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 98 篇，第 1 / 2 页

1. CVPR 2024All Rivers Run to the Sea: Private Learning with Asymmetric Flows
2. CVPR 2024Boosting Flow-based Generative Super-Resolution Models via Learned Prior
3. CVPR 2024CityDreamer: Compositional Generative Model of Unbounded 3D Cities
4. CVPR 2024DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
5. CVPR 2024Distributionally Generative Augmentation for Fair Facial Attribute Classification
6. CVPR 2024DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
7. CVPR 2024En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data
8. CVPR 2024G3DR: Generative 3D Reconstruction in ImageNet
9. CVPR 2024Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing
10. CVPR 2024Generative Multimodal Models are In-Context Learners
11. CVPR 2024Generative Powers of Ten
12. CVPR 2024Generative Quanta Color Imaging
13. CVPR 2024Generative Unlearning for Any Identity
14. CVPR 2024Learning Large-Factor EM Image Super-Resolution with Generative Priors
15. CVPR 2024MaskPLAN: Masked Generative Layout Planning from Partial Input
16. CVPR 2024MMM: Generative Masked Motion Model
17. CVPR 2024Mosaic-SDF for 3D Generative Models
18. CVPR 2024NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows
19. CVPR 2024NeRFiller: Completing Scenes via Generative 3D Inpainting
20. CVPR 2024Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling
21. CVPR 2024Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata
22. CVPR 2024PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
23. CVPR 2024Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection
24. CVPR 2024Would Deep Generative Models Amplify Bias in Future Models?
25. ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
26. ICLR 2024Bespoke Solvers for Generative Flow Models
27. ICLR 2024Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
28. ICLR 2024Emu: Generative Pretraining in Multimodality
29. ICLR 2024Fast and unified path gradient estimators for normalizing flows
30. ICLR 2024GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
31. ICLR 2024Generative Sliced MMD Flows with Riesz Kernels
32. ICLR 2024Idempotent Generative Network
33. ICLR 2024Kernelised Normalising Flows
34. ICLR 2024Lifting Architectural Constraints of Injective Flows
35. ICLR 2024Light Schrödinger Bridge
36. ICLR 2024LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
37. ICLR 2024Modelling complex vector drawings with stroke-clouds
38. ICLR 2024On the Stability of Iterative Retraining of Generative Models on their own Data
39. ICLR 2024Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
40. ICLR 2024SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
41. ICLR 2024sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
42. ICLR 2024The Generative AI Paradox: “What It Can Create, It May Not Understand”
43. ICML 2024A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models
44. ICML 2024A Computational Framework for Solving Wasserstein Lagrangian Flows
45. ICML 2024A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective
46. ICML 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
47. ICML 2024Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
48. ICML 2024COPAL: Continual Pruning in Large Language Generative Models
49. ICML 2024DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
50. ICML 2024From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers

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。