2 papers
cs.LG2026
Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure
Jingda Wu, Changxiao Cai
Masked diffusion models (MDMs) generate discrete data by iteratively unmasking multiple tokens in parallel using a learned mask predictor. Their output carries two errors: parallel…
stat.ML2026
Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
Jingda Wu, Changxiao Cai
Score-based diffusion models have demonstrated remarkable empirical success in learning high-dimensional distributions, particularly those exhibiting low-dimensional and multi-moda…