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
- 扩散模型论文从 2023 年的 660 篇增长到 2026 年的 2,691 篇，三年间扩大到约 4.1 倍。
- NeurIPS 是发扩散模型论文最多的会议，2023–2026 年共 2,202 篇，占四个会议总量的 32%。
- 交叉方向里涨得最快的是应用 · chemistry physics and earth sciences：同时属于两个主题的论文从 2023 年的 14 篇增至 2026 年的 163 篇。
- 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 1；同组增长最快的深度学习 · foundation models是 2.5 倍，扩散模型是 4.1 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 327 | 86 | 109 | 138 | 660 |
| 2024 | 520 | 260 | 195 | 496 | 1,471 |
| 2025 | 694 | 487 | 346 | 551 | 2,078 |
| 2026 | 661 | 694 | 728 | 608 | 2,691 |
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
- NeurIPS 2026$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
- ICML 2026“Do Diffusion Models Dream of Electric Planes?” Discrete and Continuous Simulation-Based Inference for Aircraft Design
- ICLR 2026$\alpha$-DPO: Robust Preference Alignment for Diffusion Models via $\alpha$ Divergence
- CVPR 20262ndMatch Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
- NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
- ICML 2025A First-order Generative Bilevel Optimization Framework for Diffusion Models
- ICLR 2025$\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps
- CVPR 20253DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
- NeurIPS 2024$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
- ICML 2024A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
- ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
- CVPR 2024D^4: Dataset Distillation via Disentangled Diffusion Model
- NeurIPS 20233D molecule generation by denoising voxel grids
- ICML 2023A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification
- ICLR 2023(Certified!!) Adversarial Robustness for Free!
- CVPR 20233D Neural Field Generation Using Triplane Diffusion
- NeurIPS 2026$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
- ICML 2026$\sigma$: Sigmoid Modulation for Ultra High Resolution Diffusion
- ICLR 2026$\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
- CVPR 20263D-LATTE Latent Space 3D Editing from Textual Instructions
全部扩散模型论文
共 2,690 篇，第 4 / 54 页
- CVPR 2026DyaDiT A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture
- CVPR 2026Dynamic-eDiTor Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
- CVPR 2026DynFusion Rethinking Condition Fusion for Adaptive Multi-Conditional Text-to-Image Generation
- CVPR 2026Easy3E Feed-Forward 3D Asset Editing via Rectified Voxel Flow
- CVPR 2026EasyOmnimatte Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered
- CVPR 2026EchoVDiff Cardiac-Cycle Echocardiography Video Generation from Arbitrary Single Frame
- CVPR 2026Edit2Perceive Image Editing Diffusion Models Are Strong Dense Perceivers
- CVPR 2026EditMGT Unleashing Potentials of Masked Generative Transformers in Image Editing
- CVPR 2026Efficient and Training-Free Single-Image Diffusion Models
- CVPR 2026Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive
- CVPR 2026Efficient Weighted Sampling via Score-based Generative Models
- CVPR 2026EgoControl Controllable Egocentric Video Generation via 3D Full-Body Poses
- CVPR 2026EgoFlow Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
- CVPR 2026EgoX Egocentric Video Generation from a Single Exocentric Video
- CVPR 2026Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
- CVPR 2026Elucidating the SNR-t Bias of Diffusion Probabilistic Models
- CVPR 2026EMR-Diff Edge-aware Multimodal Residual Diffusion Model for Hyperspectral Image Super-resolution
- CVPR 2026End-to-End Language-Action Model for Humanoid Whole Body Control
- CVPR 2026Envisioning the Future One Step at a Time
- CVPR 2026Erasing Thousands of Concepts Towards Scalable and Practical Concept Erasure
- CVPR 2026Exploring Conditions for Diffusion Models in Robotic Control
- CVPR 2026ExpPortrait Expressive Portrait Generation via Personalized Representation
- CVPR 2026Extending One-Step Image Generation from Class Labels to Text via
- CVPR 2026FabricGen Microstructure-Aware Woven Fabric Generation
- CVPR 2026FACE A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh
- CVPR 2026Face2Scene Using Facial Degradation as an Oracle for Diffusion-Based Scene
- CVPR 2026FailureAtlas Mapping the Failure Landscape of T2I Models via Active
- CVPR 2026FaithFusion Harmonizing Reconstruction and Generation via Pixel-wise Information Gain
- CVPR 2026FARMER Flow AutoRegressive Transformer over Pixels
- CVPR 2026Fast3Dcache Training-free 3D Geometry Synthesis Acceleration
- CVPR 2026FastHybrid Accelerating Hybrid Autoregressive Image Generation with Lookahead and Guided
- CVPR 2026FE2E From Editor to Dense Geometry Estimator
- CVPR 2026Few-shot Acoustic Synthesis with Multimodal Flow Matching
- CVPR 2026Few-Step Diffusion Sampling Through Instance-Aware Discretizations
- CVPR 2026FG-Portrait 3D Flow Guided Editable Portrait Animation
- CVPR 2026FiDeSR High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution
- CVPR 2026FINE Factorizing Knowledge for Initialization of Variable-sized Diffusion Models
- CVPR 2026FISHuman Fine-grained Single-image 3D Human Reconstruction via Multi-view 4D Remeshing
- CVPR 2026Flash-DMD Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and
- CVPR 2026FlashDecoder Real-Time Latent-to-Pixel Streaming Decoder with Transformers
- CVPR 2026FlashIn Fast and Accurate Image Inversion for Real-time Image Editing
- CVPR 2026FlashLips 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion
- CVPR 2026FlashVSR Towards Real-time Diffusion-Based Streaming Video Super Resolution
- CVPR 2026FloodDiffusion Tailored Diffusion Forcing for Streaming Motion Generation
- CVPR 2026Flow Map Distillation Without Data
- CVPR 2026Flow Matching for Multimodal Distributions
- CVPR 2026Flowception Temporally Expansive Flow Matching for Video Generation
- CVPR 2026FlowComposer Composable Flows for Compositional Zero-Shot Learning
- CVPR 2026FlowDC Flow-Based Decoupling-Decay for Complex Image Editing
- CVPR 2026FlowDirector Training-Free Flow Steering for Precise Text-to-Video Editing
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"}
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
- 深度学习 · generative models and autoencoders 4,314
- 深度学习 · large language models 2,334
- 深度学习 · self supervised learning 1,958
- 深度学习 · graph neural networks 1,648
- 深度学习 · optimization 953
- 深度学习 · representation learning 802
- 深度学习 · probabilistic methods 637
- 深度学习 · foundation models 536
- 深度学习 · causal inference 316
- 深度学习 · transfer learning 197