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 20 / 31 页

  1. ICLR 2025LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
  2. ICLR 2025Learned Reference-based Diffusion Sampler for multi-modal distributions
  3. ICLR 2025Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks
  4. ICLR 2025Learning to Discretize Denoising Diffusion ODEs
  5. ICLR 2025LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models
  6. ICLR 2025Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models
  7. ICLR 2025Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space
  8. ICLR 2025Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
  9. ICLR 2025Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
  10. ICLR 2025Linear combinations of latents in generative models: subspaces and beyond
  11. ICLR 2025Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models
  12. ICLR 2025Looking Backward: Streaming Video-to-Video Translation with Feature Banks
  13. ICLR 2025Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
  14. ICLR 2025Lossy Compression with Pretrained Diffusion Models
  15. ICLR 2025Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
  16. ICLR 2025Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation
  17. ICLR 2025Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling
  18. ICLR 2025Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
  19. ICLR 2025Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion
  20. ICLR 2025MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers
  21. ICLR 2025Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
  22. ICLR 2025Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos
  23. ICLR 2025MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation
  24. ICLR 2025Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
  25. ICLR 2025Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
  26. ICLR 2025Minimal Impact ControlNet: Advancing Multi-ControlNet Integration
  27. ICLR 2025Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models
  28. ICLR 2025MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
  29. ICLR 2025Modeling Complex System Dynamics with Flow Matching Across Time and Conditions
  30. ICLR 2025MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks
  31. ICLR 2025MorphoDiff: Cellular Morphology Painting with Diffusion Models
  32. ICLR 2025Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs
  33. ICLR 2025MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion
  34. ICLR 2025MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences
  35. ICLR 2025MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
  36. ICLR 2025Multi-domain Distribution Learning for De Novo Drug Design
  37. ICLR 2025Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen
  38. ICLR 2025Multi-objective antibody design with constrained preference optimization
  39. ICLR 2025Multi-Perspective Data Augmentation for Few-shot Object Detection
  40. ICLR 2025Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection
  41. ICLR 2025Multi-Robot Motion Planning with Diffusion Models
  42. ICLR 2025Multi-Task Dense Predictions via Unleashing the Power of Diffusion
  43. ICLR 2025Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning
  44. ICLR 2025MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
  45. ICLR 2025Neural Approximate Mirror Maps for Constrained Diffusion Models
  46. ICLR 2025Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry
  47. ICLR 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
  48. ICLR 2025No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
  49. ICLR 2025Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models
  50. ICLR 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generation

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