scientific-ml

Tag

Cards List
#scientific-ml

Neural Fields for NV-Center Inverse Sensing

arXiv cs.LG · 2026-05-15 Cached

This paper proposes NeTMY, an amortization-free coordinate neural field for inverse problems in NV-center quantum sensing, using a corrected forward model and sparse reconstruction losses to overcome center-collapse pathologies.

0 favorites 0 likes
#scientific-ml

Hierarchical Multi-Fidelity Learning for Predicting Three-Dimensional Flame Wrinkling and Turbulent Burning Velocity

arXiv cs.LG · 2026-05-12 Cached

This paper introduces MuFiNNs, a hierarchical multi-fidelity neural network framework for predicting 3D flame wrinkling and turbulent burning velocity using sparse experimental data. The approach integrates low-fidelity physical trends with high-fidelity corrections to enable robust prediction and extrapolation in data-limited combustion regimes.

0 favorites 0 likes
#scientific-ml

Quantitative Sobolev Approximation Bounds for Neural Operators with Empirical Validation on Burgers Equation

arXiv cs.LG · 2026-05-12 Cached

This paper establishes quantitative Sobolev approximation bounds for neural operators, proving that operators can be uniformly approximated with explicit complexity-error relations. It validates these theoretical bounds using Fourier Neural Operators on the Burgers' equation, demonstrating that Sobolev-space approximation theory accurately predicts scaling behavior.

0 favorites 0 likes
#scientific-ml

Towards Scalable One-Step Generative Modeling for Autoregressive Dynamical System Forecasting

arXiv cs.LG · 2026-05-08 Cached

This paper introduces MeLISA, a latent-free autoregressive generative surrogate for forecasting high-dimensional physical dynamics that uses pixel-space MeanFlow to achieve efficient one-step generation. It demonstrates superior long-horizon statistical accuracy and inference speed compared to neural operators on turbulent flow benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback