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 728 篇，第 12 / 15 页

  1. ICML 2026ScDiVa: Masked Discrete Diffusion for Joint Modeling of Single-Cell Identity and Expression
  2. ICML 2026SceneDirector: Bridging Explicit Geometry and Generative Priors for Unified Driving Scene Editing
  3. ICML 2026SCNS: Continual Personalization of Diffusion Models via Submodular Concept Neuron Selection
  4. ICML 2026Score Based Error Correcting Code Decoder
  5. ICML 2026Score Correction for Generative Models with Probabilistic Constraints
  6. ICML 2026ScoreMatchingRiesz: Score Matching for Debiased Machine Learning and Policy Path Estimation
  7. ICML 2026ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition
  8. ICML 2026SDiD：Shared diffusion prior for efficient distributed stereo image compression
  9. ICML 2026SE(3)-Equivariant Flow Matching with Gaussian Process Priors for Geometric Trajectory Prediction
  10. ICML 2026SE(n)-Invariant Flow Matching: A General Framework with Application to Object Reassembly
  11. ICML 2026Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
  12. ICML 2026SeisMark: A Large-Scale Open Benchmark for Robust 3D Seismic Fault Detection
  13. ICML 2026Self-Augmenting Retrieval for Diffusion Language Models
  14. ICML 2026Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Edit via In-Context Learning
  15. ICML 2026Self-Refining Video Sampling
  16. ICML 2026Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
  17. ICML 2026Semantic Editing with Coupled Stochastic Differential Equations
  18. ICML 2026Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
  19. ICML 2026SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesis
  20. ICML 2026SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
  21. ICML 2026Set Diffusion: Interpolating Token Orderings between Autoregression and Diffusion for Fast and Flexible Decoding
  22. ICML 2026Set-Coupled Guidance: Set-Level Coordination in Diffusion-Based Dataset Distillation
  23. ICML 2026SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
  24. ICML 2026Shifting the Breaking Point of Flow Matching for Multi-Instance Editing
  25. ICML 2026SimGFM: Simplifying Discrete Flow Matching for Graph Generation
  26. ICML 2026Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
  27. ICML 2026Simple Denoising Diffusion Language Models
  28. ICML 2026Singular Proxies for Adaptive Caching in Diffusion Language Models
  29. ICML 2026Sinkhorn Normalization of Diffusion Kernels
  30. ICML 2026SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models
  31. ICML 2026Skipping the Zeros in Diffusion Models for Sparse Data Generation
  32. ICML 2026SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion
  33. ICML 2026SMD: Multi-view Safety-Critical Driving Video Generation in the Real-world Domain
  34. ICML 2026Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation
  35. ICML 2026Sobolev Regularized Score Difference Estimation in Diffusion Models
  36. ICML 2026SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
  37. ICML 2026Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
  38. ICML 2026Sparse Relaxed-Lasso Steering: Automatic Sparse Autoencoder Feature Selection for Precise Image Editing
  39. ICML 2026SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes
  40. ICML 2026Spatiotemporal Imputation with Graph-Informed Flow Matching
  41. ICML 2026Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
  42. ICML 2026Spectral Flow Matching: Stabilizing Stochastic GFlowNets via Frequency-Domain Regularization
  43. ICML 2026Spectral Guidance for Flexible and Efficient Control of Diffusion Models
  44. ICML 2026Spectrally-Guided Diffusion Noise Schedules
  45. ICML 2026SPEED: Sharpened-Teacher Distillation for Parallel Decoding of Diffusion Language Models
  46. ICML 2026SpeedVFI: One-step Diffusion for Efficient Video Frame Interpolation
  47. ICML 2026Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
  48. ICML 2026SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models
  49. ICML 2026ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding
  50. ICML 2026Stability Analysis of Sharpness-Aware Minimization

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