Markus Wulfmeier
@m_wulfmeier
Followers
12K
Following
10K
Media
285
Statuses
2K
Large-Scale Robot Intelligence - Research @GoogleDeepMind European @ELLISforEurope - priors: @oxfordrobots @berkeley_ai @ETH @MIT
London, England
Joined December 2015
Imitation is the foundation of #LLM training. And it is a #ReinforcementLearning problem!. Compared to supervised learning, RL -here inverse RL- better exploits sequential structure, online data and further extracts rewards. Beyond thrilled for our @GoogleDeepMind paper!. A
10
68
373
Congrats @patricktresset (and @GoldsmithsUoL)! . Looking forward to learning more about how large language models like Gemini @GoogleDeepMind can enable and collaborate with artists.
I just signed. For the next 3 years, I will be a visiting research fellow in @GoldsmithsUoL 's computing department. Collaborating with @colormotor and others. certainly working on getting embodied AI to do silly things
0
0
1
A small nudge for a.#NeurIPS AC, a big improvement for review discussions! . I'm very impressed with reviewer uptake after sending quick reminders. If you're AC-ing for NeurIPS, send your reminders! It's worth it ๐.
0
1
16
'Google processed nearly a quadrillion AI tokens across all its products last month, which is more than double the number it processed in May.'. Quadrillion = 10^15.Googol = 10^100. Only x 10^85 missing. Maybe token is the right unit to measure here.
theverge.com
People who work in the AI industry think Google is quietly winning.
0
0
6
Gemini does! And so will Claude, ChatGPT, . Maybe it's time for LLM tooling to provide feedback on reviews before submitting!.
0
1
5
RT @heiga_zen: We're hiring @GoogleDeepMind APAC! ๐ฏ๐ต๐ฎ๐ณ. Seeking experts in multilingual, multicultural & multimodal AI to help shape the fโฆ.
0
59
0
RT @samianholt: Excited to share our new @icmlconf paper, "EvoControl". A hierarchical (bi-level) reinforcement learning (HRL) framework fโฆ.
0
3
0
One more talk at the EXAIT workshop you should not miss: . Wenhao Yu talks about foundations got scalable robot learning and #Gemini! @GoogleDeepMind. Thanks to @sukhijabhavy for organizing!.
Sadly unable to visit #ICML2025 but we have many fantastic colleagues and students joining! . Want to learn more about agents, LLM fine-tuning, exploration, CoT, reach out to @thsschmied!. Check out his @GoogleDeepMind internship paper at the EXAIT workshop!.
0
0
1
#Robotics is hard, and so is #AutonomousDriving! Massive congratulations to my friends at @Waymo for proving me wrong!. There was a time a couple years back when I was getting skeptical about the scale of both technological and societal challenges for scaling autonomy. Other.
100 million real world, fully autonomous miles driven on public roads. Thatโs more than 200 trips to the Moon and back. Thank you riders.
0
0
5
Sadly unable to visit #ICML2025 but we have many fantastic colleagues @GoogleDeepMind and students joining! . Want to learn more about exciting things happening in RL, inverse RL, and how to get robots to move, reach out to @MartinaZambelli this week!.
Excited to be attending #ICML2025 this week โ even more special that itโs happening right here in the city I now call home, Vancouver! Looking forward to connecting with friends and colleagues and catching up on all the great work being presented.
0
0
7
Sadly unable to visit #ICML2025 but we have many fantastic colleagues @GoogleDeepMind and students joining! . Want to learn more about hierarchical RL, evolution, high frequency robot control, reach out to @samianholt this week! . Check out his paper.
scholar.google.com
S Holt, T Davchev, D Tirumala, B Moran, Y Lin, A Laurens, A Iscen, E Frey, M Wulfmeier, F Romanoโฆ, International Conference on Machine Learning (ICML), 2025 - Cited by 3
Thanks for the shout-out, @m_wulfmeier! Thrilled to open-source the non-prehensile block reorientation setup from my @GoogleDeepMind internship, now part of MuJoCo Playground. By leveraging domain randomization and curriculum learning, we achieve smooth, compliant high-frequency
0
0
4
Sadly unable to visit #ICML2025 but we have many fantastic colleagues and students joining! . Want to learn more about agents, LLM fine-tuning, exploration, CoT, reach out to @thsschmied!. Check out his @GoogleDeepMind internship paper at the EXAIT workshop!.
Google announced LLMs are Greedy Agents on Hugging Face. Effects of RL Fine-tuning on Decision-Making Abilities
1
3
18
Independent on agreement of crossing the point just yet, we're getting close to cheap, large-scale evaluation. Scalable evaluation = scalable learning! What you can measure, you can optimize. Research as meta optimiser does this. RL, in the broadest sense, can automate it.
Reality is the ultimate eval . Threshold were our robots learn more by themselves than from expert demonstrations (teleop) was just passed by in silence, but I suspect in hindsight it will huge.
0
0
3
No reasonable LLM builds just on synthetic data, or just supervised data, or just RL . I'd be very surprised if we'd converge to that type of limit in robotics.
1
0
10
Imagine there'd be no text online to train language models, how would you make LLMs possible?.
2
0
5
RT @bodonoghue85: We're looking for people to join us to work on Gemini Diffusion and help revolutionize language modeling!. Details below:โฆ.
job-boards.greenhouse.io
0
43
0
Fully agree with "Grounding Intelligence in Movement"! This paper really brings home the importance of embodiment related modalities in AI - movement itself grounds intelligence for both machines & us. Segado et al @KordingLab .
arxiv.org
Recent advances in machine learning have dramatically improved our ability to model language, vision, and other high-dimensional data, yet they continue to struggle with one of the most...
1
2
12
Time to warm up to the perspective that robot actions are 'just' another modality for language models.
0
0
15
Large language and vision models alone don't solve the whole #robotics problem. But they surely have a massive impact on generalisation and robustness!. New scenes, new backgrounds, new objects, new people, new language and audio. Massive props to @ayzwah, @ColinearDevin,.
We took a robot to RSS in LA running our new Gemini Robotics On-Device VLA model. People interacted with the model with new objects and instructions in a brand new environment and the results were amazing!
0
0
7