BestHub
Sign in
Tagged articles

JAX

20 articles · Page 1 of 1
AI Agent Research Hub
AI Agent Research Hub
Jul 19, 2026 · Artificial Intelligence

Efficient Transonic Wing Flow Simulation and Shock Capture Using Euler‑PINN

This tutorial walks through building and training a physics‑informed neural network (Euler‑PINN) in JAX to simulate transonic airfoil flow, detailing the governing Euler equations, structured‑grid coordinate mapping, loss formulation, L‑BFGS optimization, and a thorough comparison with a high‑resolution finite‑volume reference solution that highlights both accuracy and efficiency trade‑offs.

Computational fluid dynamicsEuler-PINNJAX
0 likes · 20 min read
Efficient Transonic Wing Flow Simulation and Shock Capture Using Euler‑PINN
AI Agent Research Hub
AI Agent Research Hub
Jul 16, 2026 · Artificial Intelligence

Solving the Falkner‑Skan Viscous Boundary Layer with Physics‑Informed Neural Networks (PINN)

This tutorial demonstrates how to solve the two‑dimensional steady incompressible Falkner‑Skan viscous boundary‑layer equations using a physics‑informed neural network implemented in JAX, detailing the network architecture, loss construction, two‑stage training strategy, and achieving sub‑0.01 % relative errors with only 1 % interior collocation points.

Falkner‑SkanJAXPINN
0 likes · 17 min read
Solving the Falkner‑Skan Viscous Boundary Layer with Physics‑Informed Neural Networks (PINN)
AI Agent Research Hub
AI Agent Research Hub
Jun 19, 2026 · Artificial Intelligence

DeepONet Neural Operator for Fast Prediction of Non‑Smooth Discontinuities in the Sod Shock Tube

This tutorial presents a complete DeepONet workflow—two‑step separated training, Rowdy activation, SVD orthogonalisation, and a 10‑member ensemble—that predicts the density, velocity and pressure fields of the one‑dimensional Sod shock‑tube problem with an average test‑set relative error of 2.23% after only 22 minutes of training on an RTX 4090.

DeepONetJAXNeural Operator
0 likes · 22 min read
DeepONet Neural Operator for Fast Prediction of Non‑Smooth Discontinuities in the Sod Shock Tube
AI Agent Research Hub
AI Agent Research Hub
May 19, 2026 · Artificial Intelligence

Master Data‑Driven Neural Operators: DeepONet, POD‑DeepONet, FNO‑2D and Time‑Stepping FNO‑1D in One Tutorial

This tutorial presents a comprehensive JAX implementation and analysis of four neural‑operator methods—standard DeepONet, POD‑DeepONet, 2‑D Fourier Neural Operator, and time‑stepping 1‑D FNO—applied to the 1‑D advection equation, comparing their mathematical foundations, parameter counts, training efficiency, and prediction accuracy.

DeepONetFNOJAX
0 likes · 20 min read
Master Data‑Driven Neural Operators: DeepONet, POD‑DeepONet, FNO‑2D and Time‑Stepping FNO‑1D in One Tutorial
AI Agent Research Hub
AI Agent Research Hub
May 19, 2026 · Artificial Intelligence

Physics‑Informed Neural Networks for Navier‑Stokes Flow Parameter Identification

This tutorial demonstrates how continuous physics‑informed neural networks (PINNs) combined with stream‑function parameterization and nested forward‑mode automatic differentiation (JVP) can accurately identify the convection and viscosity coefficients of a two‑dimensional Navier‑Stokes cylinder‑wake problem from sparse velocity observations, achieving sub‑0.2% error for the convection term and robust performance even with 1% measurement noise, all within a few minutes on a single RTX 4090 GPU.

JAXNavier-StokesPINNs
0 likes · 28 min read
Physics‑Informed Neural Networks for Navier‑Stokes Flow Parameter Identification
AI Agent Research Hub
AI Agent Research Hub
Apr 22, 2026 · Artificial Intelligence

Solving the Burgers Equation with TINN: High‑Precision Physics‑Informed Neural Networks in 380 seconds

This tutorial presents the Time‑Induced Neural Network (TINN) framework that overcomes the time‑entanglement issue of standard PINNs by introducing a dedicated time‑subnet with FiLM modulation, employs a Levenberg‑Marquardt optimizer for second‑order updates, and demonstrates a 1e‑6 relative error solution of the 1‑D viscous Burgers equation in just 371 seconds on an RTX 4090.

Burgers EquationFiLM ModulationJAX
0 likes · 21 min read
Solving the Burgers Equation with TINN: High‑Precision Physics‑Informed Neural Networks in 380 seconds
AI Agent Research Hub
AI Agent Research Hub
Apr 1, 2026 · Artificial Intelligence

Scale‑PINN Solves High‑Re Navier‑Stokes in 100 seconds, Cutting Error by 96 %

The tutorial introduces Scale‑PINN, which adds an evolutionary regularization term inspired by pseudo‑time stepping to the PINN loss, enabling a shared‑backbone network to solve the lid‑driven cavity Navier‑Stokes problem at Re = 7500 in about 100 seconds and reducing the relative velocity error by roughly 96 % compared with a standard PINN.

Evolutionary regularizationHigh Reynolds numberJAX
0 likes · 25 min read
Scale‑PINN Solves High‑Re Navier‑Stokes in 100 seconds, Cutting Error by 96 %
DeepHub IMBA
DeepHub IMBA
Mar 25, 2026 · Artificial Intelligence

TPU Architecture and Pallas Kernels: From Memory Hierarchy to FlashAttention

This article explains why TPU programming differs from GPU, describes the explicit HBM‑VMEM‑register data movement required on TPU, introduces the Pallas grid‑BlockSpec‑Ref model, and walks through four progressively more complex kernels—including element‑wise add, tiled dot product, fused RMSNorm with scratch memory, and a production‑grade FlashAttention implementation—showing how each kernel maps to the TPU memory hierarchy and leverages Pallas features such as input_output_aliases and PrefetchScalarGridSpec.

FlashAttentionJAXPallas
0 likes · 20 min read
TPU Architecture and Pallas Kernels: From Memory Hierarchy to FlashAttention
AI Agent Research Hub
AI Agent Research Hub
Mar 18, 2026 · Artificial Intelligence

Variable-Scaling PINN for 2D Navier‑Stokes: How Coordinate Rescaling Improves Stiff PDE Training

This tutorial explains how a simple coordinate scaling (VS‑PINN) reduces stiffness in physics‑informed neural networks, demonstrates its implementation in JAX for the 2D steady incompressible Navier‑Stokes cylinder‑flow benchmark, and shows that after 80 000 Adam iterations the relative errors drop to 2.10 % (u), 5.06 % (v) and 4.45 % (p).

JAXNavier-StokesPINN
0 likes · 24 min read
Variable-Scaling PINN for 2D Navier‑Stokes: How Coordinate Rescaling Improves Stiff PDE Training
AI Agent Research Hub
AI Agent Research Hub
Mar 16, 2026 · Artificial Intelligence

How NTK Adaptive Weighting and Multi‑Scale Fourier Features Enable PINNs to Solve High‑Frequency PDEs

This tutorial explains why standard physics‑informed neural networks fail on high‑frequency partial differential equations due to spectral bias, and demonstrates how random Fourier feature embeddings, multi‑scale concatenation or spatio‑temporal separation, and Neural Tangent Kernel‑based adaptive loss weighting together overcome the bias and achieve accurate, stable solutions for heat, Poisson, and wave equations using JAX.

Fourier FeaturesJAXMulti-Scale
0 likes · 23 min read
How NTK Adaptive Weighting and Multi‑Scale Fourier Features Enable PINNs to Solve High‑Frequency PDEs
AI Agent Research Hub
AI Agent Research Hub
Mar 14, 2026 · Artificial Intelligence

Adaptive-Weight NTK-PINN Solves High-Frequency Wave Equation Using JAX

This tutorial explains how the Neural Tangent Kernel (NTK) perspective reveals the loss‑balance problem in Physics‑Informed Neural Networks (PINNs), introduces an NTK‑based adaptive‑weight algorithm, provides a full JAX implementation for a 1‑D high‑frequency wave equation, and shows that input normalisation dramatically improves accuracy while only modestly increasing training time.

JAXNTKPINN
0 likes · 27 min read
Adaptive-Weight NTK-PINN Solves High-Frequency Wave Equation Using JAX
AI2ML AI to Machine Learning
AI2ML AI to Machine Learning
Dec 29, 2025 · Artificial Intelligence

How Brin’s Return Powers Google’s First ‘Sword’: The TPU Hardware Revolution

The article examines Google’s AI resurgence after Sergey Brin’s comeback, detailing the evolution of TPU hardware from v1 to v7, the strategic focus on algorithmic efficiency, comparisons with Nvidia’s B200, the role of JAX/XLA, and how these advances create a powerful competitive moat for Google’s AI infrastructure.

AI hardwareGoogle TPUJAX
0 likes · 8 min read
How Brin’s Return Powers Google’s First ‘Sword’: The TPU Hardware Revolution
AntTech
AntTech
Nov 4, 2025 · Artificial Intelligence

Unlock Native TPU Inference with SGLang-Jax: A Jax‑Powered Open‑Source Engine

SGLang-Jax is a cutting‑edge, fully Jax‑based open‑source inference engine that delivers native TPU performance, integrates advanced features like continuous batching, tensor and expert parallelism, and speculative decoding, while providing detailed installation and usage guidance for developers.

JAXSGLang-JaxTPU inference
0 likes · 10 min read
Unlock Native TPU Inference with SGLang-Jax: A Jax‑Powered Open‑Source Engine
Data Party THU
Data Party THU
Oct 20, 2025 · Artificial Intelligence

Fine-Tuning LLMs on TPU with Tunix: A Step‑by‑Step QLoRA Guide

This article introduces Google’s Tunix library for JAX‑based LLM post‑training, explains its core features such as supervised fine‑tuning, reinforcement learning and knowledge distillation, and provides detailed installation steps and a complete TPU‑accelerated QLoRA fine‑tuning workflow on the Gemma 2B model, including code snippets and inference testing.

AIFine-tuningJAX
0 likes · 8 min read
Fine-Tuning LLMs on TPU with Tunix: A Step‑by‑Step QLoRA Guide
21CTO
21CTO
Mar 18, 2024 · Artificial Intelligence

Inside Grok-1: Elon Musk’s Open‑Source 314B LLM Architecture Revealed

Elon Musk’s AI startup xAI has open‑sourced its 314‑billion‑parameter Grok‑1 model, detailing its Rust‑based, JAX‑powered architecture, extensive parameter count, training data limits, licensing terms, hardware requirements, and community reactions, offering developers unprecedented access to a competitive large‑language‑model framework.

AIGrok-1JAX
0 likes · 9 min read
Inside Grok-1: Elon Musk’s Open‑Source 314B LLM Architecture Revealed
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Feb 23, 2024 · Artificial Intelligence

Google’s Open‑Source Gemma Large Language Model: Architecture, Performance, and Community Reception

Google has released the open‑source Gemma LLM series (2B and 7B parameters) built on Gemini‑style architecture, offering free, commercial‑ready models that run on notebooks, support JAX/PyTorch/TensorFlow, outperform many open‑source peers, and have quickly sparked extensive community testing and discussion.

Artificial IntelligenceGoogleJAX
0 likes · 5 min read
Google’s Open‑Source Gemma Large Language Model: Architecture, Performance, and Community Reception
DaTaobao Tech
DaTaobao Tech
Jul 15, 2022 · Artificial Intelligence

Edge AI Model Evaluation and Optimization with TensorFlow, JAX, and TVM

The article demonstrates how to evaluate, compress, and convert deep‑learning models for edge devices using TensorFlow, JAX, and TVM—showing a faster iPhone‑based MNIST training benchmark, FLOPs measurement scripts, TFLite/ONNX/CoreML conversion, TVM compilation with auto‑tuning, and up to 50 % speed improvements on mobile NPU hardware.

JAXTVMTensorFlow
0 likes · 29 min read
Edge AI Model Evaluation and Optimization with TensorFlow, JAX, and TVM
Alibaba Terminal Technology
Alibaba Terminal Technology
Jun 22, 2022 · Artificial Intelligence

How Fast Can Your Smartphone Run ML Models? Exploring Edge AI Optimization

This article examines the computational capabilities of modern mobile devices for machine learning, compares training times on a MacBook and iPhone, explains model evaluation metrics like FLOPs, and provides step‑by‑step guides for converting and optimizing models using TensorFlow, PyTorch, ONNX, JAX, and TVM for edge deployment.

JAXModel OptimizationTVM
0 likes · 29 min read
How Fast Can Your Smartphone Run ML Models? Exploring Edge AI Optimization