Generative Flows papers, 2023–2026

Key findings

• Generative Flows went from 73 papers in 2023 to 139 in 2026, roughly 1.9x in three years.
• NeurIPS publishes the most Generative Flows work: 130 papers from 2023 to 2026, 30% of the four-venue total.
• The fastest-growing overlap is with Applications · chemistry physics and earth sciences: papers tagged with both rose from 1 in 2023 to 5 in 2026.
• Among the 5 topics under Probabilistic and Bayesian, it ranks #3 by 2026 paper count; the fastest grower in the group, Gaussian Processes, is up 2.2x versus 1.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Generative Flows papers

429 papers, page 2 of 9

51. ICLR 2026Regulating Internal Evidence Flows for Robust Learning Under Spurious Correlations
52. ICLR 2026Reliable Probabilistic Forecasting of Irregular Time Series through Marginalization-Consistent Flows
53. ICLR 2026SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flows
54. ICLR 2026Shrinking Proteins with Diffusion
55. ICLR 2026Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models
56. ICLR 2026Terminal Velocity Matching
57. ICLR 2026ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
58. ICLR 2026Topological Flow Matching
59. ICLR 2026TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
60. ICLR 2026What happens when generative AI models train recursively on each others' outputs?
61. ICLR 2026Why We Need New Benchmarks for Local Intrinsic Dimension Estimation
62. ICML 2026A Theoretical Framework for Statistical Evaluability of Generative Models
63. ICML 2026A Unifying View of Variational Generative Wasserstein Flows
64. ICML 2026Adapting Noise to Data: Generative Flows from Learned 1D Processes
65. ICML 2026Analytic Bijections for Smooth and Interpretable Normalizing Flows
66. ICML 2026Calibrating Generative Models to Distributional Constraints
67. ICML 2026Compositional Planning with Jumpy World Models
68. ICML 2026Curated Synthetic Data Doesn’t Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
69. ICML 2026Distribution Matching Variational AutoEncoder
70. ICML 2026Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
71. ICML 2026Generative Augmented Inference
72. ICML 2026Hyperbolic RQ-VAE enhanced Generative Recommendation with Differential-Length Codebook Strategy
73. ICML 2026Improving LLM-Based Recommenders with Conservative Generative Flow Networks
74. ICML 2026Infinite-Dimensional Generative Diffusions via Doob’s h-Transform
75. ICML 2026Learning Discrete Diffusion on Graphs via Free-Energy Gradient Flows
76. ICML 2026Learning-to-Optimize via Deep Unfolded Flows
77. ICML 2026Manifold-Aware Perturbations for Constrained Generative Modeling
78. ICML 2026MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation
79. ICML 2026Normalizing Flows with Iterative Denoising
80. ICML 2026Overclocking Electrostatic Generative Models
81. ICML 2026Path-Coupled Bellman Flows for Distributional Reinforcement Learning
82. ICML 2026Quantum latent distributions in deep generative models
83. ICML 2026Revisiting Spectral Representations in Generative Diffusion Models
84. ICML 2026Scalable GANs with Transformers
85. ICML 2026SCOUT: Cyclic Causal Discovery Under Soft Interventions with Unknown Targets
86. ICML 2026Spectral Bridge Variational Inference: Dynamic LoRA via Bures-Wasserstein Gradient Flows
87. ICML 2026SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
88. ICML 2026Test-Time Guidance for Flow-Based Generative Models via Parallel Tempering on Source Distributions
89. ICML 2026Trajectory Consistency for One-Step Generation on Euler Mean Flows
90. ICML 2026Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
91. ICML 2026Unfolding Generative Flows with Koopman Operators: Trajectory-Preserving Linearization
92. ICML 2026Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path
93. ICML 2026XYZFlow: Scaling Multidimensional Shortcut Flows for Efficient Generative Modeling
94. NeurIPS 2026Active Learning for Conditional Generative Compressed Sensing
95. NeurIPS 2026Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel
96. NeurIPS 2026Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
97. NeurIPS 2026Beckmann Transport Models: From Autonomous Flows to One-Step Maps
98. NeurIPS 2026Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
99. NeurIPS 2026ChiP-STAR: Spatial-Topological Attention for Pre-trained Generative Chip Routing
100. NeurIPS 2026Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes

FAQ

How many Generative Flows papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

429 in total: 73 in 2023, 98 in 2024, 119 in 2025, 139 in 2026.

How many Generative Flows papers are at NeurIPS 2026?

NeurIPS 2026 has 46 Generative Flows papers, versus 37 the year before.

How many Generative Flows papers are at ICLR 2026?

ICLR 2026 has 37 Generative Flows papers, versus 35 the year before.

How many Generative Flows papers are at ICML 2026?

ICML 2026 has 32 Generative Flows papers, versus 25 the year before.

How many Generative Flows papers are at CVPR 2026?

CVPR 2026 has 24 Generative Flows papers, versus 22 the year before.

Which conference publishes the most Generative Flows papers?

NeurIPS, with 130 papers from 2023 to 2026.