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 108 / 138 页

  1. ICLR 2024EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
  2. ICLR 2024Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
  3. ICLR 2024Exploring Diffusion Time-steps for Unsupervised Representation Learning
  4. ICLR 2024Exposing Text-Image Inconsistency Using Diffusion Models
  5. ICLR 2024Fast Ensembling with Diffusion Schrödinger Bridge
  6. ICLR 2024Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space
  7. ICLR 2024Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
  8. ICLR 2024Finetuning Text-to-Image Diffusion Models for Fairness
  9. ICLR 2024FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
  10. ICLR 2024Flow Matching on General Geometries
  11. ICLR 2024Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
  12. ICLR 2024FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
  13. ICLR 2024FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
  14. ICLR 2024From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
  15. ICLR 2024GAIA: Zero-shot Talking Avatar Generation
  16. ICLR 2024GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
  17. ICLR 2024GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
  18. ICLR 2024Generalization in diffusion models arises from geometry-adaptive harmonic representations
  19. ICLR 2024Generalized Schrödinger Bridge Matching
  20. ICLR 2024Generating Images with 3D Annotations Using Diffusion Models
  21. ICLR 2024Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns
  22. ICLR 2024Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping
  23. ICLR 2024Generative Modeling with Phase Stochastic Bridge
  24. ICLR 2024Generative Pre-training for Speech with Flow Matching
  25. ICLR 2024GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
  26. ICLR 2024Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
  27. ICLR 2024GRAPH-CONSTRAINED DIFFUSION FOR END-TO-END PATH PLANNING
  28. ICLR 2024Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
  29. ICLR 2024HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
  30. ICLR 2024How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models
  31. ICLR 2024Human Motion Diffusion as a Generative Prior
  32. ICLR 2024HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
  33. ICLR 2024Idempotent Generative Network
  34. ICLR 2024Image Inpainting via Iteratively Decoupled Probabilistic Modeling
  35. ICLR 2024Image Inpainting via Tractable Steering of Diffusion Models
  36. ICLR 2024Image Translation as Diffusion Visual Programmers
  37. ICLR 2024ImagenHub: Standardizing the evaluation of conditional image generation models
  38. ICLR 2024Improved Active Learning via Dependent Leverage Score Sampling
  39. ICLR 2024Improved sampling via learned diffusions
  40. ICLR 2024Improved Techniques for Training Consistency Models
  41. ICLR 2024IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
  42. ICLR 2024InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
  43. ICLR 2024Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion Models
  44. ICLR 2024InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
  45. ICLR 2024Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model
  46. ICLR 2024InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
  47. ICLR 2024InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
  48. ICLR 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior
  49. ICLR 2024Interpretable Diffusion via Information Decomposition
  50. ICLR 2024Intriguing Properties of Data Attribution on Diffusion 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