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 6,899 篇，第 122 / 138 页

  1. NeurIPS 2024MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
  2. NeurIPS 2024Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
  3. NeurIPS 2024MotionBooth: Motion-Aware Customized Text-to-Video Generation
  4. NeurIPS 2024MotionCraft: Physics-Based Zero-Shot Video Generation
  5. NeurIPS 2024Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
  6. NeurIPS 2024Multistable Shape from Shading Emerges from Patch Diffusion
  7. NeurIPS 2024Multistep Distillation of Diffusion Models via Moment Matching
  8. NeurIPS 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
  9. NeurIPS 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
  10. NeurIPS 2024NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
  11. NeurIPS 2024Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
  12. NeurIPS 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
  13. NeurIPS 2024Neural Gaffer: Relighting Any Object via Diffusion
  14. NeurIPS 2024Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
  15. NeurIPS 2024Neural Residual Diffusion Models for Deep Scalable Vision Generation
  16. NeurIPS 2024NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
  17. NeurIPS 2024No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
  18. NeurIPS 2024Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
  19. NeurIPS 2024Novel Object Synthesis via Adaptive Text-Image Harmony
  20. NeurIPS 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
  21. NeurIPS 2024OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
  22. NeurIPS 2024ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
  23. NeurIPS 2024OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
  24. NeurIPS 2024On conditional diffusion models for PDE simulations
  25. NeurIPS 2024On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
  26. NeurIPS 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
  27. NeurIPS 2024On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
  28. NeurIPS 2024On the Scalability of Certified Adversarial Robustness with Generated Data
  29. NeurIPS 2024One-Step Diffusion Distillation through Score Implicit Matching
  30. NeurIPS 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolution
  31. NeurIPS 2024One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
  32. NeurIPS 2024OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
  33. NeurIPS 2024Online Posterior Sampling with a Diffusion Prior
  34. NeurIPS 2024OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
  35. NeurIPS 2024Optical Diffusion Models for Image Generation
  36. NeurIPS 2024Optimal Flow Matching: Learning Straight Trajectories in Just One Step
  37. NeurIPS 2024Optimization Can Learn Johnson Lindenstrauss Embeddings
  38. NeurIPS 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Model
  39. NeurIPS 2024PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
  40. NeurIPS 2024ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping
  41. NeurIPS 2024Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
  42. NeurIPS 2024PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
  43. NeurIPS 2024Persistent Homology for High-dimensional Data Based on Spectral Methods
  44. NeurIPS 2024Phased Consistency Models
  45. NeurIPS 2024PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging
  46. NeurIPS 2024Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
  47. NeurIPS 2024Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
  48. NeurIPS 2024Precipitation Downscaling with Spatiotemporal Video Diffusion
  49. NeurIPS 2024Prediction with Action: Visual Policy Learning via Joint Denoising Process
  50. NeurIPS 2024Preference Alignment with Flow Matching

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