[RESEARCH_LOG · ARTICLES · INSIGHTS]

Technical
Research Log

Deep dives into simulation, numerical methods, AI architecture, and high-performance engineering from the team at Turing Intelligence.

All Simulation Machine Learning C++ & HPC Numerical Methods ADAS

Neural ODEs: When Physics-Informed Learning Actually Works

When should you use a neural ODE versus a classical numerical solver? We benchmark both on stiff ODE systems and find the surprising answer.

Cache-Oblivious Algorithms for High-Dimensional Particle Systems

How we achieved a 4× memory-bandwidth speedup on N-body particle simulations using cache-oblivious data layout strategies in modern C++.

Raytracing-Based Radar Simulation for FMCW Sensor Validation

A walkthrough of the physical model and implementation behind our FMCW radar simulator — used to generate ground-truth synthetic datasets for ADAS ML pipelines.

Runge–Kutta vs. Adaptive Step Methods: A Practical Guide for Stiff Systems

Practical guidance on choosing between fixed-step RK4 and adaptive solvers like DOPRI5 when you're working with stiff ODE systems in real-time control loops.

Building a Multi-Agent Simulation Engine in C++ from Scratch

The architecture decisions behind TuringLab's entity-component-system design for simulating thousands of concurrent autonomous agents with deterministic replay.

Distributed Training of Physics-Informed Neural Networks on HPC Clusters

How we scaled PINN training across 32 GPU nodes using custom gradient synchronisation strategies that respect the structure of the underlying PDEs.

[SUBSCRIBE_TO_RESEARCH_LOG]

Stay on the Bleeding Edge

New deep-dives on simulation, AI, and HPC engineering — delivered to your inbox when we publish, never more.