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 2,202 篇，第 14 / 45 页

  1. NeurIPS 2026When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
  2. NeurIPS 2026When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds
  3. NeurIPS 2026When to Inject the Target: Stage-Decoupled Guidance for Diffusion-Based Targeted Adversarial Attacks
  4. NeurIPS 2026Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion Composition
  5. NeurIPS 2026Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation
  6. NeurIPS 2026WORD: Diffusion-Based Posterior Inference for Online Goal Recognition
  7. NeurIPS 2026World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories
  8. NeurIPS 2026World Tracing: Pixel-Aligned Geometry Beyond the Visible
  9. NeurIPS 2026WovenAnchor Matcher: Specialized Intra- and Inter-Image Context Modeling for Feature Matching
  10. NeurIPS 2026X2HDR: HDR Image Generation in a Perceptually Uniform Space
  11. NeurIPS 2026You Can’t Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
  12. NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
  13. NeurIPS 202570% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
  14. NeurIPS 2025A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
  15. NeurIPS 2025A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
  16. NeurIPS 2025A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
  17. NeurIPS 2025A Few Moments Please: Scalable Graphon Learning via Moment Matching
  18. NeurIPS 2025A Geometry-Aware Metric for Mode Collapse in Time Series Generative Models
  19. NeurIPS 2025A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
  20. NeurIPS 2025A Gradient Guided Diffusion Framework for Chance Constrained Programming
  21. NeurIPS 2025A Practical Guide for Incorporating Symmetry in Diffusion Policy
  22. NeurIPS 2025A solvable model of learning generative diffusion: theory and insights
  23. NeurIPS 2025A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks
  24. NeurIPS 2025Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
  25. NeurIPS 2025AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
  26. NeurIPS 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
  27. NeurIPS 2025Accelerating Diffusion LLMs via Adaptive Parallel Decoding
  28. NeurIPS 2025Accelerating Parallel Diffusion Model Serving with Residual Compression
  29. NeurIPS 2025AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
  30. NeurIPS 2025Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
  31. NeurIPS 2025Active Target Discovery under Uninformative Priors: The Power of Permanent and Transient Memory
  32. NeurIPS 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
  33. NeurIPS 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
  34. NeurIPS 2025Adaptive Discretization for Consistency Models
  35. NeurIPS 2025Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
  36. NeurIPS 2025Adaptive Inference-Time Scaling via Cyclic Diffusion Search
  37. NeurIPS 2025Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
  38. NeurIPS 2025ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
  39. NeurIPS 2025Adjoint Schrödinger Bridge Sampler
  40. NeurIPS 2025Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
  41. NeurIPS 2025Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
  42. NeurIPS 2025Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration
  43. NeurIPS 2025Adversarial Diffusion for Robust Reinforcement Learning
  44. NeurIPS 2025Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
  45. NeurIPS 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillation
  46. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
  47. NeurIPS 2025AlignedGen: Aligning Style Across Generated Images
  48. NeurIPS 2025Aligning Compound AI Systems via System-level DPO
  49. NeurIPS 2025Aligning Text to Image in Diffusion Models is Easier Than You Think
  50. NeurIPS 2025Aligning Text-to-Image Diffusion Models to Human Preference by Classification

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