
Me, Robot
2.6K
Russell Mendonca
@mendonca_rl
Apr 22, 2025
Really impressive generalization results, more evidence that data scaling with powerful ML models will work for robotics.
Sergey Levine
@svlevine
Apr 22, 2025
π-0.5 is here, and it can generalize to new homes! Some fun experiments with my colleagues at @physical_int, introducing π-0.5 (“pi oh five”). Our new VLA can put dishes in the sink, clean up spills and do all this in homes that it was not trained in🧵👇
00:00
3.7K
Russell Mendonca
@mendonca_rl
Aug 7, 2025
End to end approaches scale best. Direct from vision.
Skild AI
@SkildAI
Aug 6, 2025
Replying to @SkildAI
Do you know how many steps are between the street and your apartment? Humans, unlike today's robots, do not build 3D terrain maps first but instead navigate effortlessly by seeing & reacting in the moment. Skild Brain operates directly from vision!
00:00
5.2K