Masked Diffusion Decoding as $x$-Prediction Flow
Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens, but their standard decoder reduces each step to a binary action: a position is either committed to a single token or left fully masked, with no representation of partial belief in between. This all-or-nothing regime discards rich predictive information and forces premature, irrevocable commitments, leading to poor performance under a limited decoding budget. In this paper, we reinterpret mask prediction as clean-state prediction ($x$-prediction) and show that it can be used to induce a continuous flow in in
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.
- LinkedLinked via unknownminimal-diffusion-lm →
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-xl-base-1.0 →
“Fuzzy title match (0.73): “Masked Diffusion Decoding as $x$-Prediction Flow” ≈ “stabilityai/stable-diffusion-xl-base-1.0””
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “Masked Diffusion Decoding as $x$-Prediction Flow” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “Masked Diffusion Decoding as $x$-Prediction Flow” ≈ “stabilityai/stable-diffusion-3.5-large””
- PossiblePossibly related (embedding) · 59%Learning Unmasking Policies for Diffusion Language Models - Apple Machine Learning Research →
- PossiblePossibly related (embedding) · 45%GPT-2 Fully Decoded Internally Black Box Fully Open With Demo →