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 2,202 篇，第 35 / 45 页
- NeurIPS 2024Neural Residual Diffusion Models for Deep Scalable Vision Generation
- NeurIPS 2024NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
- NeurIPS 2024No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
- NeurIPS 2024Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
- NeurIPS 2024Novel Object Synthesis via Adaptive Text-Image Harmony
- NeurIPS 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
- NeurIPS 2024OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
- NeurIPS 2024ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
- NeurIPS 2024OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
- NeurIPS 2024On conditional diffusion models for PDE simulations
- NeurIPS 2024On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
- NeurIPS 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
- NeurIPS 2024On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
- NeurIPS 2024On the Scalability of Certified Adversarial Robustness with Generated Data
- NeurIPS 2024One-Step Diffusion Distillation through Score Implicit Matching
- NeurIPS 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolution
- NeurIPS 2024One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
- NeurIPS 2024OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
- NeurIPS 2024Online Posterior Sampling with a Diffusion Prior
- NeurIPS 2024OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
- NeurIPS 2024Optical Diffusion Models for Image Generation
- NeurIPS 2024Optimal Flow Matching: Learning Straight Trajectories in Just One Step
- NeurIPS 2024Optimization Can Learn Johnson Lindenstrauss Embeddings
- NeurIPS 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Model
- NeurIPS 2024PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
- NeurIPS 2024ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping
- NeurIPS 2024Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
- NeurIPS 2024PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
- NeurIPS 2024Persistent Homology for High-dimensional Data Based on Spectral Methods
- NeurIPS 2024Phased Consistency Models
- NeurIPS 2024PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging
- NeurIPS 2024Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
- NeurIPS 2024Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
- NeurIPS 2024Precipitation Downscaling with Spatiotemporal Video Diffusion
- NeurIPS 2024Prediction with Action: Visual Policy Learning via Joint Denoising Process
- NeurIPS 2024Preference Alignment with Flow Matching
- NeurIPS 2024PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
- NeurIPS 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
- NeurIPS 2024ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing
- NeurIPS 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
- NeurIPS 2024PromptFix: You Prompt and We Fix the Photo
- NeurIPS 2024Provable Posterior Sampling with Denoising Oracles via Tilted Transport
- NeurIPS 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
- NeurIPS 2024PTQ4DiT: Post-training Quantization for Diffusion Transformers
- NeurIPS 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignment
- NeurIPS 2024PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
- NeurIPS 2024QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
- NeurIPS 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
- NeurIPS 2024RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
- NeurIPS 2024Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
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