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 1,527 篇，第 9 / 31 页

  1. ICLR 2026MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
  2. ICLR 2026Measurement Score-Based Diffusion Model
  3. ICLR 2026Micro-Macro Coupled Koopman Modeling on Graph for Traffic Flow Prediction
  4. ICLR 2026MIMIC: Mask-Injected Manipulation Video Generation with Interaction Control
  5. ICLR 2026MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion
  6. ICLR 2026Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains
  7. ICLR 2026Mitigating Noise Shift in Denoising Generative Models with Noise Awareness Guidance
  8. ICLR 2026Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment
  9. ICLR 2026MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss
  10. ICLR 2026MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
  11. ICLR 2026Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
  12. ICLR 2026MoGen: Detailed Neuronal Morphology Generation via Point Cloud Flow Matching
  13. ICLR 2026MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning
  14. ICLR 2026MOLM: Mixture of LoRA Markers
  15. ICLR 2026Monocular Normal Estimation via Shading Sequence Estimation
  16. ICLR 2026MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
  17. ICLR 2026Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening
  18. ICLR 2026MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation
  19. ICLR 2026Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction
  20. ICLR 2026Multi-agent Coordination via Flow Matching
  21. ICLR 2026Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
  22. ICLR 2026Multi-Scale Diffusion-Guided Graph Learning with Power-Smoothing Random Walk Contrast for Multi-View Clustering
  23. ICLR 2026Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of Experts
  24. ICLR 2026Multiplicative Diffusion Models: Beyond Gaussian Latents
  25. ICLR 2026MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
  26. ICLR 2026MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion
  27. ICLR 2026NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion
  28. ICLR 2026Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization
  29. ICLR 2026Neodragon: Mobile Video Generation Using Diffusion Transformer
  30. ICLR 2026Neon: Negative Extrapolation From Self-Training Improves Image Generation
  31. ICLR 2026NeRV-Diffusion: Diffuse Implicit Neural Representation for Video Synthesis
  32. ICLR 2026NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
  33. ICLR 2026NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching
  34. ICLR 2026NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
  35. ICLR 2026NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
  36. ICLR 2026No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddings
  37. ICLR 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
  38. ICLR 2026NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
  39. ICLR 2026Object Fidelity Diffusion for Remote Sensing Image Generation
  40. ICLR 2026OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
  41. ICLR 2026OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation
  42. ICLR 2026OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation
  43. ICLR 2026On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond
  44. ICLR 2026On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
  45. ICLR 2026On the Design of One-step Diffusion via Shortcutting Flow Paths
  46. ICLR 2026On the Interpolation Effect of Score Smoothing in Diffusion Models
  47. ICLR 2026On the Reasoning Abilities of Masked Diffusion Language Models
  48. ICLR 2026One step further with Monte-Carlo sampler to guide diffusion better
  49. ICLR 2026One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs
  50. ICLR 2026One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning

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