Transforming cutting-edge research into physical AI products. Leading Product, Hardware & Data Collection at mimic.
Zurich
Joined March 2015
- Tweets24
- Following177
- Followers51
- Likes38
Stephan Gravert retweeted
FLUX 3 is the strongest world model in the world.
FLUX 3 is #1 on Physics-IQ, @GoogleDeepMind's benchmark for physical world understanding in video models.
How Physics-IQ works: given the start of a real filmed experiment, can a model predict what physically happens next? Tests span fluid dynamics, optics, solid mechanics, magnetism and thermodynamics, covering how liquids flow, light behaves and objects interact.
In most cases, we substantially outperform all other frontier models, Seedance 2.5, MiniMax H3, Gemini Omni 1.1 Flash, Veo 3.1 and Sora 2, Cosmos3.
The FLUX 3 base model outperforms all other foundation models, while FLUX 3 paired with a physics verification layer scores even higher.
The FLUX 3 backbone, with its strong physics understanding, gives FLUX 3 Action it’s strong action prediction for robotics, while also giving FLUX 3 Video physically accurate motion when you’re creating content, making ads, films and product shots.
Stephan Gravert retweeted
Two years later our first video model - FLUX 3 Video - is finally released🥹. This is such a strong, fun and versatile model made by the best team in the world @bfl_ai. We will add further variants and generation from references in the near future. I am also super excited about the upcoming open weight, action prediction and image variants of FLUX 3.
Stephan Gravert retweeted
Four years ago, in the early days of my PhD, I was obsessed with Stable Diffusion, and with the work of @robrombach, @pess_r, @andi_blatt and their team in image generation. You could say I had one north star: take these generative techniques and bring them to robotics.
Today, it feels unreal to announce @mimicrobotics' official collaboration with @bfl_ai and to reveal FLUX-mimic, our next-generation Video-Action Model for general purpose dexterity.
The bet behind it: control reduces to visual prediction. A model that can predict how a scene will unfold has already learned the physics of manipulation. So we built our Video-Action Model architecture on top of FLUX 3, the strongest video backbone available today.
We're already testing and deploying it with manufacturing leaders like @AudiOfficial, on complex manipulation long considered impossible for conventional automation. FLUX-mimic is the culmination of years of work: the promise of true multimodality extended beyond the visual, into the domain of action. A new bet on general-purpose manipulation.
And we're just getting started.
Stephan Gravert retweeted
Introducing FLUX 3.
One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style.
FLUX 3 Video is now available in early access (link below).
Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.
Stephan Gravert retweeted
That's the way 🎶 uh-huh uh-huh 🎶 it should be:
Stephan Gravert retweeted
I had a sneak peek last week, during my second visit to MIMIC HQ in Zurich
The handshakes with the U1 glove and the M1 robot hand felt identical. Though M1 has a stronger grip than Stephan (he skips forearm days I'm told)
The blog is a must read to understand the rationale behind the design decisions and requirements
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.
Stephan Gravert retweeted
Video action models are data efficient and allow robots to learn complex dexterous tasks. Learn more in our episode with @elvisnavah of @mimicrobotics ->
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!