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 346 篇，第 6 / 7 页

  1. ICML 2025ReFrame: Layer Caching for Accelerated Inference in Real-Time Rendering
  2. ICML 2025REG: Rectified Gradient Guidance for Conditional Diffusion Models
  3. ICML 2025ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation
  4. ICML 2025RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
  5. ICML 2025Rethinking Score Distilling Sampling for 3D Editing and Generation
  6. ICML 2025Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate
  7. ICML 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  8. ICML 2025Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
  9. ICML 2025Riemannian Diffusion Adaptation for Distributed Optimization on Manifolds
  10. ICML 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
  11. ICML 2025RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control
  12. ICML 2025Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
  13. ICML 2025S4S: Solving for a Fast Diffusion Model Solver
  14. ICML 2025SADA: Stability-guided Adaptive Diffusion Acceleration
  15. ICML 2025SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
  16. ICML 2025SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation
  17. ICML 2025Sample-specific Noise Injection for Diffusion-based Adversarial Purification
  18. ICML 2025SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
  19. ICML 2025SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
  20. ICML 2025Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching
  21. ICML 2025Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
  22. ICML 2025Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
  23. ICML 2025Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport
  24. ICML 2025Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions
  25. ICML 2025SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
  26. ICML 2025SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning
  27. ICML 2025Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
  28. ICML 2025Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
  29. ICML 2025Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN
  30. ICML 2025Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation
  31. ICML 2025Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models
  32. ICML 2025SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems
  33. ICML 2025SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
  34. ICML 2025Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
  35. ICML 2025Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling
  36. ICML 2025Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
  37. ICML 2025Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo
  38. ICML 2025Sounding that Object: Interactive Object-Aware Image to Audio Generation
  39. ICML 2025Sparse Autoencoders, Again?
  40. ICML 2025Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  41. ICML 2025Spatial Reasoning with Denoising Models
  42. ICML 2025Spherical-Nested Diffusion Model for Panoramic Image Outpainting
  43. ICML 2025SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images
  44. ICML 2025STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification
  45. ICML 2025Stealix: Model Stealing via Prompt Evolution
  46. ICML 2025Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
  47. ICML 2025Stochastic Deep Restoration Priors for Imaging Inverse Problems
  48. ICML 2025Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
  49. ICML 2025Stream-level Flow Matching with Gaussian Processes
  50. ICML 2025Sundial: A Family of Highly Capable Time Series Foundation Models

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