While AlphaFold3 improves upon the previous version, it still can't handle conformational changes during binding like our NeuralPlexer does. Paper: https://
nature.com/articles/s4225
6-024-00792-z
… Summary: https://
nature.com/articles/s4159
2-024-02249-y
…
"NeuralPLexer can predict both apo and bound forms of proteins and can
@animaanandkumar
-
NeuralPlexer Surpasses AlphaFold3 in Protein Binding Predictions
By
–
-
Neural Operators Featured in Latest Issue Cover
By
–
Fabulous cover for the issue featuring neural operators!
-
Voyager AI Project Inspires Altera Research Work
By
–
Great to see our Voyager work being an inspiration for Altera. https://t.co/basxeHY59Y https://t.co/8QJph2mTOn
— Prof. Anima Anandkumar (@AnimaAnandkumar) 8 mai 2024Great to see our Voyager work being an inspiration for Altera. https://
voyager.minedojo.org -
Galore optimization technique enhances model robustness
By
–
Our intuition is Galore could also help make it more robust @jiawzhao
-
Galore Low-Rank Pretraining Impact on Model Training
By
–
Have you explored how this would be affected by low-rank pretraining approaches such as Galore? https://
arxiv.org/abs/2403.03507 -
AI Transforms Weather Forecasting Beyond Traditional Models
By
–
It was energizing to be part of @WHOSTP45 @NOAA workshop on #AI + #weather We have come a long way. When I started working on this more than three years ago, many weather scientists were skeptical whether AI could replace weather models which have been developed for decades. The
-
Nvidia Internship Follow-up Work by Jason Ma
By
–
Really nice follow up of the earlier work that @JasonMa2020 did during his internship in my team at Nvidia. https://t.co/eEDGnT0c5D
— Prof. Anima Anandkumar (@AnimaAnandkumar) 3 mai 2024Really nice follow up of the earlier work that @JasonMa2020 did during his internship in my team at Nvidia.
-
Lean Co-pilot Reduces Effort for Theorem Proving Tasks
By
–
Our recent Lean Co-pilot significantly reduces human effort needed for theorem proving in Lean
-
Lean Copilot Automates Over 80% of Mathematical Proof Steps
By
–
We have now posted an expanded version of our Lean Co-pilot paper and updated the code base. https://
arxiv.org/abs/2404.12534 https://
github.com/lean-dojo/Lean
Copilot
…
The credit goes to @p_song1 for driving this effort.
Our latest experiments show that our co-pilot can automate >80% of the proof steps -
Neural Operators and Physical Grounding in AI Models
By
–
Thank you @shiringhaffary for covering my @TEDTalks in @business and neural operators for building physical understanding into #AI models. Language and multi-modal models lack physical grounding. models like Sora and some of the robotics models may get some of the physics