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 123 / 138 页

  1. NeurIPS 2024PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
  2. NeurIPS 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
  3. NeurIPS 2024ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing
  4. NeurIPS 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
  5. NeurIPS 2024PromptFix: You Prompt and We Fix the Photo
  6. NeurIPS 2024Provable Posterior Sampling with Denoising Oracles via Tilted Transport
  7. NeurIPS 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
  8. NeurIPS 2024PTQ4DiT: Post-training Quantization for Diffusion Transformers
  9. NeurIPS 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignment
  10. NeurIPS 2024PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
  11. NeurIPS 2024QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
  12. NeurIPS 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
  13. NeurIPS 2024RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
  14. NeurIPS 2024Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
  15. NeurIPS 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
  16. NeurIPS 2024ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
  17. NeurIPS 2024RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
  18. NeurIPS 2024ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
  19. NeurIPS 2024Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
  20. NeurIPS 2024Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
  21. NeurIPS 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
  22. NeurIPS 2024ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations
  23. NeurIPS 2024Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
  24. NeurIPS 2024Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
  25. NeurIPS 2024Rethinking Score Distillation as a Bridge Between Image Distributions
  26. NeurIPS 2024Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective
  27. NeurIPS 2024Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
  28. NeurIPS 2024Retrieval-Augmented Diffusion Models for Time Series Forecasting
  29. NeurIPS 2024Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
  30. NeurIPS 2024ReVideo: Remake a Video with Motion and Content Control
  31. NeurIPS 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
  32. NeurIPS 2024SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
  33. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
  34. NeurIPS 2024Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
  35. NeurIPS 2024SceneCraft: Layout-Guided 3D Scene Generation
  36. NeurIPS 2024SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout
  37. NeurIPS 2024Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
  38. NeurIPS 2024Schrodinger Bridge Flow for Unpaired Data Translation
  39. NeurIPS 2024Score Distillation via Reparametrized DDIM
  40. NeurIPS 2024Score-based generative models are provably robust: an uncertainty quantification perspective
  41. NeurIPS 2024Score-Optimal Diffusion Schedules
  42. NeurIPS 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
  43. NeurIPS 2024SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
  44. NeurIPS 2024Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
  45. NeurIPS 2024Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
  46. NeurIPS 2024SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
  47. NeurIPS 2024SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
  48. NeurIPS 2024Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors
  49. NeurIPS 2024Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation
  50. NeurIPS 2024SF-V: Single Forward Video Generation Model

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