Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces. To reduce this cost, block-diffusion language models decode many positions in parallel over a few denoising steps and are substantially faster, yet naively converting an AR re-ranker into one opens two accuracy gaps: (1) a structural gap: answer positions are denoised in parallel
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 unknownNew benchmark exposes reasoning gaps in top models →
- LinkedLinked via unknownDiffusionGemma: 4x faster text generation →
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “Diffusion-GR2: Diffusion Generative Reasoning Re-ranker” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “Diffusion-GR2: Diffusion Generative Reasoning Re-ranker” ≈ “stabilityai/stable-diffusion-3.5-large””
- LinkedLinked via arxiv author · 85%Zhuoxuan Zhang →
“Diffusion-GR2: Diffusion Generative Reasoning Re-ranker”
- LinkedLinked via arxiv author · 85%Kangqi Ni →
“Diffusion-GR2: Diffusion Generative Reasoning Re-ranker”
- LinkedLinked via arxiv author · 85%Yuhang Chen →
“Diffusion-GR2: Diffusion Generative Reasoning Re-ranker”
- LinkedLinked via arxiv author · 85%Mingfu Liang →
“Diffusion-GR2: Diffusion Generative Reasoning Re-ranker”