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 487 篇，第 8 / 10 页

  1. ICLR 2025RB-Modulation: Training-Free Stylization using Reference-Based Modulation
  2. ICLR 2025RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
  3. ICLR 2025Real-Time Video Generation with Pyramid Attention Broadcast
  4. ICLR 2025Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
  5. ICLR 2025Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment
  6. ICLR 2025Regularization by Texts for Latent Diffusion Inverse Solvers
  7. ICLR 2025Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features
  8. ICLR 2025Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
  9. ICLR 2025Representative Guidance: Diffusion Model Sampling with Coherence
  10. ICLR 2025Repulsive Latent Score Distillation for Solving Inverse Problems
  11. ICLR 2025Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks
  12. ICLR 2025Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
  13. ICLR 2025Rethinking Visual Counterfactual Explanations Through Region Constraint
  14. ICLR 2025Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
  15. ICLR 2025Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization
  16. ICLR 2025Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
  17. ICLR 2025RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction
  18. ICLR 2025Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples
  19. ICLR 2025Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport
  20. ICLR 2025Robust Representation Consistency Model via Contrastive Denoising
  21. ICLR 2025Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
  22. ICLR 2025Robust-PIFu: Robust Pixel-aligned Implicit Function for 3D Human Digitalization from a Single Image
  23. ICLR 2025RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement Learning
  24. ICLR 2025SafeDiffuser: Safe Planning with Diffusion Probabilistic Models
  25. ICLR 2025SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
  26. ICLR 2025SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
  27. ICLR 2025SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
  28. ICLR 2025Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
  29. ICLR 2025Scaling Diffusion Language Models via Adaptation from Autoregressive Models
  30. ICLR 2025Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport
  31. ICLR 2025Scaling up Masked Diffusion Models on Text
  32. ICLR 2025Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models
  33. ICLR 2025Score-based Self-supervised MRI Denoising
  34. ICLR 2025Self-Supervised Diffusion Models for Electron-Aware Molecular Representation Learning
  35. ICLR 2025Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement
  36. ICLR 2025Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations
  37. ICLR 2025Semantix: An Energy-guided Sampler for Semantic Style Transfer
  38. ICLR 2025Sequential Controlled Langevin Diffusions
  39. ICLR 2025SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation
  40. ICLR 2025Shallow diffusion networks provably learn hidden low-dimensional structure
  41. ICLR 2025ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design
  42. ICLR 2025SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings
  43. ICLR 2025Simple Guidance Mechanisms for Discrete Diffusion Models
  44. ICLR 2025Simple ReFlow: Improved Techniques for Fast Flow Models
  45. ICLR 2025Simplifying, Stabilizing and Scaling Continuous-time Consistency Models
  46. ICLR 2025SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects
  47. ICLR 2025Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation
  48. ICLR 2025SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
  49. ICLR 2025SMITE: Segment Me In TimE
  50. ICLR 2025Solving New Tasks by Adapting Internet Video Knowledge

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