Kamyar Azizzadenesheli (@azizzadenesheli) 's Twitter Profile
Kamyar Azizzadenesheli

@azizzadenesheli

Research Staff @nvidia, x-prof at @Purdue #MachineLearning, #ArtificialIntelligence #NeuralOperators #AI+#Science

ID: 2587743478

linkhttps://kamyar.page calendar_today06-06-2014 19:03:06

1,1K Tweet

3,3K Followers

1,1K Following

Kamyar Azizzadenesheli (@azizzadenesheli) 's Twitter Profile Photo

We're releasing the public beta of #NeuralOperator, 1.0. A ground up #Python library containing neural operator architectures, datasets, examples, running codes, and algorithms for ML on functions. As a collective effort, we invite researchers, in particular in #AInScience,

Prof. Anima Anandkumar (@animaanandkumar) 's Twitter Profile Photo

2024 was a pivotal year for AI+Science. Our team made exciting contributions. Here are some highlights: tensorlab.cms.caltech.edu/users/anima/20… 1. Neural Operators as a unifying AI framework for modeling multi-scale processes. We got to write a perspective article in Nature Reviews Physics and released an

Prof. Anima Anandkumar (@animaanandkumar) 's Twitter Profile Photo

I agree with Jensen that the next wave of AI is physical understanding, especially the ability to model and simulate physics is essential. Watch my TED talk go.ted.com/animaanandkumar #CES #Nvidia #NVIDIAcosmos

David van Dijk (@david_van_dijk) 's Twitter Profile Photo

Excited to share our new preprint: COAST: Intelligent Time-Adaptive Neural Operators! 🌊 We introduce a novel neural operator that learns to dynamically and intelligently adjust time step sizes for modeling dynamical systems from data. 🚀 doi.org/10.48550/arXiv…

Kamyar Azizzadenesheli (@azizzadenesheli) 's Twitter Profile Photo

Human, mouse, monkey brain imaging, Ultrasound imaging is about the study of wave functions and their functional inversion, constituting a critical path to brain imaging. As a problem on function spaces, we introduce a novel #NeuralOperator technology for imaging, that is 1-

Kamyar Azizzadenesheli (@azizzadenesheli) 's Twitter Profile Photo

This work has been keeping me awake for quite sometime, The secret sauce behind Adam is its Signum. This is just mind consuming, great work Antonio Orvieto and Robert M. Gower 🇺🇦. It is also a great news for efficiency and MLSys communities.

Kamyar Azizzadenesheli (@azizzadenesheli) 's Twitter Profile Photo

We developed the foundations of diffusion model and posterior sampling on function spaces. We carefully extend Tweedie principle to function spaces which sits at the core of our methods. We provide techniques for functional regressions/reconstruction given partial sample

Kamyar Azizzadenesheli (@azizzadenesheli) 's Twitter Profile Photo

Stable-ChebNet Stable long range dependency is essential for physics, social network, and science, Technically, information needs to traverse effectively through out deep learning models without dissipating by due to lack of design. We propose a fundamentally

Stable-ChebNet  

Stable long range dependency is essential for physics, social network, and science,   

Technically, information needs to traverse effectively through out deep learning models without dissipating by due to lack of design.   

We propose a fundamentally
Prof. Anima Anandkumar (@animaanandkumar) 's Twitter Profile Photo

The best undergraduate and graduate research awards at  Caltech  commencement this year were presented to research on Neural Operators by my students Zongyi Li and Miguel Liu-Schiaffini. This recognition is a testament to their passion and dedication, and the impact