DClaw

One-stop index of open-source datasets, benchmarks, tools and industrial cases in Physics-Informed Neural Networks (PINN), Neural Operators and Scientific ML surrogate models. All entries include official links and licenses, maintained by the community and AI.

Browse Datasets →

Datasets & Benchmarks

Training & evaluation datasets, scientific ML benchmarks

Tools & Frameworks

Solvers, training frameworks, post-processing & visualization tools

Applied Cases

Physics AI deployment cases in any domain - CAE, energy, weather, biomedicine, materials, geophysics and beyond

Learning Paths

Resources from beginner to industrial deployment

Papers & Surveys

Must-read benchmark papers and technical surveys (no news or industry reports)

Recent Updates

AIPerf: LLM Inference Benchmarking at Scale

Benchmarking
AIPerf is an LLM inference benchmarking tool from NVIDIA designed to evaluate the speed and performance of large language models in deployment scenarios.
See LICENSE file benchmarkingLLM inferenceperformance evaluation AI Generated

Physics-Informed CNN for Battery Pack Temperature Fields

Thermal Management / Physics-Informed ML
A physics-informed convolutional neural network whose loss encodes the finite-difference heat conduction equation, used as a surrogate for the temperature field of a liquid-cooled battery pack and more accurate than a purely data-driven model trained on the same data.
arXiv preprint (copyright held by authors) Thermal ManagementPINNBattery

HydroGym: A Reinforcement Learning Platform for Flow Control

Flow Control / Turbulent Drag Reduction
An open-source reinforcement learning platform for flow control that couples six CFD solver backends with dozens of pre-configured environments; trained policies transfer zero-shot to a wing and cut skin-friction drag substantially.
MIT (code) / Nature paper Flow ControlReinforcement LearningDrag Reduction

MACE-MP-0: A Universal Machine-Learned Interatomic Potential

Molecular Dynamics / ML Interatomic Potential
A general-purpose machine-learned interatomic potential built on an equivariant graph neural network, trained on 150k public inorganic crystals, that runs stable molecular dynamics out of the box for solids, liquids, gases and reactions, and can be fine-tuned to ab initio accuracy with only a handful of configurations.
MIT (code) / arXiv preprint Molecular DynamicsML PotentialEquivariant GNN

TopoDiff: Diffusion-Model-Driven Topology Optimization

Structural Optimization / Generative Design
A conditional diffusion approach to structural topology optimization from MIT that uses surrogate-model guidance to optimise both mechanical compliance and manufacturability, outperforming conditional GANs by a wide margin.
arXiv preprint (code and data publicly available) Topology OptimizationDiffusion ModelGenerative Design

HiDream-O1-Video by ZhiXiang

Video Generation/AI
HiDream-O1-Video-1.0 is a video generation model that demonstrates strong understanding of real-world scenarios, excelling in complex dynamic scenes like hip-hop rap and NBA game-winning shots, ranking among the top four globally.
See LICENSE file video generationAI videotext-to-video AI Generated