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 327 篇，第 4 / 7 页

  1. NeurIPS 2023GlyphControl: Glyph Conditional Control for Visual Text Generation
  2. NeurIPS 2023GMSF: Global Matching Scene Flow
  3. NeurIPS 2023GRAND-SLAMIN’ Interpretable Additive Modeling with Structural Constraints
  4. NeurIPS 2023Graph Denoising Diffusion for Inverse Protein Folding
  5. NeurIPS 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
  6. NeurIPS 2023HeadSculpt: Crafting 3D Head Avatars with Text
  7. NeurIPS 2023Hierarchical Integration Diffusion Model for Realistic Image Deblurring
  8. NeurIPS 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration
  9. NeurIPS 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
  10. NeurIPS 2023Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion
  11. NeurIPS 2023Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics
  12. NeurIPS 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
  13. NeurIPS 2023Improving Diffusion-Based Image Synthesis with Context Prediction
  14. NeurIPS 2023In-Context Learning Unlocked for Diffusion Models
  15. NeurIPS 2023Incomplete Multimodality-Diffused Emotion Recognition
  16. NeurIPS 2023InsActor: Instruction-driven Physics-based Characters
  17. NeurIPS 2023Inserting Anybody in Diffusion Models via Celeb Basis
  18. NeurIPS 2023Intervention Generalization: A View from Factor Graph Models
  19. NeurIPS 2023Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics
  20. NeurIPS 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network
  21. NeurIPS 2023Knowledge Diffusion for Distillation
  22. NeurIPS 2023L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors
  23. NeurIPS 2023Label-Only Model Inversion Attacks via Knowledge Transfer
  24. NeurIPS 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
  25. NeurIPS 2023LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
  26. NeurIPS 2023Language-driven Scene Synthesis using Multi-conditional Diffusion Model
  27. NeurIPS 2023Latent Diffusion for Language Generation
  28. NeurIPS 2023Learning a 1-layer conditional generative model in total variation
  29. NeurIPS 2023Learning Energy-Based Prior Model with Diffusion-Amortized MCMC
  30. NeurIPS 2023Learning Mixtures of Gaussians Using the DDPM Objective
  31. NeurIPS 2023Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
  32. NeurIPS 2023Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis
  33. NeurIPS 2023Likelihood-Based Diffusion Language Models
  34. NeurIPS 2023Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
  35. NeurIPS 2023LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion
  36. NeurIPS 2023Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos
  37. NeurIPS 2023Lossy Image Compression with Conditional Diffusion Models
  38. NeurIPS 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
  39. NeurIPS 2023Markovian Sliced Wasserstein Distances: Beyond Independent Projections
  40. NeurIPS 2023Metropolis Sampling for Constrained Diffusion Models
  41. NeurIPS 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
  42. NeurIPS 2023Mirror Diffusion Models for Constrained and Watermarked Generation
  43. NeurIPS 2023Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
  44. NeurIPS 2023Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
  45. NeurIPS 2023Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
  46. NeurIPS 2023Moment Matching Denoising Gibbs Sampling
  47. NeurIPS 2023MomentDiff: Generative Video Moment Retrieval from Random to Real
  48. NeurIPS 2023Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
  49. NeurIPS 2023Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion
  50. NeurIPS 2023Multi-scale Diffusion Denoised Smoothing

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