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 4 / 42 页

  1. CVPR 2025Dual-Granularity Semantic Guided Sparse Routing Diffusion Model for General Pansharpening
  2. CVPR 2025Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation
  3. CVPR 2025DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling
  4. CVPR 2025Dynamic Motion Blending for Versatile Motion Editing
  5. CVPR 2025DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes
  6. CVPR 2025Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training
  7. CVPR 2025EchoMatch: Partial-to-Partial Shape Matching via Correspondence Reflection
  8. CVPR 2025EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation
  9. CVPR 2025Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning
  10. CVPR 2025EdgeDiff: Edge-aware Diffusion Network for Building Reconstruction from Point Clouds
  11. CVPR 2025Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
  12. CVPR 2025EditAR: Unified Conditional Generation with Autoregressive Models
  13. CVPR 2025EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting
  14. CVPR 2025EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
  15. CVPR 2025Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Space
  16. CVPR 2025Efficient Diffusion as Low Light Enhancer
  17. CVPR 2025Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
  18. CVPR 2025Efficient Personalization of Quantized Diffusion Model without Backpropagation
  19. CVPR 2025EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation
  20. CVPR 2025EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing
  21. CVPR 2025EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion
  22. CVPR 2025EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space
  23. CVPR 2025Enhancing Creative Generation on Stable Diffusion-based Models
  24. CVPR 2025Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model
  25. CVPR 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purification
  26. CVPR 2025Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
  27. CVPR 2025Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways
  28. CVPR 2025Erasing Undesirable Influence in Diffusion Models
  29. CVPR 2025Estimating Body and Hand Motion in an Ego-sensed World
  30. CVPR 2025Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
  31. CVPR 2025Explaining in Diffusion: Explaining a Classifier with Diffusion Semantics
  32. CVPR 2025Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis
  33. CVPR 2025Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
  34. CVPR 2025Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think
  35. CVPR 2025FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation
  36. CVPR 2025FADE: Frequency-Aware Diffusion Model Factorization for Video Editing
  37. CVPR 2025FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution
  38. CVPR 2025FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
  39. CVPR 2025Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation
  40. CVPR 2025FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing
  41. CVPR 2025FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
  42. CVPR 2025FeedEdit: Text-Based Image Editing with Dynamic Feedback Regulation
  43. CVPR 2025Finding Local Diffusion Schrodinger Bridge using Kolmogorov-Arnold Network
  44. CVPR 2025Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models
  45. CVPR 2025Fingerprinting Denoising Diffusion Probabilistic Models
  46. CVPR 2025FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error
  47. CVPR 2025FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model
  48. CVPR 2025Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation
  49. CVPR 2025FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
  50. CVPR 2025FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations

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