Scientific Computing Comparison Hub
4 papers - avg viability 6.3
Top Papers
- Learning Neural Operators from Partial Observations via Latent Autoregressive Modeling(8.0)
A state-of-the-art framework for learning neural operators from partial observations, applicable to real-world scientific computing with up to 75% missing data.
- OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference(7.0)
OpInf-LLM leverages LLM and operator inference for efficient parametric PDE solving with low computational demands.
- NeuraLSP: An Efficient and Rigorous Neural Left Singular Subspace Preconditioner for Conjugate Gradient Methods(5.0)
NeuraLSP provides an efficient neural preconditioning method for faster PDE solutions, promising significant speed improvements for scientific computing.
- AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing(5.0)
AutoNumerics automates the creation of interpretable PDE solvers from natural language, offering a versatile tool for scientific computing.