用語辞典

A diffusion model generates realistic images or media by refining random noise through multiple learned steps

A context window refers to the maximum amount of input data—measured in tokens—that a large language model (LLM) can process at one time

Transfer learning is an AI technique where a model trained on one task is reused or adapted for a different but related task, helping save time and data during training.

Pruning in AI refers to the process of removing unnecessary or less important parts of a neural network, such as weights or nodes, to make the model smaller, faster, and more efficient—without significantly reducing its accuracy.