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 2,202 篇，第 36 / 45 页

  1. NeurIPS 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
  2. NeurIPS 2024ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
  3. NeurIPS 2024RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
  4. NeurIPS 2024ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
  5. NeurIPS 2024Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
  6. NeurIPS 2024Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
  7. NeurIPS 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
  8. NeurIPS 2024ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations
  9. NeurIPS 2024Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
  10. NeurIPS 2024Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
  11. NeurIPS 2024Rethinking Score Distillation as a Bridge Between Image Distributions
  12. NeurIPS 2024Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective
  13. NeurIPS 2024Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
  14. NeurIPS 2024Retrieval-Augmented Diffusion Models for Time Series Forecasting
  15. NeurIPS 2024Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
  16. NeurIPS 2024ReVideo: Remake a Video with Motion and Content Control
  17. NeurIPS 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
  18. NeurIPS 2024SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
  19. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
  20. NeurIPS 2024Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
  21. NeurIPS 2024SceneCraft: Layout-Guided 3D Scene Generation
  22. NeurIPS 2024SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout
  23. NeurIPS 2024Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
  24. NeurIPS 2024Schrodinger Bridge Flow for Unpaired Data Translation
  25. NeurIPS 2024Score Distillation via Reparametrized DDIM
  26. NeurIPS 2024Score-based generative models are provably robust: an uncertainty quantification perspective
  27. NeurIPS 2024Score-Optimal Diffusion Schedules
  28. NeurIPS 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
  29. NeurIPS 2024SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
  30. NeurIPS 2024Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
  31. NeurIPS 2024Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
  32. NeurIPS 2024SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
  33. NeurIPS 2024SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
  34. NeurIPS 2024Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors
  35. NeurIPS 2024Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation
  36. NeurIPS 2024SF-V: Single Forward Video Generation Model
  37. NeurIPS 2024Shared Autonomy with IDA: Interventional Diffusion Assistance
  38. NeurIPS 2024SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
  39. NeurIPS 2024ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling
  40. NeurIPS 2024SimGen: Simulator-conditioned Driving Scene Generation
  41. NeurIPS 2024Simple and Effective Masked Diffusion Language Models
  42. NeurIPS 2024Simple and Fast Distillation of Diffusion Models
  43. NeurIPS 2024Simplified and Generalized Masked Diffusion for Discrete Data
  44. NeurIPS 2024Simulation-Free Training of Neural ODEs on Paired Data
  45. NeurIPS 2024Slight Corruption in Pre-training Data Makes Better Diffusion Models
  46. NeurIPS 2024Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
  47. NeurIPS 2024Solving Inverse Problems via Diffusion Optimal Control
  48. NeurIPS 2024SongCreator: Lyrics-based Universal Song Generation
  49. NeurIPS 2024Sparse High Rank Adapters
  50. NeurIPS 2024SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening

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