seems like astra solved robotics ezpz

(part 2) I asked people: "which robotics labs and startups have the highest talent density?" Full list: frontierlist.com/robotics-ta… 1 vote each: - Amazon FAR (@pabbeel, @peterxichen, @rocky_duan) - Antim Labs (@Shreyko, Viswajit Vinod Nair) - Bedrock Robotics (@bsofman, @kevinmpeterson1, Ajay Gummalla, Tom Eliaz) - Build AI (@patrickrim, @eddybuild, @jonathanjia05, @zikangjiang) - Dimensional (@stash_pomichter) - Dream Labs (@jang_yoel + 3 in stealth) - Enact (@jamesw_stevens, @govindchada) - Eye Candy Robotics (@Mankaran32, @_raghuvamsi, Alqama Shaikh) - Foundry Robotics (@adarshkulkarni) - GDM Robotics (@parada_car88104) - Hark (@adcock_brett) - Medra (@michellearning) - microagi (@bercankilic, @YoanIlievX, @antonwontonnn, Nico Nussbaum, Artjem Weissbeck) - Mimic (@stefan_weirich, @elvisnavah, @GravertStephan, @forraibotics) - NVIDIA GEAR Lab (@DrJimFan, @yukez) - Pantograph (@apagajewski, @_kelsey_pool) - Reward AI (@zipengfu, @chenwang_j) - RobbyAnt (Xing Zhu, Yujun Shen, Yongtao Huang) - Runway (GWM) (@c_valenzuelab, @agermanidis, @matamalaortiz) - Somana - Trener Robotics (Asad Tirmizi, Lars Tingelstad) - Ultra (@JonMSchwartz, Max Friefeld, @chetan_, Oliver Ortlieb) - Unitree (Wang Xingxing) - Vision Lab (@JamesKuj_OG, Zhichu Ren, @zwbgood6) - Walden Robotics (@RussTedrake, @Ben_Burchfiel, Siyuan Feng, @RaresAmbrus, @adnothing, Kerri Fetzer-Borelli, Dave Johnson) - Watney Robotics (@rgannon_, Sean Cheong) - Xaba (Massimiliano "Max" Moruzzi)

my sides: in orbit

lmaoing, hungarians need one with Zoltán Mucsi tho (knowers will know)

simcucks smh

i would be surprised if anyone in multimodal/robot learning would be impressed by these nothingburger demos this is a cute experiment to run but thats about it

the field in a nutshell

>most on the frontier figured out icl already my sides: in orbit

I wonder who can do it

the special type of models worth to fight the borrow-checker for: today, @mimicrobotics is launching FLUX-mimic, co-built with @bfl_ai ‘s FLUX 3. check out our blog: mimicrobotics.com/blog/intro…

I remember when we started working on this, it seemed so far-fetched. Now FLUX-mimic, built together with @bfl_ml, is being tested and deployed with @AudiOfficial

Introducing FLUX-mimic, a next-generation Video-Action Model for general purpose dexterity, developed in partnership with @bfl_ai. Late last year we published mimic-video and introduced Video-Action Models (VAM): a new family of robotics foundation models built on top of video generation models. We showed that robot control reduces to visual prediction, and that robot capability is downstream of improvements in video modeling accuracy. The obvious implication was that advances in the video modeling frontier would directly translate to increased capabilities in end-to-end robot learning. FLUX-mimic is that thesis at frontier scale: We've applied our VAM architecture to the strongest video backbone available today, FLUX 3 from Black Forest Labs, and trained it on data from our own robots and wearables. General-purpose dexterity, running on a single GPU on premises. Because the model already understands world dynamics, it needs far fewer demonstrations to learn a new task. This is game-changing for our mission to deploy robots to factory floors, where industrial robot data is scarce and expensive to collect. We're now testing and deploying FLUX-mimic with manufacturing leaders like @Audi, on complex, multi-step manipulation long considered impossible for conventional automation.

Stat monster

(maybe not so) hot take: robotics is also a sw infra problem, not “just” a learning/data/hardware problem. Today, we’ve shared a glimpse into our take: truly zero copy, no serialization/deserialization. This is what it unlocks: mimicrobotics.com/blog/solvi… All rust btw

From day one, mimic has been focused on a single goal: general-purpose dexterous manipulation. Today we're proud to announce the mimic hand M1 and the mimic wearable U1. We believe the only way to solve dexterous manipulation at scale is by going full-stack at the frontier of physical AI, building every layer ourselves around one fixed point, the human hand. The M1 is a highly backdrivable, tendon-driven hand that covers the full range of human capability, from heavy payloads to fine manipulation.

A few months ago, I travelled to Zurich together with @NVIDIArobotics to spend time inside one of Europe's most exciting robotics startups... @mimicrobotics! Their mission? To solve one of the hardest problems in robotics: human-level dexterity. Because before robots can replace physical work, they first need to master the human hand. In this episode, we go behind the scenes with the team building AI-powered robotic manipulation, discuss why dexterity is still one of the biggest bottlenecks in automation, and explore what it will take to bring truly capable robots into factories. Mimic Robotics is part of the NVIDIA Inception, a program for startups and VCs, and is leveraging Cosmos to advance AI-powered robot learning. If you're interested in Physical AI, robotic manipulation, and where this industry is actually heading, I think you'll enjoy this one. Timestamps: 0:00 Inside Mimic Robotics 0:24 Building the future of robot manipulation 1:19 The mission behind Mimic Robotics 1:35 The AI powering autonomous robots 2:14 Why Mimic chose NVIDIA Cosmos 2:34 Video foundation models vs. traditional robotics 2:46 Building a multidisciplinary robotics team 3:24 Bridging customers and cutting-edge AI 4:40 Why Zurich is the perfect robotics hub 5:20 Europe vs. America: Scaling a robotics startup 6:30 Bringing generative AI to factory robots 6:49 The race to build Europe's robotics hyperscaler ♻️ Know someone working in robotics? They'll probably want to see this.

Robotics fundamentally involves understanding the dynamics of how things change in the world in response to action and force. This is impossible to learn from static images; instead, it’s far more effective and more data-efficient to learn from video. @elvisnavah joins us to talk about @mimicrobotic. One of the key findings from mimic-video is that pretraining on webscale video allows robots to learn physics priors; as a result, policies train faster, generalize better, and are capable of more impressive dexterity, versus training on static images or image-language pairs as per a VLM. Watch Episode #81 of RoboPapers with @micoolcho and @chris_j_paxton to learn more!

With mimic-video, we were among the very first to propose Video-Action Models for robotics. Today, we are open-sourcing the recipe.