Lightnews — Scholar-powered news

Stefano Martiniani @stemartiniani.bsky.social · 15d

If everyone does it, it must be right…right? Not quite. In “All That Structure Matches Does Not Glitter” #NeurIPS2025 we show CSP benchmarks miss polymorphs and datasets are duplicated. New deduped data, polymorph-aware splits, METRe & cRMSE. Harder tasks, better models!
www.arxiv.org/abs/2509.12178

All that structure matches does not glitter

Generative models for materials, especially inorganic crystals, hold potential to transform the theoretical prediction of novel compounds and structures. Advancement in this field depends critically o...

www.arxiv.org

1

Stefano Martiniani @stemartiniani.bsky.social · Sep 9

Check out our latest paper in collaboration with Mathias Casiulis, Naomi Oppenheimer, and Matan Ben Zion on a simple geometric design rule to achieve robotic swarm intelligence. The paper is out today in the Proceedings of the National Academy of Sciences (PNAS).

www.nyu.edu/about/news-p...

Scientists Find Curvy Answer to Harnessing “Swarm Intelligence”

Breakthrough offers way to develop AI to match flocking birds and schooling fish

www.nyu.edu

Stefano Martiniani @stemartiniani.bsky.social · Jun 18

Contrastive Self-Supervised Learning is Just Sphere Packing!
CLAMP (Contrastive Learning As Manifold Packing) recasts SSL as neural manifold packing with a physics-inspired repulsive-particle loss (like in jamming) and achieves new SOTA on ImageNet-100. arxiv.org/abs/2506.13717

5

Reposted by Stefano Martiniani

Stefano Martiniani @stemartiniani.bsky.social · Jun 3

www.linkedin.com/posts/smarti...

🔬 Here comes the lab’s first neurobiology paper, made possible by the… | Stefano Martiniani

🔬 Here comes the lab’s first neurobiology paper, made possible by the amazing work of Dr. Jiyeon H., grad student Asit Pal, and collaborators, especially Andre Fenton (lead PI on the paper), Hans A. H...

www.linkedin.com

1 1

Stefano Martiniani @stemartiniani.bsky.social · Jun 3

www.linkedin.com/posts/smarti...

🔬 Here comes the lab’s first neurobiology paper, made possible by the… | Stefano Martiniani

🔬 Here comes the lab’s first neurobiology paper, made possible by the amazing work of Dr. Jiyeon H., grad student Asit Pal, and collaborators, especially Andre Fenton (lead PI on the paper), Hans A. H...

www.linkedin.com

1 1

Stefano Martiniani @stemartiniani.bsky.social · Jun 3

We show that memory persistence is encoded in gene expression manifolds, not single gene changes. Shadow memory proteins like PKMzeta & KIBRA leave no single-gene signature, but reshape network structure. New from our lab + Hofmann + Fenton lab: www.biorxiv.org/content/10.1...

Persistently increased expression of PKMζ and unbiased gene expression profiles identify hippocampal molecular traces of a long-term active place avoidance memory and ′shadow′ proteins

Long-term memory formation transiently activates Ca2+-calmodulin kinase IIα (CaMKII) and atypical protein kinase C isoform iota/lambda (PKC𝜄/λ), whereas persistent activation of the other atypical PKC...

www.biorxiv.org

1 1

Stefano Martiniani @stemartiniani.bsky.social · Jun 2

🚀 Satyam and Guanming’s “Emergent Universal Long Range Structure in Random-Organizing Systems” shows noise correlations create long-range structure, from 🧩 hyperuniform materials to 🤖 ML, and that SGD’s flat minima bias is universal. 👇 arxiv.org/abs/2505.22933 #SoftMatter #ML

Emergent universal long-range structure in random-organizing systems

Self-organization through noisy interactions is ubiquitous across physics, mathematics, and machine learning, yet how long-range structure emerges from local noisy dynamics remains poorly understood. ...

arxiv.org

3 5

Stefano Martiniani @stemartiniani.bsky.social · May 31

The Martiniani Lab

Left to right: Dr. M. Casiulis, Dr. (as of today!) A. Shih , S Rawat, Dr. J. Han, Dr. K. McClain, E. House, Dr. G. Zhang, ..., Dr. P. Hoellmer, T. Egg, S. Anand, A. Pal, P. Suryadevara, G. Wolfe, Dr. M. Martirossyan, (Dr. F. Morone)

2

Stefano Martiniani @stemartiniani.bsky.social · May 22

🚀 New paper on stabilizing recurrent neural circuits! Normalization keeps recurrent networks in check. When it fails: ⏳ critical slowing, 🎲 variability ➡️ 🌪️ oscillations➡️💥 instability. Important for understanding brain functions and building AI. www.biorxiv.org/content/10.1...

Stabilization of recurrent neural networks through divisive normalization

Stability is a fundamental requirement for both biological and engineered neural circuits, yet it is surprisingly difficult to guarantee in the presence of recurrent interactions. Standard linear dyna...

www.biorxiv.org

3

Stefano Martiniani @stemartiniani.bsky.social · May 7

📄 More info: openreview.net/pdf?id=ka2jx...

🧪 Fully open-source on GitHub: github.com/FERMat-ML/OM...

🙏 Thanks to all contributors! 💻 Trained on EmpireAI and NYU, UF, & UMN HPC.

openreview.net

1 2

Stefano Martiniani @stemartiniani.bsky.social · May 7

🚀 Thrilled to introduce Open Materials Generation (OMatG), a state of the art framework for generative design of inorganic crystalline materials! Accepted at #ICML2025 & Spotlight at #AI4Mat @ICLR2025!

🔬 OMatG unifies flow matching & score-based diffusion, outperforming FlowMM and FlowLLM!

1 1 4

Stefano Martiniani @stemartiniani.bsky.social · Apr 19

RamO(N) 🤣

1 2

Stefano Martiniani @stemartiniani.bsky.social · Apr 4

as.nyu.edu/departments/...

Martiniani Receives Entropy Young Investigator Award

as.nyu.edu

2

Reposted by Stefano Martiniani

The Warren Center for Network & Data Sciences @warrencenter.bsky.social · Mar 21

On Tuesday, March 25, Stefano Martiniani will give an #AI for Science Seminar on “Learning as Manifold Packing” in room 414 AGH, hosted by the Data Driven Discovery Initiative (DDDI) and the Center for Innovation in Data Engineering and Science (IDEAS). Join us!
web.sas.upenn.edu/da...

1 6

Reposted by Stefano Martiniani

Mark Cuban @mcuban.bsky.social · Mar 22

From 2010 to 2016 (latest data I have ), NIH research contributed to EVERY drug approved by the FDA

710 8.6K 32K

Stefano Martiniani @stemartiniani.bsky.social · Mar 20

Nice!

1

Reposted by Stefano Martiniani

Stefano Martiniani @stemartiniani.bsky.social · Mar 20

Do systems where the equations are known but cannot be solved in less than exponential time count? If so just take Schroedinger's equation for an interacting many-body system. Perfect description of the problem with no solution :)

2 1 5

Stefano Martiniani @stemartiniani.bsky.social · Mar 20

Oh and if you think "but surely hydrodynamics was derived from atomistic theories", think again, a lot of hydrodynamics (e.g. Flick's law) was derived phenomenologically (in neuro language, normatively)

1 3

Stefano Martiniani @stemartiniani.bsky.social · Mar 20

So do we need to know the state of every cell in the brain to know the state of the brain? I hope not! We can only understand and predict with coarse grained theories.

1 2

Stefano Martiniani @stemartiniani.bsky.social · Mar 20

In principle this would work but the size of the system of equations that one would have to solve and the time required to solve them makes it 1/ impossible 2/ a dumb proposition because we have a coarse-grained theory (fluid dynamics and continuum mechanics) which are better suited for this problem

2 3

Stefano Martiniani @stemartiniani.bsky.social · Mar 20

I think more to your point, and not unrelated to my previous example, take the lift of a plane. Someone fixated with microscopic details would argue that to model a plane one would have to run a molecular dynamics simulation of every atom in the plane and the surrounding air.

1 1

Stefano Martiniani @stemartiniani.bsky.social · Mar 20

Do systems where the equations are known but cannot be solved in less than exponential time count? If so just take Schroedinger's equation for an interacting many-body system. Perfect description of the problem with no solution :)

2 1 5

Reposted by Stefano Martiniani

NYU Center for Data Science @nyudatascience.bsky.social · Mar 3

CDS is hiring a Clinical Professor of Data Science.

Teach ML, programming, and specialized courses in our 60 5th Ave building.

Renewable contracts with promotion opportunities.

Apply by April 1, 2025.

For details, see: apply.interfolio.com/155349

#MachineLearning #ML #AIjobs

7 7

Reposted by Stefano Martiniani

Flaviu Cipcigan @flaviucipcigan.bsky.social · Feb 13

ColabFit Exchange is another great dataset curation effort that I'd like to boost.

Great work by @stemartiniani.bsky.social and team to curate the most diverse materials database in the world!

Stefano Martiniani @stemartiniani.bsky.social · Dec 14

Join us for the #AI4Mat workshop at #NeurIPS2024 today and check out our spotlight on how we built the most diverse database for AI for materials in the world openreview.net/forum?id=b8q...

1 1

Stefano Martiniani @stemartiniani.bsky.social · Jan 6

Instagram post of the Cultural Office of the Consulate General of Spain in New York🗽🌃

Help us spread the word! 🌐✨