AI for Science

The arXiv paper “CAS I: A Geometric Coding Theorem” proposes a group-theoretic analogue of the classical Coding Theorem by measuring how likely a symmetry is to isolate a binary string as its unique fixed point.

A new arXiv paper reframes regularity through a communication-complexity lens: split an input word between Alice and Bob, then ask whether a constant amount of communication is enough to compute the function. The goal is to unify Nerode-style characterizations across different output domains.

A new arXiv paper applies Neural Spline Flows to a mono-Z dark matter search using CMS Run 2015D open data. The study reports no evidence for dark matter, but highlights how likelihood-ratio scoring in high-dimensional phase space could reshape particle-physics analyses.

A new arXiv paper introduces MxGPS, a multiplex graph transformer designed to reduce topology overfitting in power-grid GNNs. By jointly training on static state estimation and AC power flow, the model aims to generalize better to unseen grid topologies.

A new arXiv paper compares a variational quantum circuit with a parameter-matched classical message-passing model for molecular property prediction. Its main message is that topology-aligned inductive bias, not the quantum label alone, appears to drive parameter efficiency.

A new arXiv paper explores whether Quantum Generative Adversarial Networks can support the security assessment of post-quantum cryptography. Rather than claiming a practical break, the work frames QGANs as an early building block for quantum-assisted cryptanalysis workflows.