Congratulations to @johannbrehmer @pimdehaan @TacoCohen ! Thanks for saving equivariance.
@wellingmax
-
Scaling Law Progress with Hope for Near-Term Resolution
By
–
We are on a scaling law. I hope this one ends soon though.
-
AlphaFold researcher questions missing citations for Nobel Prize work
By
–
Could the “guy who worked on Alphafold” saying “This paper sure saved our ass on that Nobel prize” come forward please? Maybe a citation would have been nice .
-
CuspAI Named Among Top 25 UK Startups to Watch
By
–
CuspAI made it to the top 25 UK Startups to watch!
-
AKOrN: Kuramoto Oscillators Replace Threshold Units in Neural Networks
By
–
AKOrN is here: https://
arxiv.org/pdf/2410.13821.
It replaces threshold units with generalized Kuramoto oscillators. It dynamically binds neurons, generates waves of activations, is adversarially robust, calibrated for uncertainty, and can reason. If you ask me: this is the next big thing! -
OMat24 Dataset Achieves New SOTA Equivariant MLFF Foundation Model
By
–
I am particularly excited about OMat24, a new dataset that resulted in a new (equivariant, ) SOTA MLFF foundation model. Congratulations to Larry Zitnick and team!
-
The Scaling Church: Making Everything Bigger as Solution
By
–
The scaling church: just make them bigger and everything will alright 🧐. https://t.co/9I8YYEtNZd
— Max Welling (@wellingmax) 13 octobre 2024The scaling church: just make them bigger and everything will alright .
-
GUD: Generative Unified Diffusion Model Inspired by Renormalization Group
By
–
Meet GUD: our new Generative Unified Diffusion model inspired by the Renormalization Group. It generalizes standard diffusion by a choice of basis, a prior and separate noise schedules per dimension. Main author Mathis Gerdes and w/ Miranda Cheng. https://
arxiv.org/abs/2410.02667 -
CuspAI Welcomes New Team Member Markus
By
–
Another key hire in CuspAI. Welcome to the team Markus! Looking forward to work together.