Fantastic to see this innovative work by @Dafidofff and @davidmknigge on Equivariant Neural Fields. Creative and refreshing perspective on equivariant representation learning and neural fields. Worth a read and follow!
@wellingmax
-
New AI-Driven Carbon Capture Materials Startup Launch
By
–
I can’t wait to get started with my co-founder @ac_edwards_1 and our top-notch team of experts across ML, chemistry and engineering to design new materials for carbon capture with AI. I am confident we can make a positive impact on the world!
-
Improved Flow Matching Method for Discrete Data
By
–
Great new paper by @FEijkelboom on an improved flowmatching method for discrete data. https://t.co/uFEzQmi5xU
— Max Welling (@wellingmax) 14 juin 2024Great new paper by @FEijkelboom on an improved flowmatching method for discrete data.
-
Simple Learning Rules Can Produce Sophisticated Emergent Behavior
By
–
I think putting it that way is a fallacy. Simple learning rules can result in sophisticated emergent behavior. If you ask for a joke about a particular person it comes up with a pretty funny joke. Quite witty. It needs to understand high level concepts such as humor for that.
-
OpenAI’s Closed Ecosystem Contradicts Open Values Amid AI Race
By
–
The irony: “Open”AI has closed down the AI ecosystem. But we should have no illusions that industry just automatically aligns with academic values, certainly not in the middle of an AI arms race.
-
AI and Climate: Prioritizing Real Issues Over Distractions
By
–
It distracts from the real issues we have to solve, both AI related and climate related.
-
VAE with Phase Degrees of Freedom Achieves Unsupervised Object Segmentation
By
–
Sindy strikes again with an oral at Neurips. The truly amazing thing for me was that if you train a VAE unsupervised with addional internal phase degrees of freedom it will automatically align phases within objects and segement them. 🫨 https://t.co/cD3k9RDjJy
— Max Welling (@wellingmax) 23 novembre 2023Sindy strikes again with an oral at Neurips. The truly amazing thing for me was that if you train a VAE unsupervised with addional internal phase degrees of freedom it will automatically align phases within objects and segement them.
-
Equivariance in Machine Learning: Maurice Weiler’s Educational Guide
By
–
Check out this amazing blogpost by @maurice_weiler on equivariance. Besides an amazing researcher, Maurice is also a fantastic educator. No better source to learn equivariance IMO.
-
Maurice Weiler’s Equivariance Bible: Mathematics Physics AI
By
–
@maurice_weiler wrote an incredible bible on equivariance. You will not find a more thorough and richly illustrated introduction to the subject. It was a beautiful journey relating to concept in maths w/ Patrick Forré and to physics w/ @erikverlinde
. Grateful to be part of this. -
ChemAI Day: AI Applications in Chemistry Conference
By
–
Please join us for the ChemAI day on November 16. I am really looking forward to speaking and meeting other people who see the huge potential of AI for Chemistry. Register here: https://
acnetwork.nl/chemai