Todor Davchev

417 posts

Todor Davchev banner
Todor Davchev

Todor Davchev

@tdavchev

Senior Research Scientist @GoogleDeepMind | views are my own

London, UK Katılım Ekim 2010
418 Takip Edilen749 Takipçiler
Sabitlenmiş Tweet
Todor Davchev
Todor Davchev@tdavchev·
Ever wondered how to combine model free RL and LfD for a gentle, sample efficient robot learning in real time on contact-rich manipulation tasks? Excited to finally get to share Residual LfD arxiv.org/pdf/2008.07682…, a project I started during the AI residency at @Theteamatx 1/4
English
1
10
37
0
Todor Davchev retweetledi
Konstantinos Bousmalis
Konstantinos Bousmalis@bousmalis·
Very excited to be working together with our friends at Agile Robots to bring Gemini Robotics breakthroughs to their incredibly capable and reliable hw and to solve real problems in real environments!
Google DeepMind@GoogleDeepMind

Google DeepMind 🤝 Agile Robots Our new research partnership will integrate the Gemini foundation models with their hardware to help build the next generation of more helpful and useful robots. Find out more → goo.gle/4lKu7de

English
0
1
6
728
Todor Davchev retweetledi
Google DeepMind
Google DeepMind@GoogleDeepMind·
Google DeepMind 🤝 Agile Robots Our new research partnership will integrate the Gemini foundation models with their hardware to help build the next generation of more helpful and useful robots. Find out more → goo.gle/4lKu7de
Google DeepMind tweet media
English
61
228
1.8K
320K
Todor Davchev retweetledi
INSAIT Institute
INSAIT Institute@INSAITinstitute·
🚀 INSAIT makes an impact at @ICCVConference! With more than 10,000 participants, ICCV is the world’s leading conference in AI and computer vision - and INSAIT’s booth has become one of its most vibrant spots. Hundreds of researchers, industry leaders, and students stopped by to discover what INSAIT is all about and to connect with our team. 🤖 From cutting-edge robotics and embodied AI to next-generation foundation models, visitors experienced firsthand how INSAIT is pushing the boundaries of global AI research. 🇧🇬 We’re proud to represent Bulgaria on the world stage - proving that world-class deep tech innovation thrives right here in Sofia. #ICCV2025 #INSAIT #AI #ComputerVision #Research #DeepTech #Bulgaria #Robotics
INSAIT Institute tweet mediaINSAIT Institute tweet mediaINSAIT Institute tweet media
English
0
3
14
796
Todor Davchev retweetledi
Konstantinos Bousmalis
Konstantinos Bousmalis@bousmalis·
You have to watch this! For years now, I've been looking for signs of nontrivial zero-shot transfer across seen embodiments. When I saw the Alohas unhang tools from a wall used only on our Frankas I knew we had it! Gemini Robotics 1.5 is the first VLA to achieve such transfer!!
English
21
49
334
119.4K
Todor Davchev
Todor Davchev@tdavchev·
GR1.5 can do the entire NIST Board 2 in one go in addition to the incredible other stuff you see online!
English
1
2
17
4.6K
Todor Davchev retweetledi
Ksenia Konyushkova
Ksenia Konyushkova@ks_konyushkova·
Meet Gemini Robotics 1.5! Our ER model brings embodied reasoning to the real world. It understands high-level goals like "pack ingredients for mushroom risotto" with planning & success detection. Also, check out the cool "active vision" behavior – observing the action up close!🔍
English
0
6
15
3.8K
Todor Davchev
Todor Davchev@tdavchev·
Observability of the state space is truly important for robotics. Yet, we don't always get to navigate easy to observe spaces in our everyday life. That is why active vision is so important on our path to achieving physical intelligence. @GoogleDeepMind GR1.5 shows first signs!
Konstantinos Bousmalis@bousmalis

One of the coolest features in our newest release for Gemini Robotics 1.5 was using the wrist camera of one of the arms of our bi-arm Franka robot for active vision! Without this capability the model would not have enough visibility to solve some of our most dexterous tasks.

English
0
0
2
301
Todor Davchev retweetledi
Konstantinos Bousmalis
Konstantinos Bousmalis@bousmalis·
One of the coolest features in our newest release for Gemini Robotics 1.5 was using the wrist camera of one of the arms of our bi-arm Franka robot for active vision! Without this capability the model would not have enough visibility to solve some of our most dexterous tasks.
English
3
15
89
5.2K
Todor Davchev
Todor Davchev@tdavchev·
Did we tell you that our GR1.5 model can now do this: youtu.be/LUroyeZg5ME?si… We post-trained @GoogleDeepMind new GR1.5 model on the NIST Board 2 and we were surprised to see it solving all tasks reliably enough to video them in one go :)
YouTube video
YouTube
English
1
2
6
1.7K
Todor Davchev retweetledi
Peng Xu
Peng Xu@sippeyxp·
After you check out the #Gemini Robotics demo in #CoRL2025. Please also come to the Franka booth to see a finetuned Gemini Robotics On Device model in action. The model is finetuned from ~700 episodes using a hosted finetuning service available to the Trusted testers. Sign up for the program goo.gl/GDMR-TTP
Peng Xu tweet media
English
4
11
86
7.9K
Todor Davchev
Todor Davchev@tdavchev·
What a day it was today, we presented our GR1.5 and did live demos all day long @GoogleDeepMind booth at #CoRL2025 - come by tomorrow and play with our robots! 🤖🦾🦾
Todor Davchev tweet mediaTodor Davchev tweet mediaTodor Davchev tweet media
English
0
3
18
1.8K
Todor Davchev retweetledi
Peng Xu
Peng Xu@sippeyxp·
#DeepMind robotics has a live robot demo to show case our #Gemini robotics model in #CoRL2025. Come to our booth to check it out!
Peng Xu tweet mediaPeng Xu tweet media
English
2
12
125
8.1K
Todor Davchev retweetledi
Ted Xiao
Ted Xiao@xiao_ted·
We are living through the inflection point where general robotics evolves from cute academic sub-field to a ubiquitous technology. For those passionate about realizing this dream, consider joining my team at Google DeepMind! If you believe in the trends that have powered frontier model intelligence scaling, the robotics team at Google DeepMind is uniquely positioned: SOTA multimodal frontier model where real-world intelligence is a top priority, unmatched scale of compute + data + operations for robotics, world-class research team with enough breadth to simultaneously innovate on the bleeding edge for many emerging trends (humanoids, world models, VLAs, data scaling, dexterity, simulation... the list goes on!) It has been an opportunity of a lifetime to push on robotics + AI with colleagues that inspire me every day. We are expanding our team with many roles in both MTV and LON: Research Scientist: lnkd.in/g47zS2Xz Applied ML SWEs: lnkd.in/gCmY69XQ Robotics Engineering: lnkd.in/gDt6CeAq
English
5
8
106
8K
Todor Davchev retweetledi
Zoubin Ghahramani
Zoubin Ghahramani@ZoubinGhahrama1·
Google DeepMind has been leading the revolution in Foundation Models for Robotics. Come join us. We are hiring!
Carolina Parada@parada_car88104

It takes a village to build an awesome 🦾 🧠 . We are #hiring! Come transform robotics at Google DeepMind. I've received a lot of request for applied and engineering roles. Indeed we are hiring for those too! Robotics engineering: lnkd.in/gDt6CeAq Applied ML SWEs: lnkd.in/gCmY69XQ Research Scientist: lnkd.in/g47zS2Xz

English
11
29
508
55.2K
Todor Davchev retweetledi
Sean Kirmani
Sean Kirmani@SeanKirmani·
I am at @icmlconf! My co-organizers and I will be hosting a workshop on Building Physically Plausible World Models! Please reach out if you are here and would like to chat. physical-world-modeling.github.io
English
0
1
30
1.9K
Todor Davchev
Todor Davchev@tdavchev·
Don't miss out to learn ab out our newest hierarchical RL solution, presented by @samianholt - he led the project during his internship!
Sam Holt @ NeurIPS 2025@samianholt

Thanks @m_wulfmeier ! 🚀 If you're at ICML and interested in hierarchical RL, evolution strategies, and high-frequency robot control, please check out my EvoControl paper from my internship at @GoogleDeepMind . 🗓️ Main conference presentation: Thu 17 Jul, 4:30–7:00 pm PDT, West Exhibition Hall B2-B3 (#W-401) 📄 Latest link: openreview.net/pdf?id=JAWKe4v… 📽️ Video: icml.cc/virtual/2025/p… I’m also presenting other work on LLM agents & in-context planning—more details in my pinned tweet: x.com/samianholt/sta… Huge thanks to my incredible collaborators: @m_wulfmeier , @FranceRomano , @tdavchev , Dhruva Tirumala, @erikfrey , Ben Moran, @atiliscen , Antoine Laurens, @yixin_lin_ , Nicolas Heess Feel free to DM me to connect at ICML—looking forward to meeting everyone! #MachineLearning #ReinforcementLearning #HierarchicalRL #Robotics #ICML #GoogleDeepMind #AI

English
0
0
0
147
Todor Davchev retweetledi
Google DeepMind
Google DeepMind@GoogleDeepMind·
We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵
English
108
542
2.6K
818.2K
Todor Davchev retweetledi
Jeff Dean
Jeff Dean@JeffDean·
Building on more than 10 years of robotics research and engineering at @GoogleDeepMind, @GoogleResearch and @GoogleAI, we're delighted to announce our Gemini Robotics On-Device system. A really capable vision-language-action model that can run entirely without network access. ⬇️
Google DeepMind@GoogleDeepMind

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

English
29
73
527
54.1K