AI RESEARCH
Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling
arXiv CS.LG
•
ArXi:2604.01577v1 Announce Type: new We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable internal structures that evolve alongside the input.