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 1,792 篇，第 26 / 36 页

  1. CVPR 2024DemoFusion: Democratising High-Resolution Image Generation With No $$$
  2. CVPR 2024DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
  3. CVPR 2024Diff-BGM: A Diffusion Model for Video Background Music Generation
  4. CVPR 2024Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks
  5. CVPR 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
  6. CVPR 2024DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly
  7. CVPR 2024DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting
  8. CVPR 2024DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing
  9. CVPR 2024DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization
  10. CVPR 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans
  11. CVPR 2024DiffLoc: Diffusion Model for Outdoor LiDAR Localization
  12. CVPR 2024DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement
  13. CVPR 2024DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing
  14. CVPR 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction
  15. CVPR 2024DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation
  16. CVPR 2024DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
  17. CVPR 2024DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
  18. CVPR 2024DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model
  19. CVPR 2024DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
  20. CVPR 2024DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
  21. CVPR 2024Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion
  22. CVPR 2024DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models
  23. CVPR 2024Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features
  24. CVPR 2024Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D
  25. CVPR 2024Diffusion Model Alignment Using Direct Preference Optimization
  26. CVPR 2024Diffusion Models Without Attention
  27. CVPR 2024Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance
  28. CVPR 2024Diffusion Time-step Curriculum for One Image to 3D Generation
  29. CVPR 2024Diffusion-based Blind Text Image Super-Resolution
  30. CVPR 2024Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation
  31. CVPR 2024Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation
  32. CVPR 2024Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving
  33. CVPR 2024Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy Field
  34. CVPR 2024DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars
  35. CVPR 2024DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors
  36. CVPR 2024DiffusionLight: Light Probes for Free by Painting a Chrome Ball
  37. CVPR 2024DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data
  38. CVPR 2024DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion
  39. CVPR 2024DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression Approach
  40. CVPR 2024DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking
  41. CVPR 2024DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations
  42. CVPR 2024DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data
  43. CVPR 2024Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion
  44. CVPR 2024DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF
  45. CVPR 2024Distilled Datamodel with Reverse Gradient Matching
  46. CVPR 2024Distilling ODE Solvers of Diffusion Models into Smaller Steps
  47. CVPR 2024Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing
  48. CVPR 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
  49. CVPR 2024Don't Drop Your Samples! Coherence-Aware Training Benefits Conditional Diffusion
  50. CVPR 2024DPHMs: Diffusion Parametric Head Models for Depth-based Tracking

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