The Design Space of Tri-Modal Masked Diffusion Models

Apple Machine LearningOctober 14, 2026en

Apple Machine Learning

AI Global Wire

Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and finetuning a base unimodal model for bi-modal generation. Diverging from previous approaches, we introduce the first tri-modal Masked Diffusion Models (MDM) pretrained from scratch on text, image-text, and audio-text data. We systematically analyze multimodal scaling laws, modality mixing ratios, noise schedules, batch-size effects and provide optimized inference sampling defaults. Our batch-size analysis yields a novel stochastic differential equation (SDE) based…

This is a short summary published by AI Global Wire. The full article is owned and hosted by Apple Machine Learning — open it there to read it in full.

• Verktyg
• Bild
• Reglering