Asst. Professor of Physics, Chemistry, Mathematics, Neural Science at NYU | Simons Foundation Faculty Fellow | Open Science http://colabfit.org
martinianilab.org
Stefano Martiniani
Loading...
Excited to share our latest work with Guanming Zhang and @stemartiniani.bsky.social in @natcomms.nature.com, where we uncover universal long-range structure in three distinct noisy particle systems spanning soft matter and machine learning.
www.nature.com/articles/s41...
www.nature.com
Satyam Anand
Noise is usually associated with disorder, but it can also generate large-scale order. Here, the authors show that three distinct systems, spanning soft matter and stochastic optimization, self-organi...
What if a world model could imagine the future from a completely different perspective? Introducing XVWM: given one view and an action, predict the future from another camera. A building block for theory of mind.
Collaboration with aimlabs.com
đź“„ arxiv.org/abs/2602.07277
New preprint!
So, say you're studying some critical transition. How do you catch its universality? Pair correlations? Boring!
We threw line segments at the system, looked at intersections with clusters, and uncovered static and dynamical universal behavior of MIPS!
arxiv.org/abs/2511.09444
📢Out now! @stemartiniani.bsky.social and colleagues present PropMolFlow, a flow-matching method for property-guided molecule generation. #MoleculeDiscovery #FlowMatching www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eZ5cG
Stefano Martiniani
Alt: a close up of a person's hand holding a marker that says sharpie
📢Andreas Luttens discuss the work by @stemartiniani.bsky.social and colleagues on a flow-matching method for property-guided molecule generation. www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/e7BAy
M. Kasiulis
Video
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...
New paper just out, as an editor's suggestion in PRL!
While looking for the ideal isotropic bandgap material, we actually discovered new structures.
These structures lie at the border between order and disorder, and that's good for optics!
More about their structure here,
tinyurl.com/3aej53ht
⚛️🧪
The transformative capability of quantum-accurate machine learning interatomic potentials
Kim Review Commentary by Alfredo A. Correa; Sebastien Hamel
kimreview.org/commentaries...
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
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
Nature Computational Science
Nature Computational Science
Stefano Martiniani
M. Kasiulis
Stefano Martiniani
Stefano Martiniani
Stefano Martiniani
Breakthrough offers way to develop AI to match flocking birds and schooling fish
Commentary: Many materials' properties and phase boundaries are generally not well known under extreme pressure and temperature conditions. This is a consequence of the scarcity of experimental inform...
PropMolFlow is a flow-matching method for property-guided molecule generation that matches diffusion model performance while generating stable, valid structures more quickly and enabling the discovery...
The PropMolFlow model uses flow matching to efficiently generate chemically valid molecules in three dimensions with targeted properties, enabling accelerated discovery of molecules useful in material...
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...
