GitHub

PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

Actively Developing: In the long term, we aim to develop a comprehensive physics simulator focused on real-to-sim, serving as an easy-to-use platform for XR, VR, and robotics applications. Feel free ...
InfoWorld

12 model-level deep cuts to slash AI training costs

Stop throwing money at GPUs for unoptimized models; using smart shortcuts like fine-tuning and quantization can slash your ...
GitHub

DL-MPC: A toolbox for deep learning-based nonlinear model predictive control

The TensorDL-MPC toolbox is a Python-based software developed using the TensorFlow framework. It leverages deep learning techniques to enhance the performance of traditional Model Predictive Control ...
IEEE

Spectral Bayesian Optimization Using a Physics-Informed Rational Szegö Kernel for Microwave Design

Abstract: Microwave device design increasingly relies on surrogate modeling to accelerate optimization and reduce costly electromagnetic (EM) simulations. This article presents a spectral Bayesian ...
IEEE

Constrained Evolutionary Bayesian Optimization for Expensive Constrained Optimization Problems With Inequality Constraints

Abstract: This article proposes a constrained evolutionary Bayesian optimization (CEBO) algorithm to cope with expensive constrained optimization problems with inequality constraints. The uniqueness ...
marktechpost

A Coding Implementation to Build a Conditional Bayesian Hyperparameter Optimization Pipeline with Hyperopt, TPE, and Early Stopping

In this tutorial, we implement an advanced Bayesian hyperparameter optimization workflow using Hyperopt and the Tree-structured Parzen Estimator (TPE) algorithm. We construct a conditional search ...