botorch

A lightweight Unity asset for running powerful Bayesian optimization. It supports practical human-in-the-loop workflows where the optimizer proposes parameter values, collects user feedback as objective scores, updates the model, and recommends the next design iteration.

Probability-density-based deep learning paradigm for the fuzzy design of functional metastructures. Research AAAS & NeurIPS ML4PS.

A pipeline to generate user-preferred photo-realistic avatars using stable-diffusion and bayesian-optimization.

Hyperpatameter Bayesian Optimization for Image Classification in PyTorch

Demonstrating the use of Prefect to orchestrate the creation of machine learning surrogate models as applied to mechanistic crop models.

An introduction to Bayesian optimization with an example of accelerator tuning task.

BO Forge is a local-first, CSV-backed Bayesian optimization toolkit for mixed-variable, multi-objective, staged, multi-fidelity, contextual, and noisy experimental campaigns.

Uncertainty-aware Labelled Augmentations for High Dimensional Latent Space Bayesian Optimisation

Optimization of light-by-light scattering scenarios with BoTorch engine.

A concept-first repository of Jupyter notebooks tracing a path from PyTorch fundamentals to Bayesian Optimisation.

Testing submission of AWS batch jobs using BoTorch (via Ax) and TorchX for neural architecture search

Closed-loop molecular discovery agent combining Bayesian optimization (BoTorch), a Gymnasium environment, and a simulated QED + synthetic-accessibility oracle for autonomous drug-candidate selection.

This repository applies Machine Learning to Quantum Optimal Control (QOC) for preparing the highly entangled Greenberger–Horne–Zeilinger (GHZ) state.

🧬 Pareto-optimal drug discovery via qNEHVI Bayesian optimization over molecular libraries — built with BoTorch, PyTorch & RDKit

Build AI-driven 3D avatar animation from natural language commands for real-time WebGL interaction and training flows

Reproducible BoTorch benchmarks comparing qNEHVI, qEHVI and qNParEGO with GP and random-forest surrogates.

Bayesian Optimization framework for CO₂ mineralization using ferrochrome steel slag. Bachelor thesis, RWTH Aachen (AVT.SVT), 2025.

Исследовательский проект по Bayesian Optimization и transfer learning на BoTorch / GPyTorch

Experimental DoE + Bayesian Optimization with Domain Knowledge injection for chemistry/materials labs

Code for the paper: Wasserstein enabled Bayesian optimization of composite functions.