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 6,899 篇，第 3 / 138 页

101. CVPR 2026DABO Difficulty-Aware Bayesian Optimization with Diffusion-Learned Priors
102. CVPR 2026DBMSolver A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
103. CVPR 2026DDiT Dynamic Patch Scheduling for Efficient Diffusion Transformers
104. CVPR 2026DDT Decoupled Diffusion Transformer
105. CVPR 2026DeCo Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
106. CVPR 2026Decoupled Generative Modeling for Human-Object Interaction Synthesis
107. CVPR 2026Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient
108. CVPR 2026Degradation-Robust Fusion An Efficient Degradation-Aware Diffusion Framework for Multimodal Image
109. CVPR 2026DeltaQuant 4-bit Video Diffusion Models with Spatiotemporal Delta Smoothing
110. CVPR 2026Denoising as Path Planning Training-Free Acceleration of Diffusion Models with
111. CVPR 2026Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification
112. CVPR 2026DeX-Portrait Disentangled and Expressive Portrait Animation via Explicit and Latent
113. CVPR 2026Dexterous World Models
114. CVPR 2026DICArt Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces
115. CVPR 2026Diff-SemiER Transparency-Aware Adaptive Fusion Diffusion Model with Generative Prior for
116. CVPR 2026Diff4Splat Repurposing Video Diffusion Models for Dynamic Scene Generation
117. CVPR 2026DiffDecompose Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers
118. CVPR 2026DiffGraph An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image
119. CVPR 2026Diffusion Guided Chain-of-Vision for Large Autoregressive Vision Models
120. CVPR 2026Diffusion Mental Averages
121. CVPR 2026Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding
122. CVPR 2026Diffusion Probe Generated Image Result Prediction Using CNN Probes
123. CVPR 2026Diffusion Sampling Path Tells More An Efficient Plug-and-Play Strategy for
124. CVPR 2026Diffusion with a Linguistic Compass Steering the Generation of Clinically
125. CVPR 2026Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features
126. CVPR 2026Diffusion-Based Native Adversarial Synthesis for Enhanced Medical Segmentation Generalization
127. CVPR 2026Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning
128. CVPR 2026DiffusionFF A Diffusion-based Framework for Joint Face Forgery Detection and
129. CVPR 2026DiffusionHarmonizer Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion
130. CVPR 2026DiffuView Multi-View Diffusion Pretraining for 3D Aware Robotic Manipulation
131. CVPR 2026DiP Taming Diffusion Models in Pixel Space
132. CVPR 2026DisCa Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
133. CVPR 2026Disentangled Textual Priors for Diffusion-based Image Super-Resolution
134. CVPR 2026DiT-IC Aligned Diffusion Transformer for Efficient Image Compression
135. CVPR 2026Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization
136. CVPR 2026DiverseDiT Towards Diverse Representation Learning in Diffusion Transformers
137. CVPR 2026DMAligner Enhancing Image Alignment via Diffusion Model Based View Synthesis
138. CVPR 2026DMGD Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models
139. CVPR 2026dMLLM-TTS Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large
140. CVPR 2026DNF-SR Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
141. CVPR 2026Do Less Achieve More Do We Need Every-Step Optimization for
142. CVPR 2026DreamShot Personalized Storyboard Synthesis with Video Diffusion Prior
143. CVPR 2026DreamSR Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion
144. CVPR 2026DRiffusion Draft-and-Refine Process Parallelizes Diffusion Models with Ease
145. CVPR 2026DrivePTS A Progressive Learning Framework with Textual and Structural Enhancement
146. CVPR 2026DRM Diffusion-based Reward Model With Step-wise Guidance
147. CVPR 2026DTG-Restore Training-Free Diffusion Refinement for Generative Video Super-Resolution
148. CVPR 2026Dual Ascent Diffusion for Inverse Problems
149. CVPR 2026DUO-VSR Dual-Stream Distillation for One-Step Video Super-Resolution
150. CVPR 2026DuoMo Dual Motion Diffusion for World-Space Human Reconstruction

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。