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 2,690 篇，第 6 / 54 页

  1. CVPR 2026Guiding Diffusion Models with Fine-Grained Conditions and Semantics-Preserving Sampling for
  2. CVPR 2026Guiding Diffusion Models with Semantically Degraded Conditions
  3. CVPR 2026Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation
  4. CVPR 2026Guiding Token-Sparse Diffusion Models
  5. CVPR 2026GVIS Generative Vector Image Steganography
  6. CVPR 2026HBridge H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding
  7. CVPR 2026HDW-SR High-Frequency Guided Diffusion Model based on Wavelet Decomposition for
  8. CVPR 2026Hear What You See Video-to-Audio Generation with Diffusion Transformer and
  9. CVPR 2026Heterogeneous Decentralized Diffusion Models
  10. CVPR 2026HiCoGen Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement
  11. CVPR 2026HierEdit Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
  12. CVPR 2026High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning
  13. CVPR 2026High-Fidelity Virtual Try-On beyond Paired Data Scarcity via Diffusion-based Cycle-Consistent
  14. CVPR 2026HP-Edit A Human-Preference Post-Training Framework for Image Editing
  15. CVPR 2026Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization
  16. CVPR 2026IDperturb Enhancing Variation in Synthetic Face Generation via Angular Perturbations
  17. CVPR 2026IFCSR Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-Resolution
  18. CVPR 2026Image Diffusion Preview with Consistency Solver
  19. CVPR 2026Image Generation from Contextually-Contradictory Prompts
  20. CVPR 2026Image-Guided Geometric Stylization of 3D Meshes
  21. CVPR 2026ImageRAGTurbo Towards One-step Text-to-Image Generation with Retrieval-Augmented Diffusion Models
  22. CVPR 2026Imagine Before Concentration Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
  23. CVPR 2026Improving Controllable Generation Faster Training and Better Performance via x0-Supervision
  24. CVPR 2026Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
  25. CVPR 2026IMS3 Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation
  26. CVPR 2026Inconsistency-aware Multimodal Schrodinger Bridge for Deepfake Localization
  27. CVPR 2026Infinity-RoPE Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
  28. CVPR 2026InnoAds-Composer Efficient Condition Composition for E-Commerce Poster Generation
  29. CVPR 2026InstantRetouch Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
  30. CVPR 2026InstantViR Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior
  31. CVPR 2026InstructMix2Mix Consistent Sparse-View Editing Through Multi-View Model Personalization
  32. CVPR 2026Interact2Ar Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models
  33. CVPR 2026InvAD Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models
  34. CVPR 2026InverFill One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
  35. CVPR 2026IP-Adapter Is All You Need Towards Fine-Tuning-Free Diffusion-Based Talking Face
  36. CVPR 2026Iris Bringing Real-World Priors into Diffusion Model for Monocular Depth
  37. CVPR 2026Iris Integrating Language into Diffusion-based Monocular Depth Estimation
  38. CVPR 2026JRM Joint Reconstruction Model for Multiple Objects without Alignment
  39. CVPR 2026Just-in-Time Training-Free Spatial Acceleration for Diffusion Transformers
  40. CVPR 2026KLIP Localized Distribution Shift Detection via KL-Divergence with Diffusion Priors
  41. CVPR 2026L3DR 3D-aware LiDAR Diffusion and Rectification
  42. CVPR 2026LacTokGen Latent Consistency Tokenizer for 1024-pixel Image Generation by 256
  43. CVPR 2026Landscape-Awareness for Geometric View Diffusion Model
  44. CVPR 2026Language-Free Generative Editing from One Visual Example
  45. CVPR 2026Language-Guided One-Step Diffusion Model for Nighttime Flare Removal
  46. CVPR 2026Latent Diffusion Inversion Requires Understanding the Latent Space
  47. CVPR 2026LeapAlign Post-training Flow Matching Models at Any Generation Step by
  48. CVPR 2026Learnability-Guided Diffusion for Dataset Distillation
  49. CVPR 2026Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from
  50. CVPR 2026Learning Hierarchical Hyperbolic Mixture Model for Part-aware 3D 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