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 13 / 45 页
- NeurIPS 2026Train-free Data Poisoning Attack against Retrieval-augmented Diffusion Models
- NeurIPS 2026Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
- NeurIPS 2026Training Optimal Large Diffusion Language Models
- NeurIPS 2026Training-Free Generative Sampling via Moment-Matched Score Smoothing
- NeurIPS 2026Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
- NeurIPS 2026Trajectory-Consistent Diffusion Policies for Offline Reinforcement Learning
- NeurIPS 2026Transforming Image Editors into Video Editors
- NeurIPS 2026Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse
- NeurIPS 2026Tree-Sliced Orlicz Integral Probability Metric
- NeurIPS 2026Tri-Prompting: Controllable Video Generation with Scene, Subject, and Motion Prompts
- NeurIPS 2026Trivialized Generative Models on Lie Groups
- NeurIPS 2026Trustworthy and Efficient Map-free LiDAR Localization via Scan-Pose Alignment and Flow Matching
- NeurIPS 2026TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
- NeurIPS 2026Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
- NeurIPS 2026Two-Sided Learning in Matching Markets with Interviews
- NeurIPS 2026Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
- NeurIPS 2026Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
- NeurIPS 2026Unaligned Image Guided Denoising via Cross-modal Conditional Flow Matching
- NeurIPS 2026Uncertainty Quantification for Large Language Diffusion Models
- NeurIPS 2026Understanding diffusion models requires rethinking (again) generalization
- NeurIPS 2026UniCustom: Unified Visual Conditioning for Multi-reference Image Generation
- NeurIPS 2026UniFlowDock: Flexible Docking with Complete Equivariant Velocity Fields
- NeurIPS 2026Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
- NeurIPS 2026Universal Time Series Generation with Neural Controlled Differential Equations
- NeurIPS 2026Unlocking the Duality between Flow and Field Matching
- NeurIPS 2026Unsupervised Concept Discovery with Dirichlet Concept Diffusion Models
- NeurIPS 2026V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion
- NeurIPS 2026Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
- NeurIPS 2026Variable-Length Generative Protein Design via Generalized Poisson Flow
- NeurIPS 2026Variance Reduction for Expectations with Diffusion Teachers
- NeurIPS 2026Variance-Averse n-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
- NeurIPS 2026Variational Active Flow Matching for Discrete Online Black-Box Optimization
- NeurIPS 2026Variational Trajectory Optimization of Anisotropic Diffusion Schedules
- NeurIPS 2026Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow Matching
- NeurIPS 2026Vermeer: Autoregressive generative modeling of microscopy predicts protein localization
- NeurIPS 2026VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing
- NeurIPS 2026Video Models Can Reason with Verifiable Rewards
- NeurIPS 2026Virtual-Flow: Virtual Microphone-based Speech Enhancement via Unsupervised Flow Matching
- NeurIPS 2026Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
- NeurIPS 2026Volatility-Whitened Probabilistic Residual Modeling for Long-Term Time Series Forecasting
- NeurIPS 2026VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation
- NeurIPS 2026VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
- NeurIPS 2026Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
- NeurIPS 2026Watermarking as a Learned Intrinsic Property of Diffusion Models
- NeurIPS 2026Wavelet Flow Matching for Multi-Scale Physics Emulation
- NeurIPS 2026What kills $v$-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching
- NeurIPS 2026What Makes a Good Path? Factoring Manifold Support and Path Geometry
- NeurIPS 2026What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
- NeurIPS 2026What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching
- NeurIPS 2026When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
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