The Polymathic AI Collaboration. Shared account.
Joined September 2023
- Tweets78
- Following69
- Followers3.7K
- Likes52
1/ NMR is one of the most important tools for figuring out molecular structure that's used across chemistry, biology, materials science, and drug development.
Collecting the data is routine, interpreting it can take days, sometimes years 😮
We built an AI agent for this 🧵
On the rest of the tasks, we show that framing NMR elucidation as an agentic search is not only viable but competitive with modeling approaches trained on simulated data and/or tabulated peaks on a variety of small molecules with different environmental sample conditions.
(5/7)
Anthropic’s work starts from reported peak lists. But, that’s *not* how chemists work.
They start with FID data, which includes effects of impurities, solvents, and artifacts.
Only *after* solving the structure, chemists report a clean tabulated list of compound peaks.
(2/7)
Come check out the @FlatironInst booth #523 at #SC24 ! 🔥
Our own @rdMorel will give a talk on Wednesday at 2:45-3pm!
Are you a student looking for an internship this summer or fall?
Want to build foundation models for science in NYC?
Join us at @PolymathicAI at @FlatironInst!
forms.gle/io8ZQuEBxo9qM7x48
Blog: polymathic-ai.org/blog/mpp/
Paper: arxiv.org/abs/2310.02994
Code: github.com/PolymathicAI/mult…
We are hiring a software engineer or software-focused researcher to embark with us on this journey of changing how science is done with large foundation models!
Reach out if you are excited!
A large number of our team is at NOLA this week!
Find us : polymathic-ai.org/#team
Finally, check out our work on bringing multi-modal astronomical data into a common embedding at #AI4Science workshop!
Blog: polymathic-ai.org/blog/astro…
xitter.cf/liamhparker/status/171…
Excited to share some of our recent work at
@polymathicAI! With AstroCLIP we are bringing multimodal contrastive pretraining to astrophysics!
And got problems with numerics with LLMs?
Check out our xVal presentation at #AI4Science Workshop! where we discuss how to get efficient numeric encoding that generalizes well!
Blog: polymathic-ai.org/blog/xval/
xitter.cf/SiavashGolkar/status/1…
1/ Did you know LLMs like ChatGPT struggle with number manipulation and data analysis? They make up answers and fail to generalize.
Today I am excited to share xVal, a continuous and efficient number encoding scheme with better generalization performance.
polymathic-ai.org/blog/xval/
Check out our oral presentation of Multiple Physics Pretraining (MPP) at #AI4Science workshop!
MPP is a group of techniques for pretraining on a diverse set of time-dependent physics to learn models that can be fine-tuned for multiple problems.
xitter.cf/mikemccabe210/status/1…
Very excited to present Multiple Physics Pretraining!
MPP is a group of techniques for pretraining on a diverse set of time-dependent physics to learn models that can be fine-tuned for multiple problems.
Blog: polymathic-ai.org/blog/mpp/
Paper: arxiv.org/abs/2310.02994
We're thrilled to be at @NeurIPSConf for the first time since we formed a few months ago!
If you're there, we'd love to chat with you about our team and AI/ML research!
Reach out and be sure to check out our accepted papers👇#NeurIPS2023 #AI4Science
and we are HIRING 🥳
We are graciously supported with funding from @SimonsFdn @FlatironInst.
Additional participating institutions include @nyuniversity, @Cambridge_Uni, @SchmidtFutures, @Princeton, and @BerkeleyLab.
4/n
Polymathic AI is guided by a scientific advisory group of world-leading experts: @ylecun @hardmaru Leslie Greengard @DavidSpergel @laurezanna Colm-cille Caulfield @OlgaTroyanskaya and Stephane Mallat.
3/n
