The Polymathic AI Collaboration. Shared account.
Joined September 2023
- Tweets80
- Following69
- Followers3.8K
- Likes53
PolymathicAI retweeted
1/7 Frontier LLMs make powerful agents, but communication with other models hits a bottleneck: translating high-dimensional representations into human-understandable forms. AI Mindmeld connects them directly, opening up information an agent may never know to ask for.
ALT AI Mindmeld cartoon. Left: a specialist reads a detailed schematic and describes it as “A gear, some pipes...” while the LLM draws a sparse sketch. Right: specialist and LLM share the detailed schematic through the Latent Interconnect Protocol.
PolymathicAI retweeted
Announcing FlashMap: a new speculative decoding algorithm based on flow maps! >6x faster inference on Qwen3-8B 🧵
Project page: jshen.net/flashmap
arXiv: arxiv.org/abs/2610.24365
w/ @Jay41969851 @_ryantlee @jonathanmay @cosmo_shirley
PolymathicAI retweeted
"The world is predictable in the right coordinates. The open question is whether a model can learn those coordinates on its own."
World model for Physics conference in Aspen coming winter 2027! Application deadline October 5 !
organized by @randall_balestr @KempeLab @ylecun and me 😀
PolymathicAI retweeted
1/ At @PolymathicAI, we have been asking:
What does it take to integrate general LLM agents with specialized scientific software?
Today, I am happy to announce Agent Rosetta, an LLM agent to support scientists in real-world protein design tasks using the Rosetta Modeling Suite.
PolymathicAI retweeted
Want to apply principled Bayesian methods to Large scientific foundation models?
Join @PolymathicAI and @EmtiyazKhan at Adaptive Bayesian Intelligence to explore the boundaries of SOTA large models for scientific data and Bayesian Principles in Tokyo 🗻 , Germany 🍺 and NYC 🍎!
post-doc: apply.interfolio.com/184211
research-scientist: apply.interfolio.com/184213
PolymathicAI retweeted
Happy to announce the partnership between @relativityspace and @PolymathicAI to explore Mars!! 🤩
Come work with real rocket scientists, astrophysicists and AI experts to explore Mars ❣️
Links:
job-boards.greenhouse.io/rel…
job-boards.greenhouse.io/rel…
PolymathicAI retweeted
1/12 Introducing MIMIC: a SOTA foundation model trained natively across DNA, RNA and proteins. MIMIC is multimodal and generative: it can use structure, regulation, evolution, and experimental context to infer missing biology or design new sequences.
PolymathicAI retweeted
physical systems (orbits/fluid mechanics) may look complex, but are often governed by simple equations/few parameters. can current self-supervised methods learn the underlying physics?
our new paper finds that learning in latent space may be the key!
arxiv.org/abs/2603.13227🧵
PolymathicAI retweeted
Join @PolymathicAI and @EmtiyazKhan and me to explore the world of frontier AI for science using new Bayesian techniques!
We are looking for both postdoctoral fellows and research scientists! 🚀
If you want to work with our group while living in New-York and also spend time in Tokyo and Germany!, check out the new positions available at the NYU and Flatiron Institute by @cosmo_shirley
post-doc: apply.interfolio.com/184211
research-scientist: apply.interfolio.com/184213
PolymathicAI retweeted
Getting ready to speak at the @worldmodel_26 at Mila alongside @ylecun, @Yoshua_Bengio and @sherryyangML :)
Excited to see you online or in person! 🤪
🚨Announcing the World Modeling Workshop 2026 🚨
📅 When: Feb 4–6, 2026
📍Where: Mila (Montréal) + Online (free)
💡 What: Keynotes, Methods Deep Dive, and Tutorials
🌐 world-model-mila.github.io/
✉️ [email protected]
🧵 Details below:
PolymathicAI retweeted
We built a semantic search engine for millions of galaxy images by having LLMs write the captions.
These images are completely unlabeled, but our method enables astronomers to search for rare phenomena via text. Try our app! 🔭👇
PolymathicAI retweeted
I’m excited to announce that @PolymathicAI new astrophysics model, AION-1, has been accepted to #neurips2025 ! 🎉
Come see our poster on Dec 5 (Friday) at 1-4pm PT, poster session 5
OR
hear our talk from @liamhparker and Francois Lanusse at #AI4Science workshop
It’s the first large-scale multimodal foundation model for astronomy!
PolymathicAI retweeted
Latent diffusion Models are all the rage right now. But how far can we push it ?
What happens if we use a very^3 small latent space? 🧐
Come find out at our @NeurIPSConf paper led by @FrancoisRozet Tomorrow (Thursday) in San Diego at 4:30-7:30pm at the Exhibit Hall CDE poster #2311 !
PolymathicAI retweeted
Most real-life systems are only partially observed, whether it is our Earth, the sun, or the air flow in our house! So, how do we predict these dynamical systems if nothing is perfectly observed?
Come join @PolymathicAI tomorrow (Thursday) at 4:30-7:30 PST at Exhibit Hall CDE #2213 at @NeurIPSConf at our poster on how to predict partially observed dynamical systems!
-> A Multiscale Inference Scheme+ Diffusion! 🚀
Led by @rdMorel and @FrankPRCP !!
Partial observability is a key challenge in predicting physical systems, where only part of the state is observed.
Check out our poster #2213 at #neurips2025 on Thu, Dec 4, 4:30pm! We propose a multiscale inference scheme for diffusion models to better predict these systems.
PolymathicAI retweeted
Partial observability is a key challenge in predicting physical systems, where only part of the state is observed.
Check out our poster #2213 at #neurips2025 on Thu, Dec 4, 4:30pm! We propose a multiscale inference scheme for diffusion models to better predict these systems.
PolymathicAI retweeted
So proud to see the culmination of effort led by @mikemccabe210 @PayelMukhopadh3 @__tm__157 @BrunoRegaldo @FrancoisRozet along with the amazing team at @PolymathicAI to produce
The first "Polymathic"/cross-disciplinary AI model for fluid dynamics!
We started with creating The Well, the first internet scale of fluids dataset co-led by @mikemccabe210 and @oharub with the goal of creating the first cross-disciplinary fluid model!
Now it is here, and we are lovingly naming it the Polymathic Walrus 😁!
1/ Today with my colleagues @PolymathicAI, I'm excited to release our latest project, Walrus, a cross-domain foundation model for physical dynamics, into the world.
polymathic-ai.org/blog/walru…
Paper: arxiv.org/abs/2511.15684
Git: github.com/PolymathicAI/walr…
HF: huggingface.co/polymathic-ai…
RT @cosmo_shirley: Extremely proud and honored to be named among the great minds of Schmidt Sciences AI2050 Senior fellows!
A special sh…
This quoted post is unavailable.
PolymathicAI retweeted
PolymathicAI is recruiting two postdoctoral researchers to join our team at Cambridge, to work on building and understanding large-scale foundation models for science. Please share with potential candidates!
PolymathicAI retweeted
Does a smaller latent space lead to worse generation in latent diffusion models? Not necessarily! We show that LDMs are extremely robust to a wide range of compression rates (10-1000x) in the context of physics emulation.
We got lost in latent space. Join us 👇
PolymathicAI retweeted
The final days of summer are upon us, and it is bittersweet to say goodbye to our great group of @PolymathicAI interns! 😭 @JacopoTeneggi @cskokgibbs @astro_nolan @CristianaD2202 @LouisSerrano31 @rachelczhang
Here are a few pics to remind us all the fun we had! (and hold your breath for our amazing list of papers led by our interns out soon!)
