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 39 / 54 页

  1. ICML 2026Stability Analysis of Sharpness-Aware Minimization
  2. ICML 2026Stabilizing Reinforcement Learning for Diffusion Language Models
  3. ICML 2026Stable Velocity: A Variance Perspective on Flow Matching
  4. ICML 2026Stage-wise Distortion–Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
  5. ICML 2026STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
  6. ICML 2026STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
  7. ICML 2026Stationary MMD Points
  8. ICML 2026Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions
  9. ICML 2026STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction
  10. ICML 2026STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation
  11. ICML 2026Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
  12. ICML 2026Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
  13. ICML 2026StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation
  14. ICML 2026STRIDE: Post-Training LLMs to Reason and Refine Bio-Sequences via Edit Trajectories
  15. ICML 2026Structure-Aware Riemannian Flow Matching for Registration and Fusion of Hyperspectral and Multispectral Images
  16. ICML 2026Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
  17. ICML 2026StyleDistillation: A New Insight of Image Style Enables Personalized Aesthetic Manipulation
  18. ICML 2026SuperHype: Hypergraph Generation via Graph-Superposition Decomposition
  19. ICML 2026Supervised Guidance Training for Infinite-Dimensional Diffusion Models
  20. ICML 2026Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
  21. ICML 2026SURF: Separation via Unsupervised Remixing Flow
  22. ICML 2026SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate
  23. ICML 2026SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
  24. ICML 2026SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis
  25. ICML 2026Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models
  26. ICML 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
  27. ICML 2026TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling
  28. ICML 2026TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment
  29. ICML 2026Tail Annealing for Heavy-Tailed Flow Matching
  30. ICML 2026TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation
  31. ICML 2026TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
  32. ICML 2026TEAM: Temporal–Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration
  33. ICML 2026Temperature Scaling in Discrete Sequence (Language) Models
  34. ICML 2026Temporal Difference Learning for Diffusion Models
  35. ICML 2026Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
  36. ICML 2026Temporal-aware Flow Matching for Video Generation with Temporally Coherent Motion
  37. ICML 2026Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
  38. ICML 2026Test-Time Anchoring for Discrete Diffusion Posterior Sampling
  39. ICML 2026Test-Time Reinforcement Learning for Flow Matching
  40. ICML 2026TFTF: Training-Free Targeted Flow for Conditional Sampling
  41. ICML 2026The Accumulation of Score Estimation Error in Diffusion Models
  42. ICML 2026The Efficiency Gap in Byte Modeling
  43. ICML 2026The Entropic Signature of Class Speciation in Diffusion Models
  44. ICML 2026The Safety-Aware Denoiser for Text Diffusion Models
  45. ICML 2026The Velocity Deficit: Initial Energy Injection for Flow Matching
  46. ICML 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
  47. ICML 2026Tightening the Score Matching Gap for Diffusion Models
  48. ICML 2026Tilt Matching for Scalable Sampling and Fine-Tuning
  49. ICML 2026Timestep Rescheduling in Diffusion Inversion
  50. ICML 2026Tokenised Flow Matching for Hierarchical Simulation Based Inference

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