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 73 篇，第 1 / 2 页

1. CVPR 2023Delving Into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling
2. CVPR 2023FlowGrad: Controlling the Output of Generative ODEs With Gradients
3. CVPR 2023GaitGCI: Generative Counterfactual Intervention for Gait Recognition
4. CVPR 2023GANHead: Towards Generative Animatable Neural Head Avatars
5. CVPR 2023Generalizing Dataset Distillation via Deep Generative Prior
6. CVPR 2023Generative Semantic Segmentation
7. CVPR 2023Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
8. CVPR 2023Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
9. CVPR 2023Persistent Nature: A Generative Model of Unbounded 3D Worlds
10. CVPR 2023PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow
11. CVPR 2023RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models
12. CVPR 2023SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene
13. ICLR 2023AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly Detection
14. ICLR 2023Better Generative Replay for Continual Federated Learning
15. ICLR 2023Blurring Diffusion Models
16. ICLR 2023Building Normalizing Flows with Stochastic Interpolants
17. ICLR 2023Deterministic training of generative autoencoders using invertible layers
18. ICLR 2023Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models
19. ICLR 2023Explicitly Minimizing the Blur Error of Variational Autoencoders
20. ICLR 2023Flow Annealed Importance Sampling Bootstrap
21. ICLR 2023Flow Matching for Generative Modeling
22. ICLR 2023Generative Augmented Flow Networks
23. ICLR 2023GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure
24. ICLR 2023Hierarchical Sliced Wasserstein Distance
25. ICLR 2023Learning Continuous Normalizing Flows For Faster Convergence To Target Distribution via Ascent Regularizations
26. ICLR 2023MMVAE+: Enhancing the Generative Quality of Multimodal VAEs without Compromises
27. ICLR 2023OPTQ: Accurate Quantization for Generative Pre-trained Transformers
28. ICLR 2023Quantized Compressed Sensing with Score-Based Generative Models
29. ICLR 2023Structure by Architecture: Structured Representations without Regularization
30. ICML 2023Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces
31. ICML 2023Chemically Transferable Generative Backmapping of Coarse-Grained Proteins
32. ICML 2023Conditionally Strongly Log-Concave Generative Models
33. ICML 2023Data-Copying in Generative Models: A Formal Framework
34. ICML 2023Disentangled Generative Models for Robust Prediction of System Dynamics
35. ICML 2023Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
36. ICML 2023FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
37. ICML 2023Latent Traversals in Generative Models as Potential Flows
38. ICML 2023Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
39. ICML 2023MixFlows: principled variational inference via mixed flows
40. ICML 2023MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows
41. ICML 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplings
42. ICML 2023Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels
43. ICML 2023Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
44. ICML 2023Normalizing Flows for Interventional Density Estimation
45. ICML 2023On Kinetic Optimal Probability Paths for Generative Models
46. ICML 2023On Provable Copyright Protection for Generative Models
47. ICML 2023Poisoning Generative Replay in Continual Learning to Promote Forgetting
48. ICML 2023Predictive Flows for Faster Ford-Fulkerson
49. ICML 2023Proper Losses for Discrete Generative Models
50. ICML 2023Q-Flow: Generative Modeling for Differential Equations of Open Quantum Dynamics with Normalizing Flows

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。