Apple Introduces First Tri-Modal Masked Diffusion Model Pretrained From Scratch
Apple ML Research · rss · 2026-10-14
Apple ML researchers present the first tri-modal Masked Diffusion Model (MDM) pretrained from scratch on text, image-text, and audio-text data, exploring discrete diffusion as an alternative to autoregressive LMs.
- Systematic analysis of multimodal scaling laws, modality mixing ratios, noise schedules, and batch-size effects
- Provides optimized inference sampling defaults
- The batch-size analysis yields a novel SDE-based technique (details in the full paper)
More from Research
- AI 抢不走人类的品味：模型只会做常见的东西，而人脑天生奖励新奇 — tejaskumarlol · 2026-10-16
- Hugging Face launches AI4Science heatmap tracking open models from 79 orgs, AI2 and OpenMed lead — anshulkundaje · 2026-10-16
- MIT's Neil Thompson: AI comes for tasks before jobs, and fixed costs favor big firms — bigdata · 2026-10-16
- UMD's PAIR framework bridges perception and action in VLA models via bridge tokens — Kaixi Feng · 2026-10-16
- CI-MSE offline metric hits -0.87 Spearman correlation with real robot task success vs weak raw MSE — chris_j_paxton · 2026-10-16
- Colossal Biosciences uses AI to decode genetic switches behind the extinct dodo — castrotech · 2026-10-16