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 728 篇，第 7 / 15 页

  1. ICML 2026iGRPO: Fast Online RL for Flow Matching Model with Instant Reward
  2. ICML 2026Image Restoration via Diffusion Models with Dynamic Resolution
  3. ICML 2026Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
  4. ICML 2026Improving Backward Conformal Prediction via Non-Conformity Score Transformation
  5. ICML 2026Improving Classifier-Free Guidance of Flow Matching via Manifold Projection
  6. ICML 2026Improving Diffusion Planners by Self-Supervised Action Gating with Energies
  7. ICML 2026Improving Sampling for Masked Diffusion Models via Information Gain
  8. ICML 2026Incomplete Multi-View Clustering via Neighborhood-Conditioned Diffusion
  9. ICML 2026Infinite Mask Diffusion for Few-Step Distillation
  10. ICML 2026Infinite-Dimensional Generative Diffusions via Doob’s h-Transform
  11. ICML 2026InfoDLM: an Information-Adaptive Framework for Discrete Diffusion Language Model Pretraining
  12. ICML 2026Information dynamics and Memory in Neural Networks through Fisher Information Diffusion
  13. ICML 2026Information-Geometric Adaptive Sampling for Graph Diffusion
  14. ICML 2026Information-Theoretic Disentangled Latent Modeling with Conditional Diffusion for Incomplete Multi-View Clustering
  15. ICML 2026InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution
  16. ICML 2026Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
  17. ICML 2026Insertion Based Sequence Generation with Learnable Order Dynamics
  18. ICML 2026Inverting Data Transformations via Diffusion Sampling
  19. ICML 2026Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language Models
  20. ICML 2026JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference
  21. ICML 2026Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits
  22. ICML 2026Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution
  23. ICML 2026Just Y-Prediction: Enabling Historical Cumulative Inconsistency in Label Diffusion for Learning with Noisy Label
  24. ICML 2026KineFlow: Kinematic Second-Order Flow Matching for Time-Series Forecasting
  25. ICML 2026KIStego: Key-Independent Secure Image Distribution via Bipartite Structural Invariants
  26. ICML 2026Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
  27. ICML 2026Large-capacity and Receiver Authenticable Generative Image Steganography
  28. ICML 2026Latent Diffusion Pretraining for Crystal Property Prediction
  29. ICML 2026Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
  30. ICML 2026Latent Laplace Diffusion for Irregular Multivariate Time Series
  31. ICML 2026Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
  32. ICML 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
  33. ICML 2026LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer
  34. ICML 2026Lavida-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
  35. ICML 2026LayerT2V: A Unified Multi-Layer Video Generation Framework
  36. ICML 2026LeakGFN: Robust Molecular Generation in Generative Flow Networks via Flow Decomposition
  37. ICML 2026Learnability-Informed Fine-Tuning of Diffusion Language Models
  38. ICML 2026LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
  39. ICML 2026Learning a Generative Meta-Model of LLM Activations
  40. ICML 2026Learning Coupled Continuous-Time Latent Dynamics from Irregular Events
  41. ICML 2026Learning Discrete Diffusion on Graphs via Free-Energy Gradient Flows
  42. ICML 2026Learning Manifold Data with Flow Matching
  43. ICML 2026Learning Normalized Energy Models for Linear Inverse Problems
  44. ICML 2026Learning Permutation Distributions via Reflected Diffusion on Ranks
  45. ICML 2026Learning Stochastic Bridges for Video Object Removal via Video-to-Video Translation
  46. ICML 2026Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting
  47. ICML 2026Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
  48. ICML 2026Learning Unmasking Policies for Diffusion Language Models
  49. ICML 2026Let EEG Models Learn EEG
  50. ICML 2026Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching

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