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 1,527 篇，第 23 / 31 页

  1. ICLR 2025StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces
  2. ICLR 2025Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling
  3. ICLR 2025Structure Language Models for Protein Conformation Generation
  4. ICLR 2025Supervised and Semi-Supervised Diffusion Maps with Label-Driven Diffusion
  5. ICLR 2025SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency
  6. ICLR 2025SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
  7. ICLR 2025SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix
  8. ICLR 2025Swing-by Dynamics in Concept Learning and Compositional Generalization
  9. ICLR 2025SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
  10. ICLR 2025SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models
  11. ICLR 2025SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups
  12. ICLR 2025SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
  13. ICLR 2025Synthesizing Realistic fMRI: A Physiological Dynamics-Driven Hierarchical Diffusion Model for Efficient fMRI Acquisition
  14. ICLR 2025Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data
  15. ICLR 2025T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
  16. ICLR 2025T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
  17. ICLR 2025TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
  18. ICLR 2025TabWak: A Watermark for Tabular Diffusion Models
  19. ICLR 2025TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
  20. ICLR 2025Targeted Attack Improves Protection against Unauthorized Diffusion Customization
  21. ICLR 2025TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel Conditioning
  22. ICLR 2025Test-time Alignment of Diffusion Models without Reward Over-optimization
  23. ICLR 2025Text-to-Image Rectified Flow as Plug-and-Play Priors
  24. ICLR 2025Text2PDE: Latent Diffusion Models for Accessible Physics Simulation
  25. ICLR 2025TexTailor: Customized Text-aligned Texturing via Effective Resampling
  26. ICLR 2025TFG-Flow: Training-free Guidance in Multimodal Generative Flow
  27. ICLR 2025The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise
  28. ICLR 2025The Superposition of Diffusion Models Using the Itô Density Estimator
  29. ICLR 2025Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
  30. ICLR 2025Think while You Generate: Discrete Diffusion with Planned Denoising
  31. ICLR 2025ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge
  32. ICLR 2025TopoDiffusionNet: A Topology-aware Diffusion Model
  33. ICLR 2025Topological Schrödinger Bridge Matching
  34. ICLR 2025Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs
  35. ICLR 2025Toward Exploratory Inverse Constraint Inference with Generative Diffusion Verifiers
  36. ICLR 2025Towards Hierarchical Rectified Flow
  37. ICLR 2025Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling
  38. ICLR 2025Towards Realistic Data Generation for Real-World Super-Resolution
  39. ICLR 2025Towards Scalable Topological Regularizers
  40. ICLR 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
  41. ICLR 2025Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
  42. ICLR 2025Training Free Guided Flow-Matching with Optimal Control
  43. ICLR 2025Training-free Camera Control for Video Generation
  44. ICLR 2025Training-Free Diffusion Model Alignment with Sampling Demons
  45. ICLR 2025Trajectory attention for fine-grained video motion control
  46. ICLR 2025Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
  47. ICLR 2025Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers
  48. ICLR 2025Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy
  49. ICLR 2025Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
  50. ICLR 2025Truncated Consistency 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