扩散模型论文趋势 2023–2026

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。

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 551 篇，第 3 / 12 页

101. CVPR 2025DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
102. CVPR 2025Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI
103. CVPR 2025DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
104. CVPR 2025Detail-Preserving Latent Diffusion for Stable Shadow Removal
105. CVPR 2025Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
106. CVPR 2025Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention
107. CVPR 2025DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation
108. CVPR 2025DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation
109. CVPR 2025DiC: Rethinking Conv3x3 Designs in Diffusion Models
110. CVPR 2025Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models
111. CVPR 2025Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
112. CVPR 2025Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation
113. CVPR 2025DiffFNO: Diffusion Fourier Neural Operator
114. CVPR 2025DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
115. CVPR 2025DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis
116. CVPR 2025DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
117. CVPR 2025Diffusion Bridge: Leveraging Diffusion Model to Reduce the Modality Gap Between Text and Vision for Zero-Shot Image Captioning
118. CVPR 2025Diffusion Model is Effectively Its Own Teacher
119. CVPR 2025Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models
120. CVPR 2025Diffusion Self-Distillation for Zero-Shot Customized Image Generation
121. CVPR 2025Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
122. CVPR 2025Diffusion-based Event Generation for High-Quality Image Deblurring
123. CVPR 2025Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling
124. CVPR 2025DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
125. CVPR 2025DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion
126. CVPR 2025DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation
127. CVPR 2025DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution
128. CVPR 2025DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
129. CVPR 2025DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
130. CVPR 2025DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels
131. CVPR 2025Directional Label Diffusion Model for Learning from Noisy Labels
132. CVPR 2025Disco4D: Disentangled 4D Human Generation and Animation from a Single Image
133. CVPR 2025Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observations
134. CVPR 2025Disentangled Pose and Appearance Guidance for Multi-Pose Generation
135. CVPR 2025DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery
136. CVPR 2025Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
137. CVPR 2025Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection
138. CVPR 2025DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
139. CVPR 2025Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
140. CVPR 2025Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
141. CVPR 2025DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
142. CVPR 2025DNF: Unconditional 4D Generation with Dictionary-based Neural Fields
143. CVPR 2025Do Visual Imaginations Improve Vision-and-Language Navigation Agents?
144. CVPR 2025DreamRelation: Bridging Customization and Relation Generation
145. CVPR 2025DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
146. CVPR 2025DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation
147. CVPR 2025DriveScape: High-Resolution Driving Video Generation by Multi-View Feature Fusion
148. CVPR 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometry
149. CVPR 2025Dual Diffusion for Unified Image Generation and Understanding
150. CVPR 2025Dual Prompting Image Restoration with Diffusion Transformers

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。