arXiv cs.CL
· Papers
Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance
arXiv:2608.00024v1 Announce Type: new Abstract: Although diffusion models have revolutionized continuous domains like image synthesis through high quality generations and controllable guidance mechanisms, bringing this controllability to the discrete, sequential nature of text remains an open challenge. Meanwhile, curr