Our latest brain-to-image decoding model is now available on 🤗 HuggingFace:
"Dynadiff: Single-stage Decoding of Images from Continuously Evolving fMRI"
led by M Careil & @BenchetritYoha1:
- Paper: https://t.co/Qn5h80gY6I
- Github: https://t.co/ni6k50sKRR
- Thread: 👇
I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using @NVIDIAAIDev's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats.
The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens.
I plan to make a "first reactions/overview video". Tutorial after that.
For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture.
#3D #AEC #Computervision
https://t.co/Hc34XKQjfi
So I updated "Water" !
The sim is running in a single CPU thread.
It should work faster now, rendering optimized & WebAssembly SIMD support!
But seems like the speedup with wasm is only limited because of the heavily scattered memory access pattern 😇
Everything you love about generative models — now powered by real physics!
Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications.
Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: https://t.co/bEkIlCKqdf).
The Genesis physics engine and simulation platform is fully open source at https://t.co/DhBv7NdyqH. We'll gradually roll out access to our generative framework in the near future.
Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism.
We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fully automated data generation for robotics, physical AI and other applications.
Open Source Code: https://t.co/DhBv7NdyqH
Project webpage: https://t.co/SBNyhFB0yn
Documentation: https://t.co/3yuBoaealV
1/n
I just tried out playing Counter-Strike in a neural network on my MacBook. In my first run, it diverged into mush pretty quickly. The recording is sped up 5x.
Optimal transport flows define particle evolutions which are classical gradient flows over the positions of the particles. Pairwise interaction potentials are ubiquitous in physics, biology, and chemistry. Corresponds to non-local PDEs over the densities.
I remember seeing backprop as a senior in undergrad in the late 90s, frankly I couldn’t follow. Much of the prezi was tied to a specific architecture with sigmoids. It was only years later when I saw the modular approach did it make sense!