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
- Linked via arxiv authorZhuoxuan Zhang →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorKangqi Ni →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorYuhang Chen →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorMingfu Liang →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorXiaohan Wei →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorYunchen Pu →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorFei Tian →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorChonglin Sun →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorFrank Shyu →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorAdam →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorSong →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorSandeep Pandey →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorLuke Simon →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorTianlong Chen →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
- Linked via arxiv authorXi Liu →
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker