Alberto
@taiuti
Followers
4K
Following
12K
Media
370
Statuses
1K
CEO & co-founder @reactorworld - prev 3D @skydioHQ, cofounder & CTO @lumalabsai, @apple on VisionPro - super hardcore multi theft auto san andreas player
San Francisco
Joined August 2010
Big update: I’m starting a new company. 6 months ago, @_bschmidtchen and I made a bet. What if entire worlds could be generated on the fly, pixel by pixel? World models are the next platform shift, and we saw it coming. Since then, we’ve: - secured major contracts across media
61
31
359
I completely agree. It's going to be a game changer. And you can try it right now, here:
creations.mtdv.me
The future of entertainment.
Pretty big deal to be able to deliver instantaneous video generation with time-to-first-frame under 100ms. Removing the latency that has always stood between an idea and the output. A fundamentally different speed of iteration.
4
0
24
For a century, video has been something you watch. World models make it something you inhabit. We're building for that shift. We're hiring: https://t.co/fPLciLaGRg
12
7
64
Come check it out. We’ll show an exclusive overview of Reactor. Thanks to @nebiusai for having us
Today at #NVIDIAGTC. Live demos at Nebius Booth 713 from teams building on Nebius AI infrastructure: 2 PM @swordhealth 2:30 PM Lynxkite, @biophytis 3 PM @NexlaInc 4 PM Reactor 5 PM Overworld Production AI. Real workloads. #GTC26
0
0
20
I cannot believe everyone is quoting an article that is so wrong, it says that avatar models are world models. Did you people read it or are you just riding the next cool wave?
AMI (Yann LeCun) is modeling physics. World Labs (Fei Fei Li) is modeling the physics objects of the world. Genie is modeling both. Really good analysis.
4
0
15
The World Models era is here. AI that understands the world, and lets you create and interact with new ones, all in real time. More soon.
9
3
57
This is the revenge of the dust3r approach.
The secret sauce? 🥫 We train on simple, synthetic "causal primitives": videos of toppling dominos, colliding balls, and swaying flowers. By randomly masking the "cause" or the "effect" during training, the model learns to propagate physical forces through time and space. (3/n)
0
2
7