One binary operator eml(x,y)=exp(x)-ln(y) plus the constant 1 generates all elementary functions including sin, cos, sqrt, log, arithmetic operations, and constants e, pi, i.
AI Feynman: A physics-inspired method for symbolic regression.Science Advances, 6(16):eaay2631, 2020
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
fields
cond-mat.mtrl-sci 2 cs.LG 2 astro-ph.EP 1 cs.AI 1 cs.CE 1 cs.CV 1 cs.ET 1 cs.RO 1 cs.SC 1 math-ph 1years
2026 15verdicts
UNVERDICTED 15representative citing papers
Single-cell patterning of bacterial spores shows that parallel initial orientations create highly ordered nematic films that buckle synchronously, while orthogonal seeding yields chaos, enabling macroscopic control of alignment and optical anisotropy in living films.
Ultrafast nonlinear Hall effect is observed in centrosymmetric black phosphorus via femtosecond laser pulses polarized along the armchair direction, persisting beyond 300 fs.
DoLQ employs a sampler agent, parameter optimizer, and LLM-based scientist agent to iteratively propose, refine, and evaluate ODE candidates, yielding higher success rates and better symbolic term recovery than prior symbolic regression methods on multi-dimensional benchmarks.
AMTe4 (A=Ta,Nb; M=Ir,Rh) compounds host Weyl points within a few meV of the Fermi energy, including multiple types such as type-I, II, and III in NbRhTe4, substantially revising the topological electronic structure.
DenSNet learns the Hohenberg-Kohn map to electron density with equivariant networks and delta-learning, then maps density to energy, producing stable MD trajectories whose infrared spectra match experiment and DFT on ethanol, ethanethiol, resorcinol, and polythiophene oligomers.
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
A simplicial set sOb_bullet(M) of Hamiltonian forms in n-plectic geometry is shown to be a Kan complex, supplying an n-groupoid model for observables and a categorified pre-n-Hilbert space via recursive inner products.
MicroDiffuse3D is a foundation model that restores 3D microscopy images under sparse super-resolution, joint degradation, and low-SNR denoising, reporting 10.58% segmentation and 15.59% line-profile gains over baselines.
A material formulation of the cross-sectional warping problem for hyperelastic beams is derived in Voigt notation to compute effective nonlinear beam stiffness efficiently.
No single post-Moore technology replaces current HPC for plasma simulations, but FPGA-class accelerators offer near-term kernel offload, non-von Neumann architectures medium-term operator acceleration, and quantum computing long-term potential for warm dense matter microphysics.
FASE pairs a spatiotemporal graph neural network and multivariate Hawkes process for crime prediction with a fairness-constrained linear program for patrol allocation, showing that allocation fairness holds in simulation but a 3.5 percentage point detection gap between minority and non-minority ZIPs
A semi-supervised teacher-student framework enables neural networks to proxy CVaR portfolio optimization using synthetic data augmentation for scarce labels and regime shifts.
A QDMI-based adapter for IQM quantum hardware enables reusable integration with Slurm and Qiskit in HPC centers, with open-source code provided.
A review of SPH modeling for global-scale impacts, emphasizing material properties across size regimes and links to Solar System observations.
citing papers explorer
-
All elementary functions from a single binary operator
One binary operator eml(x,y)=exp(x)-ln(y) plus the constant 1 generates all elementary functions including sin, cos, sqrt, log, arithmetic operations, and constants e, pi, i.
-
Shaping nematic order in bacterial films with single-cell resolution patterning
Single-cell patterning of bacterial spores shows that parallel initial orientations create highly ordered nematic films that buckle synchronously, while orthogonal seeding yields chaos, enabling macroscopic control of alignment and optical anisotropy in living films.
-
Ultrafast nonlinear Hall effect in black phosphorus
Ultrafast nonlinear Hall effect is observed in centrosymmetric black phosphorus via femtosecond laser pulses polarized along the armchair direction, persisting beyond 300 fs.
-
Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
DoLQ employs a sampler agent, parameter optimizer, and LLM-based scientist agent to iteratively propose, refine, and evaluate ODE candidates, yielding higher success rates and better symbolic term recovery than prior symbolic regression methods on multi-dimensional benchmarks.
-
Fermi energy Weyl nodes in $\mathbf{AM}$Te$_4$ ($\mathbf{A}$=Ta, Nb, $\mathbf{M}$=Ir, Rh)
AMTe4 (A=Ta,Nb; M=Ir,Rh) compounds host Weyl points within a few meV of the Fermi energy, including multiple types such as type-I, II, and III in NbRhTe4, substantially revising the topological electronic structure.
-
Enhancing molecular dynamics with equivariant machine-learned densities
DenSNet learns the Hohenberg-Kohn map to electron density with equivariant networks and delta-learning, then maps density to energy, producing stable MD trajectories whose infrared spectra match experiment and DFT on ethanol, ethanethiol, resorcinol, and polythiophene oligomers.
-
Evidence of an Emergent "Self" in Continual Robot Learning
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
-
A Simplicial Approach to Higher Geometric Quantization
A simplicial set sOb_bullet(M) of Hamiltonian forms in n-plectic geometry is shown to be a Kan complex, supplying an n-groupoid model for observables and a categorified pre-n-Hilbert space via recursive inner products.
-
MicroDiffuse3D: A Foundation Model for 3D Microscopy Imaging Restoration
MicroDiffuse3D is a foundation model that restores 3D microscopy images under sparse super-resolution, joint degradation, and low-SNR denoising, reporting 10.58% segmentation and 15.59% line-profile gains over baselines.
-
The cross-sectional warping problem for hyperelastic beams: An efficient formulation in Voigt notation
A material formulation of the cross-sectional warping problem for hyperelastic beams is derived in Voigt notation to compute effective nonlinear beam stiffness efficiently.
-
Post-Moore Technologies for Plasma Simulation: A Community Roadmap
No single post-Moore technology replaces current HPC for plasma simulations, but FPGA-class accelerators offer near-term kernel offload, non-von Neumann architectures medium-term operator acceleration, and quantum computing long-term potential for warm dense matter microphysics.
-
FASE : A Fairness-Aware Spatiotemporal Event Graph Framework for Predictive Policing
FASE pairs a spatiotemporal graph neural network and multivariate Hawkes process for crime prediction with a fairness-constrained linear program for patrol allocation, showing that allocation fairness holds in simulation but a 3.5 percentage point detection gap between minority and non-minority ZIPs
-
Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training
A semi-supervised teacher-student framework enables neural networks to proxy CVaR portfolio optimization using synthetic data augmentation for scarce labels and regime shifts.
-
Practical HPCQC Integration with QDMI: A Real-Hardware Case Study with IQM Systems
A QDMI-based adapter for IQM quantum hardware enables reusable integration with Slurm and Qiskit in HPC centers, with open-source code provided.
-
Recent advances in modelling of global-scale collisions using smoothed particle hydrodynamics
A review of SPH modeling for global-scale impacts, emphasizing material properties across size regimes and links to Solar System observations.