Introducing humans on @flairAI_.🔥
Generate thousands of composable human models in various poses to sell your products! Target different demographics, and represent your audience in marketing campaigns.
RT and comment to try this feature in beta. Serving access codes today:)
Today in partnership with @emblebi, we’re releasing predicted structures for nearly all catalogued proteins known to science, which will expand the #AlphaFold database by over 200x - from nearly 1 million to 200+ million structures: https://t.co/GjVES2pBFY 1/
🌟 A star is born!
Behind the curtain of dust and gas in these “Cosmic Cliffs” are previously hidden baby stars, now uncovered by Webb. We know — this is a show-stopper. Just take a second to admire the Carina Nebula in all its glory: https://t.co/tlougFWg8B #UnfoldTheUniverse
I truly believe that anything and everything can be represented as a #vector with any number of features. Which I guess makes #LinearAlgebra the #BasisVector of all other branches of #Math & #Science 😉
We’re very excited to release the Open Catalyst 2022 (OC22) Dataset: Oxide Electrocatalysis!
Paper: https://t.co/9eLI9K3BeO
Dataset: https://t.co/eEqYoRIczQ
Blog: https://t.co/luocU8KUuW
1/n
Protein structure can be predicted from a single sequence alone with high accuracy.
@HelixonBio team have developed OmegaFold, achieving performance similar to RF and AF2's MSA versions. Only a single sequence is given as input. 1/5
Very happy to finally show our latest work: VCT, a transformer for video compression 🤖 We radically simplify the video compression setup by getting rid of motion prediction, warping, and residuals. Instead, a transformer learns to model temporal redundancies purely from data:
Our new paper on Meta Optimal Transport uses amortized optimization to predict initializations and improve optimal transport solver runtimes by 100x and more. With @CohenSamuel13@GiuliaLuise1@IevgenRedko
Paper: https://t.co/FTT3NxqJP9
JAX source code: https://t.co/qRsfyDGpK6
GraphGPS: with a few simple tricks we managed to scale Graph Transformers to much larger graphs and get SOTA in competitive benchmarks, e.g. 0.07 MAE on ZINC.
With @michael_galkin, @dom_beaini, @vijaypradwi, @mrguywolf
📝https://t.co/Hz5xtCJn0y
📜https://t.co/iyvNMRkCr7
🧵1/8
🗓 July 12 — Save the date!
Count down with us to the big reveal of Webb’s first full-color images and spectroscopic data: https://t.co/hyZAYXvwfN
Want a hint on how Webb will #UnfoldTheUniverse? Read more: https://t.co/tv4SBRv9xI
New paper! Torsional Diffusion for Molecular Conformer Generation!!
- novel toroidal diffusion & score model
- 1st ML method to outperform SOTA cheminformatics tools
- 100x faster than previous diffusion models
- 1st generalizable Boltzmann generator
https://t.co/s3WyFLYEYk 👇