生成流论文趋势 2023–2026

主要结论

• 生成流论文从 2023 年的 73 篇增长到 2026 年的 139 篇，三年间扩大到约 1.9 倍。
• NeurIPS 是发生成流论文最多的会议，2023–2026 年共 130 篇，占四个会议总量的 30%。
• 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 1 篇增至 2026 年的 5 篇。
• 在「概率与贝叶斯」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的高斯过程是 2.2 倍，生成流是 1.9 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 2026Exact Recovery of Lipschitz Orthogonal Coordinate Transformations via Constrained Normalizing Flows
• ICML 2026Learning-to-Optimize via Deep Unfolded Flows
• ICLR 2026Frozen Priors, Fluid Forecasts: Prequential Uncertainty for Low-Data Deployment with Pretrained Generative Models
• CVPR 2026AnchorFlow Training-Free 3D Editing via Latent Anchor-Aligned Flows
• NeurIPS 2025Amortized Sampling with Transferable Normalizing Flows
• ICML 2025Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions
• ICLR 2025Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
• CVPR 2025DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows
• NeurIPS 2024Learning Distributions on Manifolds with Free-Form Flows
• ICML 2024A Computational Framework for Solving Wasserstein Lagrangian Flows
• ICLR 2024Fast and unified path gradient estimators for normalizing flows
• CVPR 2024Distributionally Generative Augmentation for Fair Facial Attribute Classification
• NeurIPS 2023Canonical normalizing flows for manifold learning
• ICML 2023MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows
• ICLR 2023AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly Detection
• CVPR 2023Delving Into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling
• NeurIPS 2026From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
• ICML 2026Hyperbolic RQ-VAE enhanced Generative Recommendation with Differential-Length Codebook Strategy
• ICLR 2026JAPAN: Joint Adaptive Prediction Areas with Normalising Flow
• CVPR 2026BUSSARD Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection

全部生成流论文

共 119 篇，第 2 / 3 页

51. ICLR 2025PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation
52. ICLR 2025Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?
53. ICLR 2025Restructuring Vector Quantization with the Rotation Trick
54. ICLR 2025Think while You Generate: Discrete Diffusion with Planned Denoising
55. ICLR 2025Topological Schrödinger Bridge Matching
56. ICLR 2025Towards Hierarchical Rectified Flow
57. ICLR 2025Truncated Consistency Models
58. ICML 2025A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
59. ICML 2025AffinityFlow: Guided Flows for Antibody Affinity Maturation
60. ICML 2025An Error Analysis of Flow Matching for Deep Generative Modeling
61. ICML 2025Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions
62. ICML 2025Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows
63. ICML 2025Concept-Centric Token Interpretation for Vector-Quantized Generative Models
64. ICML 2025Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation
65. ICML 2025Flexible Tails for Normalizing Flows
66. ICML 2025Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
67. ICML 2025Hessian Geometry of Latent Space in Generative Models
68. ICML 2025Importance Corrected Neural JKO Sampling
69. ICML 2025Improving Consistency Models with Generator-Augmented Flows
70. ICML 2025Inductive Moment Matching
71. ICML 2025InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference
72. ICML 2025Is Noise Conditioning Necessary for Denoising Generative Models?
73. ICML 2025Learning Distances from Data with Normalizing Flows and Score Matching
74. ICML 2025Learning Monotonic Probabilities with a Generative Cost Model
75. ICML 2025Normalizing Flows are Capable Generative Models
76. ICML 2025Revisiting Unbiased Implicit Variational Inference
77. ICML 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generators
78. ICML 2025Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
79. ICML 2025Stream-level Flow Matching with Gaussian Processes
80. ICML 2025Temperature-Annealed Boltzmann Generators
81. ICML 2025Testing Conditional Mean Independence Using Generative Neural Networks
82. ICML 2025Training Diffusion-based Generative Models with Limited Data
83. NeurIPS 2025Ambient Diffusion Omni: Training Good Models with Bad Data
84. NeurIPS 2025Amortized Sampling with Transferable Normalizing Flows
85. NeurIPS 2025Amortized Variational Transdimensional Inference
86. NeurIPS 2025Asymptotically exact variational flows via involutive MCMC kernels
87. NeurIPS 2025Balanced Conic Rectified Flow
88. NeurIPS 2025Beyond Scores: Proximal Diffusion Models
89. NeurIPS 2025CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
90. NeurIPS 2025Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
91. NeurIPS 2025Counterfactual Identifiability via Dynamic Optimal Transport
92. NeurIPS 2025DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control
93. NeurIPS 2025Edit Flows: Variable Length Discrete Flow Matching with Sequence-Level Edit Operations
94. NeurIPS 2025Enhancing Consistency of Flow-Based Image Editing through Kalman Control
95. NeurIPS 2025Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
96. NeurIPS 2025Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
97. NeurIPS 2025FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
98. NeurIPS 2025From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
99. NeurIPS 2025Generative Distribution Embeddings
100. NeurIPS 2025Gradient Variance Reveals Failure Modes in Flow-Based Generative Models

常见问题

2023–2026 年四大会议一共有多少篇生成流论文？

共 429 篇，按年份分别是 2023 年 73 篇、2024 年 98 篇、2025 年 119 篇、2026 年 139 篇。

NeurIPS 2026 有多少篇生成流论文？

NeurIPS 2026 有 46 篇生成流论文，上一届是 37 篇。

ICLR 2026 有多少篇生成流论文？

ICLR 2026 有 37 篇生成流论文，上一届是 35 篇。

ICML 2026 有多少篇生成流论文？

ICML 2026 有 32 篇生成流论文，上一届是 25 篇。

CVPR 2026 有多少篇生成流论文？

CVPR 2026 有 24 篇生成流论文，上一届是 22 篇。

哪个会议的生成流论文最多？

NeurIPS，2023–2026 年共 130 篇。