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 2,690 篇，第 51 / 54 页

  1. NeurIPS 2026Refining Compositional Diffusion for Reliable Long-Horizon Planning
  2. NeurIPS 2026Reflected Schrödinger Bridge Matching
  3. NeurIPS 2026ReFlex: Faithful Panorama Reconstruction from a Single Image with Reflections
  4. NeurIPS 2026ReFPO: Reflow Regularization for Flow Matching Policy Gradients
  5. NeurIPS 2026ReGuidance: Diffusion Steering with Strong Latent Initializations Solves Hard Inverse Problems
  6. NeurIPS 2026Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow Models
  7. NeurIPS 2026Reinforcement learning enhanced flow matching for reference-based tumor generation on unpaired CT images
  8. NeurIPS 2026Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
  9. NeurIPS 2026Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
  10. NeurIPS 2026Reliability-Coupled Manifold-Aware Diffusion for Missing-Modality Inference
  11. NeurIPS 2026Renoise Consistency: Unlocking Efficient Self-Correction for Diffusion Large Language Models
  12. NeurIPS 2026RePiD: Efficient Recursive Pixel-Space Diffusion via Hierarchical Patch Denoising
  13. NeurIPS 2026RepoScope: Bridging Physical Structure and Logical Flow for Intent-Driven Repository Documentation
  14. NeurIPS 2026Representation Preconditioning for Efficient Diffusion Model Training
  15. NeurIPS 2026Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
  16. NeurIPS 2026ResFusion: Medical Image Fusion Driven by Implicit-Forward Diffusion and Time-aware Joint Optimization
  17. NeurIPS 2026Response Time Enhances Alignment with Heterogeneous Preferences
  18. NeurIPS 2026Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching
  19. NeurIPS 2026Rethinking Diffusion Decoding via Structural Commitment
  20. NeurIPS 2026Rethinking Knowledge Distillation for Diffusion Language Models
  21. NeurIPS 2026Rethinking Learning from Label Proportions via Moment Matching
  22. NeurIPS 2026Rethinking Memorization–Generalization Trade-Off in Generative Models
  23. NeurIPS 2026Rethinking Vector Field Learning for Generative Segmentation
  24. NeurIPS 2026Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery
  25. NeurIPS 2026Reversing the Roles of Signal and Noise: Modeling Noise in Astronomical Images without Paired Data
  26. NeurIPS 2026Revisiting The Power of Closed-Form: Robust Deep Image Prototype Discovery via Scale Mixtures
  27. NeurIPS 2026Reweighted Flow Matching via Unbalanced Optimal Transport for Label-free Long-tailed Generation
  28. NeurIPS 2026RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement
  29. NeurIPS 2026RoboExo: Structure-Guided Wrist-to-Exocentric Video Generation for Scalable Robot Learning
  30. NeurIPS 2026Robust Diffusion Models via Divergence-Induced Weighted Denoising
  31. NeurIPS 2026Robust Flow Matching under Target Corruption and Label Noise
  32. NeurIPS 2026Robust Graph Diffusion Model
  33. NeurIPS 2026Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
  34. NeurIPS 2026Rotations on Latent Hyperspheres: a Geometry-Aware Guiding Framework for Diffusion Models
  35. NeurIPS 2026RotVLA: Rotational Latent Action for Vision-Language-Action Model
  36. NeurIPS 2026RxDiff: Discrete Diffusion for Medication Recommendation with Inference-Time Safety Control
  37. NeurIPS 2026S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation
  38. NeurIPS 2026Safe Few-Step Generation via Velocity Editing
  39. NeurIPS 2026Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
  40. NeurIPS 2026Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
  41. NeurIPS 2026SARA: Step-Adaptive Rank Adjustment for Diffusion Inference Acceleration
  42. NeurIPS 2026Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models
  43. NeurIPS 2026scShapeBench: Discovering geometry from high dimensional scRNAseq data
  44. NeurIPS 2026SCULPT: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis.
  45. NeurIPS 2026SDFlow: Similarity-Driven Flow Matching for Time Series Generation
  46. NeurIPS 2026Search-Augmented Masked Diffusion Models for Constrained Generation
  47. NeurIPS 2026Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
  48. NeurIPS 2026Seed-Your-Motion: Householder Orthogonal Noise for Motion-Controllable Video Diffusion Models
  49. NeurIPS 2026Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
  50. NeurIPS 2026SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

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