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 2,078 篇，第 8 / 42 页

  1. CVPR 2025OSDFace: One-Step Diffusion Model for Face Restoration
  2. CVPR 2025OSV: One Step is Enough for High-Quality Image to Video Generation
  3. CVPR 2025Paint by Inpaint: Learning to Add Image Objects by Removing Them First
  4. CVPR 2025Panorama Generation From NFoV Image Done Right
  5. CVPR 2025ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions
  6. CVPR 2025PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models
  7. CVPR 2025PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model
  8. CVPR 2025PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
  9. CVPR 2025PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution
  10. CVPR 2025Pathways on the Image Manifold: Image Editing via Video Generation
  11. CVPR 2025Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
  12. CVPR 2025PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models
  13. CVPR 2025PersonaBooth: Personalized Text-to-Motion Generation
  14. CVPR 2025Personalized Preference Fine-tuning of Diffusion Models
  15. CVPR 2025Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories
  16. CVPR 2025PhysAnimator: Physics-Guided Generative Cartoon Animation
  17. CVPR 2025PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?
  18. CVPR 2025PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
  19. CVPR 2025PICD: Versatile Perceptual Image Compression with Diffusion Rendering
  20. CVPR 2025Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
  21. CVPR 2025Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control
  22. CVPR 2025Point Cloud Upsampling Using Conditional Diffusion Module with Adaptive Noise Suppression
  23. CVPR 2025PoseTraj: Pose-Aware Trajectory Control in Video Diffusion
  24. CVPR 2025POSTA: A Go-to Framework for Customized Artistic Poster Generation
  25. CVPR 2025PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction
  26. CVPR 2025Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
  27. CVPR 2025Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models
  28. CVPR 2025Probability Density Geodesics in Image Diffusion Latent Space
  29. CVPR 2025Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data
  30. CVPR 2025Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation
  31. CVPR 2025Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attack on Breast Ultrasound Images
  32. CVPR 2025ProReflow: Progressive Reflow with Decomposed Velocity
  33. CVPR 2025PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention
  34. CVPR 2025PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
  35. CVPR 2025PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model
  36. CVPR 2025Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction
  37. CVPR 2025Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
  38. CVPR 2025RAD: Region-Aware Diffusion Models for Image Inpainting
  39. CVPR 2025Random Conditioning for Diffusion Model Compression with Distillation
  40. CVPR 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
  41. CVPR 2025RaSS: Improving Denoising Diffusion Samplers with Reinforced Active Sampling Scheduler
  42. CVPR 2025RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories
  43. CVPR 2025Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model
  44. CVPR 2025Reanimating Images using Neural Representations of Dynamic Stimuli
  45. CVPR 2025ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning
  46. CVPR 2025Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual
  47. CVPR 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
  48. CVPR 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
  49. CVPR 2025Rectified Diffusion Guidance for Conditional Generation
  50. CVPR 2025Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative 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