AIBullisharXiv – CS AI · Mar 37/103
🧠
Dream2Learn: Structured Generative Dreaming for Continual Learning
Researchers introduce Dream2Learn (D2L), a continual learning framework that enables AI models to generate synthetic training data from their own internal representations, mimicking human dreaming for knowledge consolidation. The system creates novel 'dreamed classes' using diffusion models to improve forward knowledge transfer and prevent catastrophic forgetting in neural networks.