EVOLVE, an agentic framework that autonomously optimizes AI training data, model architectures, and learning algorithms — boosting MMLU scores by 18 points over human baselines.

RiverWare optimization can simultaneously solve over multiple reservoirs and multiple time periods with objectives such as maximizing hydropower value and balancing reservoir operations and impacts.

Simplex optimization is one of the simplest algorithms available to train a neural network. Understanding how simplex optimization works, and how it compares to the more commonly used back-propagation ...

ByteDance's Doubao AI team has open-sourced COMET, a Mixture of Experts (MoE) optimization framework that improves large language model (LLM) training efficiency while reducing costs. Already ...

Based on my experience, when working with a neural network, I generally try back-propagation training first and then check my results using either particle swarm optimization or evolutionary ...