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. NeurIPS 2025ASDSV: Multimodal Generation Made Efficient with Approximate Speculative Diffusion and Speculative Verification
52. NeurIPS 2025Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds
53. NeurIPS 2025Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR Spectra
54. NeurIPS 2025Attention with Trained Embeddings Provably Selects Important Tokens
55. NeurIPS 2025AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition
56. NeurIPS 2025AutoEdit: Automatic Hyperparameter Tuning for Image Editing
57. NeurIPS 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
58. NeurIPS 2025Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling
59. NeurIPS 2025BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
60. NeurIPS 2025BADiff: Bandwidth Adaptive Diffusion Model
61. NeurIPS 2025Balanced Conic Rectified Flow
62. NeurIPS 2025Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
63. NeurIPS 2025Beyond Scores: Proximal Diffusion Models
64. NeurIPS 2025Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
65. NeurIPS 2025Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
66. NeurIPS 2025BlurDM: A Blur Diffusion Model for Image Deblurring
67. NeurIPS 2025BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation
68. NeurIPS 2025Boosting Generative Image Modeling via Joint Image-Feature Synthesis
69. NeurIPS 2025BrainFlow: A Holistic Pathway of Dynamic Neural System on Manifold
70. NeurIPS 2025Breaking AR’s Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
71. NeurIPS 2025Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection
72. NeurIPS 2025BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
73. NeurIPS 2025BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization
74. NeurIPS 2025CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes
75. NeurIPS 2025CADMorph: Geometry‑Driven Parametric CAD Editing via a Plan–Generate–Verify Loop
76. NeurIPS 2025CamEdit: Continuous Camera Parameter Control for Photorealistic Image Editing
77. NeurIPS 2025Can Diffusion Models Disentangle? A Theoretical Perspective
78. NeurIPS 2025Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
79. NeurIPS 2025CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching
80. NeurIPS 2025CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
81. NeurIPS 2025CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
82. NeurIPS 2025CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects
83. NeurIPS 2025Color Conditional Generation with Sliced Wasserstein Guidance
84. NeurIPS 2025Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
85. NeurIPS 2025Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
86. NeurIPS 2025Composition and Alignment of Diffusion Models using Constrained Learning
87. NeurIPS 2025Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
88. NeurIPS 2025Compositional Monte Carlo Tree Diffusion for Extendable Planning
89. NeurIPS 2025Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion models
90. NeurIPS 2025Compressed and Smooth Latent Space for Text Diffusion Modeling
91. NeurIPS 2025Conditional Diffusion Anomaly Modeling on Graphs
92. NeurIPS 2025Conditional Panoramic Image Generation via Masked Autoregressive Modeling
93. NeurIPS 2025Conditioning Matters: Training Diffusion Policies is Faster Than You Think
94. NeurIPS 2025Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models
95. NeurIPS 2025Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
96. NeurIPS 2025Constrained Diffusers for Safe Planning and Control
97. NeurIPS 2025Constrained Discrete Diffusion
98. NeurIPS 2025Constrained Posterior Sampling: Time Series Generation with Hard Constraints
99. NeurIPS 2025Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
100. NeurIPS 2025Continuous Concepts Removal in Text-to-image 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。