Anima Anandkumar

Thank you @cvprconference.bsky.social for hosting my
IEEE Kiyo Tomiyasu award for bringing AI to scientific domains with Neural Operators and physics-informed learning. The future of science is AI+Science!
corporate-awards.ieee.org/award/ieee-k...

🚨We propose EquiReg, a generalized regularization framework that uses symmetry in generative diffusion models to improve solutions to inverse problems. arxiv.org/abs/2505.22973

@aditijc.bsky.social, Rayhan Zirvi, Abbas Mammadov, @jiacheny.bsky.social, Chuwei Wang, @anima-anandkumar.bsky.social 1/

The Roots of Neural Network: How Caltech Research Paved the Way to Modern AI — Caltech Magazine Tracing the roots of neural networks, the building blocks of modern AI, at Caltech. By Whitney Clavin

Thank you @caltech.edu for including me in the history of AI. It starts with Carver Mead, John Hopfield and Richard Feynman teaching a course on physics of computation. Not many are aware that the main AI conference, NeurIPS, started at @caltech.edu

magazine.caltech.edu/post/ai-mach...

Check out our new preprint 𝐓𝐞𝐧𝐬𝐨𝐫𝐆𝐑𝐚𝐃.
We use a robust decomposition of the gradient tensors into low-rank + sparse parts to reduce optimizer memory for Neural Operators by up to 𝟕𝟓%, while matching the performance of Adam, even on turbulent Navier–Stokes (Re 10e5).

TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training Scientific problems require resolving multi-scale phenomena across different resolutions and learning solution operators in infinite-dimensional function spaces. Neural operators provide a powerful fr...

Thanks to my co-authors David Pitt, Robert Joseph George, Jiawwei Zhao, Cheng Luo, Yuandong Tian, Jean Kossaifi, @anima-anandkumar.bsky.social, and @caltech.edu for hosting me this spring!
Paper: arxiv.org/abs/2501.02379
Code: github.com/neuraloperat...

YouTube video by Google for Developers Science in the age of AI

It was an honor to be part of Google IO Dialogues stage and talk about AI+Science.

AI needs to understand the physical world to make new scientific discoveries.

LLMs come up with new ideas, but bottleneck is testing in real world.

Physics-informed learning is needed

youtu.be/NYtQuneZMXc?...

Indian American professor Anima Anandkumar on developing AI for new scientific discoveries Learn how Indian American professor Anima Anandkumar is revolutionizing the world of artificial intelligence to drive new scientific discoveries. Explore her cutting-edge research and innovative appro...

In a recent interview I talk about what it takes for AI to make new scientific discoveries. tldr: it won’t be just LLMs. www.newindiaabroad.com/english/tech...

YouTube video by EO Caltech AI Professor: The One Skill AI Can't Replace | Anima Anandkumar

Thank you EO for coming to @caltech.edu interviewing me on #ai I talk about the need to keep being curious and use AI as a tool, rather than being afraid of AI. I talk about AI for scientific modeling and discovery, and training the first high-resolution AI-based weather model. youtu.be/FIxLJVthW6I

We have released VARS-fUSI: Variable sampling for fast and efficient functional ultrasound imaging (fUSI) using neural operators.

The first deep learning fUSI method to allow for different sampling durations and rates during training and inference. biorxiv.org/content/10.1... 1/

Rayhan Zirvi is presenting our paper "Diffusion State-Guided Projected Gradient for Inverse Problems" at #ICLR2025! Joint work with @anima-anandkumar.bsky.social 1/

paper: openreview.net/pdf?id=kRBQw...
code: github.com/Anima-Lab/Di...
website: diffstategrad.github.io

Collage with 20 trailblazing Women of AI- Anima Anandakumar, Ayanna Howard, Cynthia Breazeal, Cynthia Rudin, Daphne Koller, Devi Parikh, Doina Precup, Fei-Fei Li, Hanna Hajishirzi, Joelle Pineau, Joy Buolamwini, Latanya Sweeney, Leslie Kaelbling, Margaret Mitchell, Melanie Mitchell, Niki Parmar, Rana el Kaliouby, Regina Barzilay, Timnit Gebru, Yejin Choi

#WomensHistoryMonth: Honoring trailblazing #WomenOfAI whose research has made an impact on the current #AI/ML revolution incl. @anima-anandkumar.bsky.social @timnitgebru.bsky.social @mmitchell.bsky.social @deviparikh.bsky.social @ajlunited.bsky.social @yejinchoinka.bsky.social @drfeifei.bsky.social

How does the brain integrate prior knowledge with sensory data to perceive the world?

Come check out our poster [1-090] at #cosyne2025:
"A feedback mechanism in generative networks to remove visual degradation," joint work with Yuelin Shi, @anima-anandkumar.bsky.social, and Doris Tsao. 1/2

Thank you, IEEE, for the honor! AI+Science is here to stay. I started working on this seriously after I joined @caltech.edu in 2017. We grounded our work in principled foundations, such as Neural Operators and physics-informed learning, for accelerating modeling and making scientific discoveries.

LeanAgent: Lifelong Learning for Formal Theorem Proving Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existing approaches involv...

LeanAgent: Lifelong learning for formal theorem proving. ~ Adarsh Kumarappan, Mo Tiwari, Peiyang Song, Robert Joseph George, Chaowei Xiao, Anima Anandkumar. arxiv.org/abs/2410.06209 #LLMs #ITP #LeanProver #Math

LeanAgent: Lifelong Learning for Formal Theorem Proving Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existing approaches involv...

We are excited to share our #ICLR2025 paper on LeanAgent: the first lifelong learning agent for formal theorem proving in Lean. It achieves exceptional scores in stability and backward transfer.
arxiv.org/abs/2410.06209 github.com/lean-dojo/Le...

Thank you for Time 100 AI impact award time.com/7212504/time...

Anima AI + Science Lab

2024 was a pivotal year for ai+science. Here’s my research summary tensorlab.cms.caltech.edu/users/anima/...

GitHub - neuraloperator/CoDA-NO: Codomain attention neural operator for single to multi-physics PDE adaptation. Codomain attention neural operator for single to multi-physics PDE adaptation. - neuraloperator/CoDA-NO

Code: github.com/neuraloperat...

The architecture shows strong generalization capabilities, being able to adapt to new physical variables and geometries not seen during training, while maintaining discretization convergence properties that make it resolution-agnostic.

Using a two-stage approach of self-supervised pretraining followed by few-shot supervised finetuning, CoDA-NO outperforms existing methods by over 36% on these challenging tasks.

CoDA-NO extends transformer architecture concepts like positional encoding, self-attention, and normalization to function spaces, allowing it to learn representations of different PDE systems with a single model.
We demonstrate CoDA-NO's effectiveness through experiments on complex multiphysics.

Unlike existing approaches that are limited to fixed sets of variables, CoDA-NO can handle varying combinations of physical variables by tokenizing functions along their codomain space.

Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs Existing neural operator architectures face challenges when solving multiphysics problems with coupled partial differential equations (PDEs) due to complex geometries, interactions between physical va...

Excited to present our work on CoDA-NO at #NeurIPS2024 We develop a novel neural operator architecture designed to solve coupled partial differential equations (PDEs) in multiphysics systems. Paper: arxiv.org/abs/2403.12553

Hello blue sky!