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 2,202 篇，第 42 / 45 页

  1. NeurIPS 2023Language-driven Scene Synthesis using Multi-conditional Diffusion Model
  2. NeurIPS 2023Latent Diffusion for Language Generation
  3. NeurIPS 2023Learning a 1-layer conditional generative model in total variation
  4. NeurIPS 2023Learning Energy-Based Prior Model with Diffusion-Amortized MCMC
  5. NeurIPS 2023Learning Mixtures of Gaussians Using the DDPM Objective
  6. NeurIPS 2023Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
  7. NeurIPS 2023Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis
  8. NeurIPS 2023Likelihood-Based Diffusion Language Models
  9. NeurIPS 2023Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
  10. NeurIPS 2023LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion
  11. NeurIPS 2023Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos
  12. NeurIPS 2023Lossy Image Compression with Conditional Diffusion Models
  13. NeurIPS 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
  14. NeurIPS 2023Markovian Sliced Wasserstein Distances: Beyond Independent Projections
  15. NeurIPS 2023Metropolis Sampling for Constrained Diffusion Models
  16. NeurIPS 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
  17. NeurIPS 2023Mirror Diffusion Models for Constrained and Watermarked Generation
  18. NeurIPS 2023Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
  19. NeurIPS 2023Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
  20. NeurIPS 2023Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
  21. NeurIPS 2023Moment Matching Denoising Gibbs Sampling
  22. NeurIPS 2023MomentDiff: Generative Video Moment Retrieval from Random to Real
  23. NeurIPS 2023Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
  24. NeurIPS 2023Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion
  25. NeurIPS 2023Multi-scale Diffusion Denoised Smoothing
  26. NeurIPS 2023MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
  27. NeurIPS 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
  28. NeurIPS 2023NAP: Neural 3D Articulated Object Prior
  29. NeurIPS 2023Neural Sampling in Hierarchical Exponential-family Energy-based Models
  30. NeurIPS 2023Norm-guided latent space exploration for text-to-image generation
  31. NeurIPS 2023Normalizing flow neural networks by JKO scheme
  32. NeurIPS 2023OBJECT 3DIT: Language-guided 3D-aware Image Editing
  33. NeurIPS 2023Object-Centric Slot Diffusion
  34. NeurIPS 2023On Calibrating Diffusion Probabilistic Models
  35. NeurIPS 2023On Measuring Fairness in Generative Models
  36. NeurIPS 2023On the Constrained Time-Series Generation Problem
  37. NeurIPS 2023On the Generalization Properties of Diffusion Models
  38. NeurIPS 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
  39. NeurIPS 2023One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models
  40. NeurIPS 2023One-Step Diffusion Distillation via Deep Equilibrium Models
  41. NeurIPS 2023Optimal Preconditioning and Fisher Adaptive Langevin Sampling
  42. NeurIPS 2023Optimal Transport-Guided Conditional Score-Based Diffusion Model
  43. NeurIPS 2023P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting
  44. NeurIPS 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation
  45. NeurIPS 2023Parallel Sampling of Diffusion Models
  46. NeurIPS 2023Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
  47. NeurIPS 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
  48. NeurIPS 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
  49. NeurIPS 2023PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation
  50. NeurIPS 2023Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability

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