203 citations · 261 across the 21 of their papers we have counts for
12 papers · 1 filter
Reinforcement Learning on the Discrete Composition Channel of a Crystal Generator: Validated Gains and Reward Hacking
Pawan Prakash, Philipp Höllmer, Addis Fuhr +4
Inverse materials design is a long-standing goal of computational materials discovery. Generative models for crystalline materials are typically trained to match the distribution o…
Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Prediction
Thomas Egg, Harry Winston Sullivan, Maya M. Martirossyan +8
Crystal structure governs material properties, making crystal structure prediction (CSP) a fundamental problem in materials science. Generative models are a promising approach for…
OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery
Thomas Egg, Harry Winston Sullivan, Ellad B. Tadmor +1
The discovery of novel inorganic materials drives technological breakthroughs in critical fields such as computing and energy storage. Generative AI has promised to accelerate the…
A minimal mechanism to generate long timescales without fine tuning
Kathryn McClain, Shivang Rawat, Mia Morrell +3
Long timescales in brain dynamics give rise to power law correlations measured in experiments. A simple linear recurrent neural network model can reproduce this power law behavior,…
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
Bing Yan, Gregory Wolfe, Stefano Martiniani +1
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked docume…
Hyperuniform systems are maximally irreversible
Mathias Casiulis, Satyam Anand, Stefano Martiniani
Hyperuniform systems, defined by the anomalous suppression of large-scale density fluctuations, are a paradigm of non-equilibrium self-assembly. While mechanisms underlying the sel…
Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models
Rishabh Sharma, Stefano Martiniani
We introduce cyclic denoising -- repeated forward and reverse diffusion at controlled noise amplitudes -- as an extraction attack for image diffusion models. Inspired by random org…
Exact Variance and Fano Factor for Arbitrary Level Crossings in Stationary Gaussian Processes
Shivang Rawat, Flaviano Morone, David J. Heeger +1
Understanding the statistics of level crossings in stochastic processes is crucial across many scientific disciplines. The traditional Kac-Rice formula gives the mean rate of level…
MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching
Cheng Zeng, Harry W. Sullivan, Thomas Egg +8
Molecular crystal structure prediction represents a grand challenge in computational chemistry due to large sizes of constituent molecules and complex intra- and intermolecular int…
Cross-View World Models
Rishabh Sharma, Gijs Hogervorst, Wayne E. Mackey +2
World models enable agents to plan by imagining future states, but existing approaches operate from a single viewpoint, typically egocentric, even when other perspectives would mak…
Open Materials Generation with Inference-Time Reinforcement Learning
Philipp Hoellmer, Stefano Martiniani
Continuous-time generative models for crystalline materials enable inverse materials design by learning to predict stable crystal structures, but incorporating explicit target prop…
Spatial self-organization driven by temporal noise
Satyam Anand, Guanming Zhang, Stefano Martiniani
The counterintuitive emergence of order from noise is a central phenomenon in science, ranging from pattern formation and synchronization to order-by-disorder in frustrated systems…