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 728 篇，第 2 / 15 页

51. ICML 2026Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
52. ICML 2026Bi-Anchor Interpolation Solver for Accelerating Generative Modeling
53. ICML 2026Biased Generalization in Diffusion Models
54. ICML 2026BioDynaSpec: Harmonic-Guided Spatio-Spectral Autoregressive Diffusion for Protein Dynamics Generation
55. ICML 2026BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
56. ICML 2026Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
57. ICML 2026Branching Diffusion for Point Processes in Time and Space
58. ICML 2026Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
59. ICML 2026Breaking Manifold Continuity: Vector Quantized Modeling for Real-Centric Deepfake Detection
60. ICML 2026Breaking the Factorization Barrier in Diffusion Language Models
61. ICML 2026Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation
62. ICML 2026Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching
63. ICML 2026Bridging Dynamics and Data: A Unified Diffusion Framework for Mechanistically-Informed Epidemic Forecasting
64. ICML 2026Bridging RGB and RAW: Single-step Deterministic Flow with Homogeneous Representation Alignment
65. ICML 2026Bridging Structure and Semantics: Uncertainty-Modulated Dual-Path Diffusion for Robust Text-Attributed Graph Learning
66. ICML 2026Budget-Constrained Step-Level Diffusion Caching
67. ICML 2026CacheEdit: Efficient Multi-round Image Editing via Adaptive Token-wise Reuse.
68. ICML 2026Calibrated Test-Time Guidance for Bayesian Inference
69. ICML 2026Calibrating Generative Models to Distributional Constraints
70. ICML 2026CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping
71. ICML 2026Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models
72. ICML 2026CANDI: Hybrid Discrete-Continuous Diffusion Models
73. ICML 2026Cardio-mmFlow: A Gaussian-Prior-Free Physics-Informed Flow Matching Framework for Electrocardiogram to mmWave Radar Synthesis
74. ICML 2026Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features
75. ICML 2026Categorical Flow Maps
76. ICML 2026Categorical Reparameterization with Denoising Diffusion Models
77. ICML 2026CatFlow: Co-generation of Slab-Adsorbate Systems via Flow Matching
78. ICML 2026Causal Flow Q-Learning for Robust Offline Reinforcement Learning
79. ICML 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
80. ICML 2026Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
81. ICML 2026CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models
82. ICML 2026CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment
83. ICML 2026Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
84. ICML 2026Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
85. ICML 2026Clustering in Deep Stochastic Transformers
86. ICML 2026CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
87. ICML 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
88. ICML 2026CODiff: One-Step Diffusion Model for Camouflaged Object Detection
89. ICML 2026Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
90. ICML 2026CoGenCast: A Coupled Autoregressive–Flow Generative Framework for Time Series Forecasting
91. ICML 2026Compositional Generative Modeling from Decentralized Data
92. ICML 2026Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
93. ICML 2026Concept Removal for Frontier Image Generative Models
94. ICML 2026Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion Sampling
95. ICML 2026Condition-Aware Graph Flow Matching for Modeling the Distributions of Complex Fluid Systems
96. ICML 2026Conditional Diffusion Sampling
97. ICML 2026Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
98. ICML 2026Consistent Diffusion Language Models
99. ICML 2026Constrained Flow Optimization via Sequential Fine-Tuning for Molecular Design
100. ICML 2026Continuity-Regularized Flow Matching for Offline Reinforcement Learning

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。