Starred repositories
Jacobian Orthogonal Polynomial-based Physics-Informed Kolmogorov-Arnold Network for fluid dynamics
西北工业大学硕博学位论文模版 | Yet Another Thesis Template for Northwestern Polytechnical University
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides [EMNLP 2025]
[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers
A machine learning software for extracting information from scholarly documents
Welcome to the CTF for Science Framework, a modular and extensible platform designed for benchmarking modeling methods on dynamic systems. This framework supports the evaluation and comparison of m…
Repo for finding effective Hamiltonians using Physics Informed Neural Networks
[EMNLP2025] From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
Course website for AI in Sciences and Engineering at ETH Zurich
[NeurIPS 2025] Geometry Aware Operator Transformer As An Efficient And Accurate Neural Surrogate For PDEs On Arbitrary Domains
About code release of "Transolver: A Fast Transformer Solver for PDEs on General Geometries", ICML 2024 Spotlight. https://arxiv.org/abs/2402.02366
Code for the paper: Physics-informed neural networks for modelling anisotropic and bi-anisotropic electromagnetic constitutive laws through indirect data
A repository containing the data and source code needed to reproduce the results and figures from our paper “Towards Deep Physics-Informed Kolmogorov–Arnold Networks.”
A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Physics-Informed Machine Learning (PIML) and Physics-Informe…
NACA airfoil manipulation tools for AIAA Design/Build/Fly
Repository for NeurIPS 2025 paper, "Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers."
The codes for the work "Legend-KINN: A Legendre Polynomial-Based Kolmogorov-Arnold-Informed Neural Network for Efficient PDE Solving"
Physics-informed Graph Neural Networks for learning PDEs on 3D meshes.
Exploration of the Lorenz system using data-driven and physics-informed methods, including FFT, DMD, EDMD, Takens embedding, Deep Koopman learning, and PINNs. Jupyter notebooks demonstrate modeling…
Gauss-Newton optimization for finite basis physics-informed neural networks
1
Updated Oct 15, 2025
AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models