New PUMA method accelerates masked diffusion model training

Researchers have introduced Progressive UnMAsking (PUMA), a novel method to accelerate the training of Masked Diffusion Models (MDMs). PUMA aligns the masking patterns used during training with those employed during inference, thereby focusing optimization on more relevant masks. This approach has demonstrated a significant speed-up in pretraining, achieving approximately a 2.5x faster training time at the 125 million parameter scale. AI

IMPACT Accelerates training for diffusion models, potentially enabling faster iteration and development of generative AI.

RANK_REASON The cluster contains an academic paper detailing a new method for training diffusion models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Jaeyeon Kim
• Masked Diffusion Models
• Progressive UnMAsking

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →