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 6,899 篇，第 116 / 138 页

  1. NeurIPS 2024Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
  2. NeurIPS 2024Aligning Diffusion Models by Optimizing Human Utility
  3. NeurIPS 2024Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
  4. NeurIPS 2024Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
  5. NeurIPS 2024Amortizing intractable inference in diffusion models for vision, language, and control
  6. NeurIPS 2024An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
  7. NeurIPS 2024An Image is Worth 32 Tokens for Reconstruction and Generation
  8. NeurIPS 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
  9. NeurIPS 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Models
  10. NeurIPS 2024Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
  11. NeurIPS 2024AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
  12. NeurIPS 2024AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
  13. NeurIPS 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
  14. NeurIPS 2024AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
  15. NeurIPS 2024Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
  16. NeurIPS 2024AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
  17. NeurIPS 2024AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
  18. NeurIPS 2024Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
  19. NeurIPS 2024AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  20. NeurIPS 2024Attack-Resilient Image Watermarking Using Stable Diffusion
  21. NeurIPS 2024AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
  22. NeurIPS 2024Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI
  23. NeurIPS 2024Autoregressive Image Generation without Vector Quantization
  24. NeurIPS 2024BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
  25. NeurIPS 2024BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
  26. NeurIPS 2024BiDM: Pushing the Limit of Quantization for Diffusion Models
  27. NeurIPS 2024Binarized Diffusion Model for Image Super-Resolution
  28. NeurIPS 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
  29. NeurIPS 2024BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
  30. NeurIPS 2024Blind Image Restoration via Fast Diffusion Inversion
  31. NeurIPS 2024BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model
  32. NeurIPS 2024Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
  33. NeurIPS 2024Boosting Text-to-Video Generative Model with MLLMs Feedback
  34. NeurIPS 2024BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?
  35. NeurIPS 2024Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model
  36. NeurIPS 2024Breaking Semantic Artifacts for Generalized AI-generated Image Detection
  37. NeurIPS 2024Bridging Geometric States via Geometric Diffusion Bridge
  38. NeurIPS 2024Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
  39. NeurIPS 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models
  40. NeurIPS 2024Categorical Flow Matching on Statistical Manifolds
  41. NeurIPS 2024Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
  42. NeurIPS 2024CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
  43. NeurIPS 2024CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition
  44. NeurIPS 2024ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
  45. NeurIPS 2024Classification Diffusion Models: Revitalizing Density Ratio Estimation
  46. NeurIPS 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models
  47. NeurIPS 2024CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
  48. NeurIPS 2024CLIP in Mirror: Disentangling text from visual images through reflection
  49. NeurIPS 2024CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models
  50. NeurIPS 2024Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation

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