From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts to generalize beyond their individual training data. Recent theoretical corrections introduce time-dependent mixing weights to better align composed diffusion dynamics with the intended target. However, these methods are fundamentally limited by working on a per-sample basis, treating each generated state monolithically and ignoring the potential spatial or functional specializations of different experts. In this wo
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%tensorflow/probability →
- PossiblePossibly related (embedding) · 46%minimal-diffusion-lm →
- PossiblePossibly related (embedding) · 45%Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains →
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-xl-base-1.0 →
“Fuzzy title match (0.73): “From Global to Factor-Wise Expert Composition in Discrete Di” ≈ “stabilityai/stable-diffusion-xl-base-1.0””
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “From Global to Factor-Wise Expert Composition in Discrete Di” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “From Global to Factor-Wise Expert Composition in Discrete Di” ≈ “stabilityai/stable-diffusion-3.5-large””
- LinkedLinked via arxiv author · 85%Haozhe Huang →
“From Global to Factor-Wise Expert Composition in Discrete Diffusion Models”
- LinkedLinked via arxiv author · 85%Yudong Xu →
“From Global to Factor-Wise Expert Composition in Discrete Diffusion Models”