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 694 篇，第 2 / 14 页

51. ICLR 2026Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
52. ICLR 2026Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
53. ICLR 2026Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model
54. ICLR 2026Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion Models
55. ICLR 2026BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
56. ICLR 2026BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
57. ICLR 2026BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
58. ICLR 2026Block-wise Adaptive Caching for Accelerating Diffusion Policy
59. ICLR 2026Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer
60. ICLR 2026Branched Schrödinger Bridge Matching
61. ICLR 2026BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
62. ICLR 2026BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
63. ICLR 2026Bridging Degradation Discrimination and Generation for Universal Image Restoration
64. ICLR 2026Bridging Successor Measure and Online Policy Learning with Flow Matching-Based Representations
65. ICLR 2026Bridging the Distribution Gap to Harness Pretrained Diffusion Priors for Super-Resolution
66. ICLR 2026Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
67. ICLR 2026Bures-Wasserstein Flow Matching for Graph Generation
68. ICLR 2026BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
69. ICLR 2026Captain Cinema: Towards Short Movie Generation
70. ICLR 2026Capturing Visual Environment Structure Correlates with Control Performance
71. ICLR 2026CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models
72. ICLR 2026Carré du champ flow matching: better quality-generalisation tradeoff in generative models
73. ICLR 2026CASteer: Cross-Attention Steering for Controllable Concept Erasure
74. ICLR 2026Causal Score Conditioning for Multi-Resolution Latent Systems
75. ICLR 2026CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators
76. ICLR 2026CheckMate! Watermarking Graph Diffusion Models in Polynomial Time
77. ICLR 2026CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models
78. ICLR 2026CL-DPS: A Contrastive Learning Approach to Blind Nonlinear Inverse Problem Solving via Diffusion Posterior Sampling
79. ICLR 2026Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
80. ICLR 2026Clustering by Denoising: Latent plug-and-play diffusion for single-cell embeddings
81. ICLR 2026CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow-Map Models
82. ICLR 2026Co-occurring Associated REtained concepts in Diffusion Unlearning
83. ICLR 2026CO3: CONTRASTING CONCEPTS COMPOSE BETTER
84. ICLR 2026CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer
85. ICLR 2026CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
86. ICLR 2026CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation
87. ICLR 2026ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes
88. ICLR 2026Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
89. ICLR 2026Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
90. ICLR 2026Composition of Memory Experts for Diffusion World Models
91. ICLR 2026Compositional amortized inference for large-scale hierarchical Bayesian models
92. ICLR 2026Compositional Diffusion with Guided search for Long-Horizon Planning
93. ICLR 2026Compositional Visual Planning via Inference-Time Diffusion Scaling
94. ICLR 2026Concept-based Adversarial Attack: a Probabilistic Perspective
95. ICLR 2026Concept-TRAK: Understanding how diffusion models learn concepts through concept attribution
96. ICLR 2026Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss
97. ICLR 2026Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting
98. ICLR 2026Conjuring Semantic Similarity
99. ICLR 2026Consis-GCPO: Consistency-Preserving Group Causal Preference Optimization for Vision Customization
100. ICLR 2026Consistency Geodesic Bridge: Image Restoration with Pretrained 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。