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 110 篇，第 2 / 3 页

51. ICML 2025Revisiting Unbiased Implicit Variational Inference
52. ICML 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generators
53. ICML 2025Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
54. ICML 2025Stream-level Flow Matching with Gaussian Processes
55. ICML 2025Temperature-Annealed Boltzmann Generators
56. ICML 2025Testing Conditional Mean Independence Using Generative Neural Networks
57. ICML 2025Training Diffusion-based Generative Models with Limited Data
58. ICML 2024A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models
59. ICML 2024A Computational Framework for Solving Wasserstein Lagrangian Flows
60. ICML 2024A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective
61. ICML 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
62. ICML 2024Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
63. ICML 2024COPAL: Continual Pruning in Large Language Generative Models
64. ICML 2024DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
65. ICML 2024From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
66. ICML 2024Generative Active Learning for Long-tailed Instance Segmentation
67. ICML 2024Generative Conditional Distributions by Neural (Entropic) Optimal Transport
68. ICML 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design
69. ICML 2024Generative Marginalization Models
70. ICML 2024Genie: Generative Interactive Environments
71. ICML 2024GiLOT: Interpreting Generative Language Models via Optimal Transport
72. ICML 2024HexGen: Generative Inference of Large Language Model over Heterogeneous Environment
73. ICML 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?
74. ICML 2024Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict?
75. ICML 2024Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows
76. ICML 2024Masked Face Recognition with Generative-to-Discriminative Representations
77. ICML 2024Nearest Neighbour Score Estimators for Diffusion Generative Models
78. ICML 2024ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models
79. ICML 2024On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows
80. ICML 2024Reflected Flow Matching
81. ICML 2024Self-Correcting Self-Consuming Loops for Generative Model Training
82. ICML 2024Single-Model Attribution of Generative Models Through Final-Layer Inversion
83. ICML 2024Stochastic Interpolants with Data-Dependent Couplings
84. ICML 2024Timer: Generative Pre-trained Transformers Are Large Time Series Models
85. ICML 2023Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces
86. ICML 2023Chemically Transferable Generative Backmapping of Coarse-Grained Proteins
87. ICML 2023Conditionally Strongly Log-Concave Generative Models
88. ICML 2023Data-Copying in Generative Models: A Formal Framework
89. ICML 2023Disentangled Generative Models for Robust Prediction of System Dynamics
90. ICML 2023Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
91. ICML 2023FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
92. ICML 2023Latent Traversals in Generative Models as Potential Flows
93. ICML 2023Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
94. ICML 2023MixFlows: principled variational inference via mixed flows
95. ICML 2023MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows
96. ICML 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplings
97. ICML 2023Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels
98. ICML 2023Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
99. ICML 2023Normalizing Flows for Interventional Density Estimation
100. ICML 2023On Kinetic Optimal Probability Paths for 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。