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 661 篇，第 2 / 14 页

51. NeurIPS 2026B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet
52. NeurIPS 2026Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
53. NeurIPS 2026Beckmann Transport Models: From Autonomous Flows to One-Step Maps
54. NeurIPS 2026Bernini: Latent Semantic Planning for Video Diffusion
55. NeurIPS 2026Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data
56. NeurIPS 2026Best-of-$N$ Guidance for Test-time Diffusion Alignment
57. NeurIPS 2026Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
58. NeurIPS 2026Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation
59. NeurIPS 2026Beyond Generation: Unlocking Discriminative Representations from Diffusion Models
60. NeurIPS 2026Beyond Local Neighborhoods: Fractional Diffusion with Levy Flights on Simplicial Complexes for Link Prediction
61. NeurIPS 2026Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
62. NeurIPS 2026Beyond Node Sequences: Relational Diffusion for Unified Graph Learning
63. NeurIPS 2026Beyond Single-Shot Conditioning: Test-Time Condition Refinement for Diffusion-Based Image Restoration
64. NeurIPS 2026Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
65. NeurIPS 2026Bidirectional Sparse Attention for Faster Video Diffusion Training
66. NeurIPS 2026BigCell: Generating Gigapixel Whole-Slide Images
67. NeurIPS 2026BiLoCo: Binary Low-Rank Corrections for LLM FP4 Decode
68. NeurIPS 2026BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion
69. NeurIPS 2026Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
70. NeurIPS 2026Bonobo: Efficient Library-Scale Generation for De Novo Antibody Design
71. NeurIPS 2026Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
72. NeurIPS 2026Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
73. NeurIPS 2026Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
74. NeurIPS 2026Bridge Graphical Models: Coupling, Projection, and Current-Preserving Dynamics for Generative Modeling
75. NeurIPS 2026Bridging Diffusion and Autoregression for Flexible Time Series Synthesis
76. NeurIPS 2026BuresTomFlow: Bures-Geometric Flow Matching for Posterior Quantum Tomography
77. NeurIPS 2026Cache the Future: Training-Free Self-Revision for Diffusion Transformer Acceleration
78. NeurIPS 2026Calibrating Generative Models to Feature Distributions with MMD Finetuning
79. NeurIPS 2026Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
80. NeurIPS 2026Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
81. NeurIPS 2026Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
82. NeurIPS 2026Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
83. NeurIPS 2026CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation
84. NeurIPS 2026Co-Evolving Interpolants and Flows via Path-Flow Alignment
85. NeurIPS 2026Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image Generation
86. NeurIPS 2026Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
87. NeurIPS 2026CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention
88. NeurIPS 2026Collective Supervision for Unified Biomolecular Conformation and Dynamics Modeling with CoDyna
89. NeurIPS 2026Colored Noise Diffusion Sampling
90. NeurIPS 2026Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Flow
91. NeurIPS 2026Conditioning Gaussian Processes on Almost Anything
92. NeurIPS 2026Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
93. NeurIPS 2026Confidence-Based Diffusion Sampling with Geometric Readiness Awareness for Accelerated Structure-based Drug Design
94. NeurIPS 2026Conservation Laws for Diffusion Models
95. NeurIPS 2026Consistent 3D Surface Flow Model with Global State
96. NeurIPS 2026Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
97. NeurIPS 2026Contextual Flow Matching for High-quality Visual Content Generation
98. NeurIPS 2026Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
99. NeurIPS 2026Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
100. NeurIPS 2026Continuous Diffusion Scales Competitively with Discrete Diffusion for Language

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。