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 34 / 42 页

  1. NeurIPS 2025Generative Pre-trained Autoregressive Diffusion Transformer
  2. NeurIPS 2025Generative Trajectory Stitching through Diffusion Composition
  3. NeurIPS 2025Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
  4. NeurIPS 2025GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
  5. NeurIPS 2025GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters
  6. NeurIPS 2025GeoRemover: Removing Objects and Their Causal Visual Artifacts
  7. NeurIPS 2025GeoVideo: Introducing Geometric Regularization into Video Generation Model
  8. NeurIPS 2025GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design
  9. NeurIPS 2025Go With the Flow: Fast Diffusion for Gaussian Mixture Models
  10. NeurIPS 2025GOATex: Geometry & Occlusion-Aware Texturing
  11. NeurIPS 2025GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
  12. NeurIPS 2025GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing
  13. NeurIPS 2025Gradient Variance Reveals Failure Modes in Flow-Based Generative Models
  14. NeurIPS 2025Graph Diffusion that can Insert and Delete
  15. NeurIPS 2025Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges
  16. NeurIPS 2025Greed is Good: A Unifying Perspective on Guided Generation
  17. NeurIPS 2025Guided Diffusion Sampling on Function Spaces with Applications to PDEs
  18. NeurIPS 2025GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer
  19. NeurIPS 2025HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance
  20. NeurIPS 2025Heterogeneous Diffusion Structure Inference for Network Cascade
  21. NeurIPS 2025Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
  22. NeurIPS 2025High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction
  23. NeurIPS 2025High-Order Flow Matching: Unified Framework and Sharp Statistical Rates
  24. NeurIPS 2025HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion
  25. NeurIPS 2025HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
  26. NeurIPS 2025How to build a consistency model: Learning flow maps via self-distillation
  27. NeurIPS 2025IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation
  28. NeurIPS 2025Image as a World: Generating Interactive World from Single Image via Panoramic Video Generation
  29. NeurIPS 2025Image Editing As Programs with Diffusion Models
  30. NeurIPS 2025Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation
  31. NeurIPS 2025Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
  32. NeurIPS 2025Improving Progressive Generation with Decomposable Flow Matching
  33. NeurIPS 2025Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity
  34. NeurIPS 2025Improving Video Generation with Human Feedback
  35. NeurIPS 2025In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain
  36. NeurIPS 2025In-Context Learning of Stochastic Differential Equations with Foundation Inference Models
  37. NeurIPS 2025Increasing the Utility of Synthetic Images through Chamfer Guidance
  38. NeurIPS 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
  39. NeurIPS 2025Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
  40. NeurIPS 2025Information Theoretic Learning for Diffusion Models with Warm Start
  41. NeurIPS 2025Information-Theoretic Discrete Diffusion
  42. NeurIPS 2025Informed Correctors for Discrete Diffusion Models
  43. NeurIPS 2025Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes
  44. NeurIPS 2025InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
  45. NeurIPS 2025IntrinsiX: High-Quality PBR Generation using Image Priors
  46. NeurIPS 2025InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
  47. NeurIPS 2025Is Artificial Intelligence Generated Image Detection a Solved Problem?
  48. NeurIPS 2025Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models
  49. NeurIPS 2025Is Your Diffusion Model Actually Denoising?
  50. NeurIPS 2025ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model

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