扩散模型论文趋势 2023–2026

扩散、flow matching 与 score-based 生成

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,900 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

扩散模型论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202332786109138660
20245202601954961,471
20256944873465512,078
20266616947286082,691

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部扩散模型论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 6,899 篇，第 9 / 138 页

  1. CVPR 2026PLACID Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories
  2. CVPR 2026PlannerRFT Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning
  3. CVPR 2026Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers
  4. CVPR 2026PnP-CM Consistency Models as Plug-and-Play Priors for Inverse Problems
  5. CVPR 2026Points-to-3D Structure-Aware 3D Generation with Point Cloud Priors
  6. CVPR 2026Polyphony Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and
  7. CVPR 2026PoseD-Flow Versatile and Guided Flow Matching Model of Human Pose
  8. CVPR 2026PR-IQA Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis
  9. CVPR 2026Pressure2Motion Hierarchical Human Motion Reconstruction from Ground Pressure with Text
  10. CVPR 2026PrITTI Primitive-based Generation of Controllable and Editable 3D Semantic Urban
  11. CVPR 2026PrivateEyes Gaze-Preserving Anonymization for Data Sharing
  12. CVPR 2026Probabilistic Discrepancy Learning for Roadside LiDAR Scene Completion
  13. CVPR 2026Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
  14. CVPR 2026Progressive Supernet Training for Efficient Visual Autoregressive Modeling
  15. CVPR 2026ProjFlow Projection Sampling with Flow Matching for Zero-Shot Exact Spatial
  16. CVPR 2026PROMO Promptable Outfitting for Efficient High-Fidelity Virtual Try-On
  17. CVPR 2026PromptEnhancer Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
  18. CVPR 2026PromptLoop Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model
  19. CVPR 2026PropFly Learning to Propagate via On-the-Fly Supervision from Pre-trained Video
  20. CVPR 2026Prototype-Guided Concept Erasure in Diffusion Models
  21. CVPR 2026Proxy-Tuning Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation
  22. CVPR 2026PS-SR Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
  23. CVPR 2026PyramidalWan On Making Pretrained Video Model Pyramidal for Efficient Inference
  24. CVPR 2026Qwen-Image-Layered Towards Inherent Editability via Layer Decomposition
  25. CVPR 2026RADAR VQ-VAE Decoder of VAR is a Good Student for
  26. CVPR 2026RAISE Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment
  27. CVPR 2026RAPID Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video
  28. CVPR 2026RawMetaDiff Unlocking Extreme Darkness from Dual-Exposure RAW with Meta-Guided Diffusion
  29. CVPR 2026RDF-MIG A Robust Diffusion Framework for Masked Image Generation to
  30. CVPR 2026REACH Explicit Recovery Behavior for Diffusion Policies
  31. CVPR 2026Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep
  32. CVPR 2026Realiz3D 3D Generation Made Photorealistic via Domain-Aware Learning
  33. CVPR 2026RebRL Reinforcing Discrete Visual Diffusion Models with Rebalanced Timestep Credits
  34. CVPR 2026ReCoFuse Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling
  35. CVPR 2026Rectifying Latent Space for Generative Single-Image Reflection Removal
  36. CVPR 2026RecTok Reconstruction Distillation along Rectified Flow
  37. CVPR 2026Red-teaming Retrieval-Augmented Diffusion Models via Poisoning Knowledge Bases
  38. CVPR 2026Refacade Editing Object with Given Reference Texture
  39. CVPR 2026Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
  40. CVPR 2026Reflection Separation from a Single Image via Joint Latent Diffusion
  41. CVPR 2026ReFlow Self-correction Motion Learning for Dynamic Scene Reconstruction
  42. CVPR 2026Region-Adaptive Sampling for Diffusion Transformers
  43. CVPR 2026RegionRoute Regional Style Transfer with Diffusion Model
  44. CVPR 2026ReHyAt Recurrent Hybrid Attention for Video Diffusion Transformers
  45. CVPR 2026Relightful Video Portrait Harmonization
  46. CVPR 2026Remote Sensing Image Super-Resolution for Imbalanced Textures A Texture-Aware Diffusion
  47. CVPR 2026RenderFlow Single-Step Neural Rendering via Flow Matching
  48. CVPR 2026Repurposing 3D Generative Model for Autoregressive Layout Generation
  49. CVPR 2026ResCa Residual Caching for Diffusion Transformers Acceleration
  50. CVPR 2026ResDiT Evoking the Intrinsic Resolution Scalability in Diffusion Transformers

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查扩散模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "diffusion-models"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇扩散模型论文？
共 6,900 篇，按年份分别是 2023 年 660 篇、2024 年 1,471 篇、2025 年 2,078 篇、2026 年 2,691 篇。
NeurIPS 2026 有多少篇扩散模型论文？
NeurIPS 2026 有 661 篇扩散模型论文，上一届是 694 篇。
ICLR 2026 有多少篇扩散模型论文？
ICLR 2026 有 694 篇扩散模型论文，上一届是 487 篇。
ICML 2026 有多少篇扩散模型论文？
ICML 2026 有 728 篇扩散模型论文，上一届是 346 篇。
CVPR 2026 有多少篇扩散模型论文？
CVPR 2026 有 608 篇扩散模型论文，上一届是 551 篇。
哪个会议的扩散模型论文最多？
NeurIPS，2023–2026 年共 2,202 篇。

「深度学习」下的其他主题