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 37 篇，第 1 / 1 页

1. NeurIPS 2025Ambient Diffusion Omni: Training Good Models with Bad Data
2. NeurIPS 2025Amortized Sampling with Transferable Normalizing Flows
3. NeurIPS 2025Amortized Variational Transdimensional Inference
4. NeurIPS 2025Asymptotically exact variational flows via involutive MCMC kernels
5. NeurIPS 2025Balanced Conic Rectified Flow
6. NeurIPS 2025Beyond Scores: Proximal Diffusion Models
7. NeurIPS 2025CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
8. NeurIPS 2025Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
9. NeurIPS 2025Counterfactual Identifiability via Dynamic Optimal Transport
10. NeurIPS 2025DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control
11. NeurIPS 2025Edit Flows: Variable Length Discrete Flow Matching with Sequence-Level Edit Operations
12. NeurIPS 2025Enhancing Consistency of Flow-Based Image Editing through Kalman Control
13. NeurIPS 2025Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
14. NeurIPS 2025Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
15. NeurIPS 2025FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
16. NeurIPS 2025From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
17. NeurIPS 2025Generative Distribution Embeddings
18. NeurIPS 2025Gradient Variance Reveals Failure Modes in Flow-Based Generative Models
19. NeurIPS 2025Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
20. NeurIPS 2025Learning to Integrate Diffusion ODEs by Averaging the Derivatives
21. NeurIPS 2025MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
22. NeurIPS 2025Mean Flows for One-step Generative Modeling
23. NeurIPS 2025Missing Data Imputation by Reducing Mutual Information with Rectified Flows
24. NeurIPS 2025Multitask Learning with Stochastic Interpolants
25. NeurIPS 2025Multivariate Latent Recalibration for Conditional Normalizing Flows
26. NeurIPS 2025Normalizing Flows are Capable Models for Continuous Control
27. NeurIPS 2025Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions
28. NeurIPS 2025Path Gradients after Flow Matching
29. NeurIPS 2025Riemannian Consistency Model
30. NeurIPS 2025SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories
31. NeurIPS 2025Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models
32. NeurIPS 2025Sequence Modeling with Spectral Mean Flows
33. NeurIPS 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
34. NeurIPS 2025STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
35. NeurIPS 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
36. NeurIPS 2025Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
37. NeurIPS 2025When Models Don’t Collapse: On the Consistency of Iterative MLE

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。