Research Scientist Intern @Meta 🤖 | PhD Student in 3D Vision @ETH_en | ETH AI Center Fellow | prev. VSR @Stanford

San Francisco, CA
Joined February 2012
Happy to share that SuperFlex is accepted to ECCV’26! 🇸🇪✨ SuperFlex as SuperDec is a feed-forward method for superquadric decomposition, but it achieves a huge jump in the reconstruction quality by incorporating deformable superquadrics and a novel loss function ✨
3
24
4
156
22,446
Elisabetta Fedele retweeted
Congratulations to Karl Deisseroth, winner of the 2026 Nobel Prize in physiology or medicine. The @StanfordMed & @StanfordEng professor of bioengineering and of psychiatry and behavioral sciences is a pioneering developer of optogenetics, a technique that uses light to control the behavior of cells.
85
809
58
6,263
157,370
Elisabetta Fedele retweeted
🤖 🚀 I am opening one fully-funded 2-year postdoc position to explore egocentric 4D scene representation and understanding for robot learning, with fantastic collaborators @FrancisEngelman and @antoniloq ⏰ Deadline: November 23rd, 23:59 🔗 lnkd.in/e4ZW5WrB
🤖 Made with AI
1
8
1
30
4,812
Elisabetta Fedele retweeted
Everyone's asking what humans are still worth in the age of AI. To me, it's the part of us that AI keeps flattening - our individuality. Yet I feel I'm constantly being sold a choice: extend myself with AI, or preserving my unique thoughts, tastes and opinions. What if I didn't have to choose? There is a future where we get the magic of feeling totally understood by the technology that serves us, while staying ourselves. In this future, the model of us -- our "second selves" -- must be owned by us. That's the future we want to live in, and one we're building at Aesona. The open, top-of-mind questions right now: 1. What's the right representation of a person and how should it evolve over time? 2. How do we measure individual-level alignment? How should you interact with the model to close gaps in what it doesn't yet know about you? 3. What should your second self refuse to say about you? How should the user create the right "disclosure policy" and how should it be enforced? If this sounds like a future you want to build, my DMs are open!
We should all be asking who — or what — owns our minds. A model that understands what makes you you can be incredibly enabling and deeply dangerous. That's why we think a "second self" — a model whose only job is to understand you and make your life better — must be owned by you. A faithful second self, in both senses, is the foundation of personal AI. Our founding thesis, below.
15
16
11
61
147,407
Elisabetta Fedele retweeted
In the afternoon, grab a coffee ☕️ and come chat with us at Poster #15 on **SuperFlex** ➡️ superflex3d.github.io
If you are at #ECCV26 you shouldn't miss @TaveGabriel and @FrancisEngelman presenting SuperFlex, our latest work on superquadrics! 📍: 3pm, poster #15 🌍: superflex3d.github.io
1
18
984
Elisabetta Fedele retweeted
This Saturday at #ECCV2026 (3pm - 5pm) come talk to us at our poster - SuperFlex - compact representation of pointclouds using deformable Superquadrics.
We added bending and tapering to superquadric reconstruction / decomposition. ➡️ big step forward in reconstruction quality Check out SuperFlex for compact & explicit 3D object/scene representations. @eccvconf #ECCV More details: superflex3d.github.io
6
24
1,718
Elisabetta Fedele retweeted
Last day of #ECCV2026! Here is where to find us today 🇸🇪✨
2
12
685
TLDR: SuperFlex as SuperDec is a feedforward method turning point clouds into superquadrics. It obtains more accurate reconstructions using an improved loss and deformations! We also show some initial work on obtaining these compact representations from partial inputs 👀🔜
1
306
🙏 this is the result of an amazing collaboration with @TaveGabriel @FrancisEngelman @TiagoNovello @mapo1 Leo Guibas @ETH_AI_Center
1
220
If you are at #ECCV26 you shouldn't miss @TaveGabriel and @FrancisEngelman presenting SuperFlex, our latest work on superquadrics! 📍: 3pm, poster #15 🌍: superflex3d.github.io
1
8
1
87
5,375
Elisabetta Fedele retweeted
We are ready for the fourth day of #ECCV2026! Here is where to find us today 🇸🇪✨
1
3
13
808
Elisabetta Fedele retweeted
We are ready for the third day of #ECCV2026! Check out our works at both poster sessions today 🇸🇪✨
3
12
606
Elisabetta Fedele retweeted
1/ today we're rolling out Muse, our new personal ai assistant. Muse is always-on, wicked fast, can use a browser, connect to your apps, and is designed to be secure. try it now: muse.ai.
686
516
464
6,597
12,757,533
Elisabetta Fedele retweeted
GPT 6 Astra is capable of orchestrating two robots juggling with one ball at least airborne throughout the exchange This is an actual MuJoCo physics simulation at 1x speed
25
62
14
674
80,674
Elisabetta Fedele retweeted
I fed GPT-6 Astra 9 crappy photos of my studio and it was able to understand the spatial arrangement, stitch them together and create a fully interactive 3D model of the space. Absurd. I'll link it below so you can check it out for yourself:
266
1,233
176
11,811
1,712,932
Elisabetta Fedele retweeted
Kicking off @eccvconf tomorrow morning in 📍MalmöMässan (Room B) with: 🔹9:10: Matthias Niessner @MattNiessner (TUM/SpAItial) 🔹9:40: Dima Damen @dimadamen (Bristol/Google) 🔹11:00: Carl Doersch @CarlDoersch (Google) 🔹11:30: Peter Kontschieder (Meta) ➡️opensun3d.github.io
1
10
27
2,489
Elisabetta Fedele retweeted
Part 5: 3D has tremendous value when making things in the physical world (engineering, manufacturing, construction, etc), because here the 3D model is the final deliverable, not an intermediate representation. 3D vision's role here is in allowing us to leverage abundant 2D data.
2
3
32
3,363
Elisabetta Fedele retweeted
The era of Physical AI is coming, and I firmly believe that embodied intelligence will not emerge from imitation learning alone. Just as humans first learn by observing the world and then build deeper understanding through interaction, the breakthrough moment for Physical AI will come through interactive learning. Real-world trial and error is too slow, expensive, and unsafe. To scale interactive learning, we need to recreate the richness of reality without being constrained by reality itself. We need simulated reality—a place where embodied intelligence can experience situations, make mistakes, learn from them, and try again millions of times before encountering them in the real world. I am incredibly excited to build @VeedaAI alongside my co-founders, @FidlerSanja and @HuanLing6 , and an extraordinary group of researchers and engineers. Together, we are developing the next generation of interactive foundation world models for Physical AI. There is no team I would rather take on this challenge alongside, and I couldn’t be more excited for what we’re going to build. veeda.ai
I’m incredibly excited to introduce @VeedaAI , which I co-founded with my incredible longtime collaborators @ZGojcic and @HuanLing6 . We started Veeda because we believe robotics will reshape the world—changing how we move people and goods, how we manufacture and build, and how we operate in the physical world. We also firmly believe that the scaling moment for Physical AI will come from robots learning through interaction with the world. Just like humans learn from interaction with their environments by trying, failing and trying again, until we succeed. And just like the capabilities of LLMs were truly unlocked when they started training in interactive environments and not only on vast amounts of internet text. For Physical AI, the central challenge is making this kind of interactive learning possible at scale. The real world is simply not a practical training ground for robots to learn through trial and error. It is unsafe, expensive, and time-consuming. To scale interactive learning, robots will need to learn in simulated reality. At Veeda, our sole mission is to build simulated reality for Physical AI. Our conviction is that this will become the critical infrastructure layer for all areas of robotics. As envisioned in pop culture, this means building “the Matrix” for Physical AI, where, through a virtual embodiment, robot intelligence can interact with an entirely virtual world in a million possible ways, learning from its own mistakes. We believe that World Models are the foundational technology that can make this possible. These generative models learn from massive amounts of sensor and physical-world data to reach the quality, diversity, and physical realism of the simulated reality that robots require. I could not be more excited to take on this challenge and build this transformative technology alongside an extraordinary team of engineers and researchers who have spent years working on some of the hardest problems across simulation, generative AI, 3D, robotics, and embodied intelligence. Together with our investors at @khoslaventures and @radicalvcfund , we intend to push the frontier of this technology and build the foundational infrastructure for interactive robotics learning and evaluation at scale. Come build this future with us. And to roboticists, help us understand what you need, we’re building this for you. veeda.ai
15
17
1
179
29,980
Elisabetta Fedele retweeted
Grip builds intelligent robots that pick the trash existing sorting machines can't. Robotic manipulation just started working. Foundation models can now grasp the deformable, entangled, never-before-seen objects that waste streams are full of, on hardware that's finally cheap enough to make the economics work. We install modular robotic cells and every pick makes the whole fleet smarter. We start with plastic contamination in organic waste, then expand to every stream where machines still leave the hard objects to humans. Grip is becoming the general manipulation platform for global waste infrastructure. Founded by robotics engineers from ETH Zürich. Backed by Y Combinator (S26).
52
76
21
628
189,325
I'm back in the Bay Area, where I joined @Meta as a Research Scientist Intern! 🤖✨ Couldn't be more excited to be back in this magical place - happy to connect if you're also around ☕️
18
3
165
8,710
Elisabetta Fedele retweeted
1/ I let @claudeai use the animoflow.ai API, and the result is an effectively infinite G1 locomotion dataset, rendered in a CAD apartment environment. Here's how:
13
23
1
202
19,957