CoDeepNEAT: Neural Architecture Search
A novel algorithm that automatically discovers optimal deep architectures by coevolving both macro and micro structure. Scaled to large distributed environments with hundreds of GPUs and applied across vision and language tasks.
NAS
Neuroevolution
Distributed
MEA: Evolutionary Bilevel Optimization
Meta-evolutionary bilevel algorithm for complex control problems, applied to challenging tasks including helicopter hovering and sparse-reward RL, optimizing topology and weights simultaneously where gradient-based RL struggles to converge.
Evolution
RL
Control
EPBT: Population-Based Training
Evolves neural-network hyperparameters and loss functions during training. Backed by scalable distributed infrastructure for large-scale evolutionary optimization in parallel with gradient-based learning.
PBT
AutoML
Distributed
Code Archaeologist
Agentic system that reasons over repository histories (Git/LFS) to detect architectural patterns, surface technical debt, and support large-scale code understanding.
Agents
Code Analysis