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 520 篇，第 6 / 11 页

  1. NeurIPS 2024Guiding a Diffusion Model with a Bad Version of Itself
  2. NeurIPS 2024HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
  3. NeurIPS 2024Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation
  4. NeurIPS 2024Hamiltonian Score Matching and Generative Flows
  5. NeurIPS 2024HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation
  6. NeurIPS 2024HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
  7. NeurIPS 2024Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
  8. NeurIPS 2024How Control Information Influences Multilingual Text Image Generation and Editing?
  9. NeurIPS 2024How Diffusion Models Learn to Factorize and Compose
  10. NeurIPS 2024How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
  11. NeurIPS 2024How to Use Diffusion Priors under Sparse Views?
  12. NeurIPS 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
  13. NeurIPS 2024Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
  14. NeurIPS 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
  15. NeurIPS 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
  16. NeurIPS 2024ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
  17. NeurIPS 2024Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model
  18. NeurIPS 2024Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
  19. NeurIPS 2024IllumiNeRF: 3D Relighting Without Inverse Rendering
  20. NeurIPS 2024Image Copy Detection for Diffusion Models
  21. NeurIPS 2024Image Reconstruction Via Autoencoding Sequential Deep Image Prior
  22. NeurIPS 2024Images that Sound: Composing Images and Sounds on a Single Canvas
  23. NeurIPS 2024IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
  24. NeurIPS 2024Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
  25. NeurIPS 2024Improved Distribution Matching Distillation for Fast Image Synthesis
  26. NeurIPS 2024Improved off-policy training of diffusion samplers
  27. NeurIPS 2024Improved Sample Complexity Bounds for Diffusion Model Training
  28. NeurIPS 2024Improving the Training of Rectified Flows
  29. NeurIPS 2024In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
  30. NeurIPS 2024Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models
  31. NeurIPS 2024InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
  32. NeurIPS 2024InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
  33. NeurIPS 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
  34. NeurIPS 2024Interpreting the Weight Space of Customized Diffusion Models
  35. NeurIPS 2024Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
  36. NeurIPS 2024Invisible Image Watermarks Are Provably Removable Using Generative AI
  37. NeurIPS 2024IR-CM: The Fast and General-purpose Image Restoration Method Based on Consistency Model
  38. NeurIPS 2024Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models.
  39. NeurIPS 2024Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
  40. NeurIPS 2024KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
  41. NeurIPS 2024LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction
  42. NeurIPS 2024Latent Diffusion for Neural Spiking Data
  43. NeurIPS 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
  44. NeurIPS 2024LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D
  45. NeurIPS 2024Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
  46. NeurIPS 2024Learning diffusion at lightspeed
  47. NeurIPS 2024Learning Diffusion Priors from Observations by Expectation Maximization
  48. NeurIPS 2024Learning Discrete Concepts in Latent Hierarchical Models
  49. NeurIPS 2024Learning Distributions on Manifolds with Free-Form Flows
  50. NeurIPS 2024Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems

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