EMI-Group

Infrastructure for evolutionary AI systems. GPU-accelerated, PyTorch-based optimization with an ecosystem of algorithm libraries, benchmarks, and tools.

EvoX Genesis is an autonomous system for long-horizon software evolution that recursively builds, continues, and transforms complex software from high-level objectives.

GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)

EvoRL is a fully GPU-accelerated framework for Evolutionary Reinforcement Learning, implemented with JAX. It supports Reinforcement Learning (RL), Evolutionary Computation (EC), Evolution-guided...

A GPU-accelerated library for Tree-based Genetic Programming, leveraging PyTorch and custom CUDA kernels for high-performance evolutionary computation. It supports symbolic regression,...

EvoMO is a GPU-accelerated library for evolutionary multiobjective optimization (EMO)

MetaDE is a GPU-accelerated evolutionary framework that optimizes Differential Evolution (DE) strategies via meta-level evolution. Supporting both JAX and PyTorch, it dynamically adapts mutation...

iStratDE is a GPU-accelerated Differential Evolution framework that enhances performance through individual-level strategy diversity. By assigning unique, fixed strategies to each individual at...

[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

Transforming Neural Architecture Search (NAS) into multi-objective optimization problems. A benchmark suite for testing evolutionary algorithms in deep learning.

[TEVC] Evolutionary Generative Optimization(EvoGO) is a fully data-driven framework for black-box optimization.