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 107 篇，第 2 / 3 页

51. ICLR 2025FaceShot: Bring Any Character into Life
52. ICLR 2025Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
53. ICLR 2025Flow matching achieves almost minimax optimal convergence
54. ICLR 2025Generative Flows on Synthetic Pathway for Drug Design
55. ICLR 2025GMValuator: Similarity-based Data Valuation for Generative Models
56. ICLR 2025Heavy-Tailed Diffusion Models
57. ICLR 2025Injective flows for star-like manifolds
58. ICLR 2025Latent Bayesian Optimization via Autoregressive Normalizing Flows
59. ICLR 2025Multilevel Generative Samplers for Investigating Critical Phenomena
60. ICLR 2025MuPT: A Generative Symbolic Music Pretrained Transformer
61. ICLR 2025Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry
62. ICLR 2025No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
63. ICLR 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generation
64. ICLR 2025NRGBoost: Energy-Based Generative Boosted Trees
65. ICLR 2025ParetoFlow: Guided Flows in Multi-Objective Optimization
66. ICLR 2025PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation
67. ICLR 2025Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?
68. ICLR 2025Restructuring Vector Quantization with the Rotation Trick
69. ICLR 2025Think while You Generate: Discrete Diffusion with Planned Denoising
70. ICLR 2025Topological Schrödinger Bridge Matching
71. ICLR 2025Towards Hierarchical Rectified Flow
72. ICLR 2025Truncated Consistency Models
73. ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
74. ICLR 2024Bespoke Solvers for Generative Flow Models
75. ICLR 2024Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
76. ICLR 2024Emu: Generative Pretraining in Multimodality
77. ICLR 2024Fast and unified path gradient estimators for normalizing flows
78. ICLR 2024GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
79. ICLR 2024Generative Sliced MMD Flows with Riesz Kernels
80. ICLR 2024Idempotent Generative Network
81. ICLR 2024Kernelised Normalising Flows
82. ICLR 2024Lifting Architectural Constraints of Injective Flows
83. ICLR 2024Light Schrödinger Bridge
84. ICLR 2024LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
85. ICLR 2024Modelling complex vector drawings with stroke-clouds
86. ICLR 2024On the Stability of Iterative Retraining of Generative Models on their own Data
87. ICLR 2024Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
88. ICLR 2024SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
89. ICLR 2024sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
90. ICLR 2024The Generative AI Paradox: “What It Can Create, It May Not Understand”
91. ICLR 2023AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly Detection
92. ICLR 2023Better Generative Replay for Continual Federated Learning
93. ICLR 2023Blurring Diffusion Models
94. ICLR 2023Building Normalizing Flows with Stochastic Interpolants
95. ICLR 2023Deterministic training of generative autoencoders using invertible layers
96. ICLR 2023Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models
97. ICLR 2023Explicitly Minimizing the Blur Error of Variational Autoencoders
98. ICLR 2023Flow Annealed Importance Sampling Bootstrap
99. ICLR 2023Flow Matching for Generative Modeling
100. ICLR 2023Generative Augmented Flow Networks

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。