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 2,078 篇，第 27 / 42 页

  1. ICML 2025S4S: Solving for a Fast Diffusion Model Solver
  2. ICML 2025SADA: Stability-guided Adaptive Diffusion Acceleration
  3. ICML 2025SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
  4. ICML 2025SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation
  5. ICML 2025Sample-specific Noise Injection for Diffusion-based Adversarial Purification
  6. ICML 2025SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
  7. ICML 2025SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
  8. ICML 2025Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching
  9. ICML 2025Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
  10. ICML 2025Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
  11. ICML 2025Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport
  12. ICML 2025Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions
  13. ICML 2025SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
  14. ICML 2025SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning
  15. ICML 2025Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
  16. ICML 2025Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
  17. ICML 2025Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN
  18. ICML 2025Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation
  19. ICML 2025Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models
  20. ICML 2025SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems
  21. ICML 2025SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
  22. ICML 2025Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
  23. ICML 2025Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling
  24. ICML 2025Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
  25. ICML 2025Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo
  26. ICML 2025Sounding that Object: Interactive Object-Aware Image to Audio Generation
  27. ICML 2025Sparse Autoencoders, Again?
  28. ICML 2025Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  29. ICML 2025Spatial Reasoning with Denoising Models
  30. ICML 2025Spherical-Nested Diffusion Model for Panoramic Image Outpainting
  31. ICML 2025SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images
  32. ICML 2025STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification
  33. ICML 2025Stealix: Model Stealing via Prompt Evolution
  34. ICML 2025Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
  35. ICML 2025Stochastic Deep Restoration Priors for Imaging Inverse Problems
  36. ICML 2025Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
  37. ICML 2025Stream-level Flow Matching with Gaussian Processes
  38. ICML 2025Sundial: A Family of Highly Capable Time Series Foundation Models
  39. ICML 2025Supercharging Graph Transformers with Advective Diffusion
  40. ICML 2025Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion
  41. ICML 2025TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular Data
  42. ICML 2025Taming Diffusion for Dataset Distillation with High Representativeness
  43. ICML 2025Taming Rectified Flow for Inversion and Editing
  44. ICML 2025Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion
  45. ICML 2025Targeted Unlearning with Single Layer Unlearning Gradient
  46. ICML 2025Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
  47. ICML 2025TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change Awareness
  48. ICML 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
  49. ICML 2025Temporal Difference Flows
  50. ICML 2025Test-Time Canonicalization by Foundation Models for Robust Perception

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