Improving Sampling for Masked Diffusion Models via Information Gain
arXiv:2602.18176v1 Announce Type: new Abstract: Masked Diffusion Models (MDMs) offer greater flexibility in decoding order than autoregressive models but require careful planning to achieve high-quality …
Kaisen Yang, Jayden Teoh, Kaicheng Yang, Yitong Zhang, Alex Lamb
조회수 26회