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 1 / 3 页

1. ICLR 2026``Noisier'’ Noise Contrastive Estimation is (Almost) Maximum Likelihood
2. ICLR 2026Accelerated Parallel Tempering via Neural Transports
3. ICLR 2026AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport
4. ICLR 2026Antithetic Noise in Diffusion Models
5. ICLR 2026Any-Order Flexible Length Masked Diffusion
6. ICLR 2026Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models
7. ICLR 2026Carré du champ flow matching: better quality-generalisation tradeoff in generative models
8. ICLR 2026Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators
9. ICLR 2026FALCON: Few-step Accurate Likelihoods for Continuous Flows
10. ICLR 2026FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference
11. ICLR 2026FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows
12. ICLR 2026From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments
13. ICLR 2026Frozen Priors, Fluid Forecasts: Prequential Uncertainty for Low-Data Deployment with Pretrained Generative Models
14. ICLR 2026GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes
15. ICLR 2026Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making
16. ICLR 2026GenCtrl -- A Formal Controllability Toolkit for Generative Models
17. ICLR 2026Generative Blocks World: Moving Things Around in Pictures
18. ICLR 2026Generative Universal Verifier as Multimodal Meta-Reasoner
19. ICLR 2026HoloPart: Generative 3D Part Amodal Segmentation
20. ICLR 2026JAPAN: Joint Adaptive Prediction Areas with Normalising Flow
21. ICLR 2026Latent Stochastic Interpolants
22. ICLR 2026Measurement Score-Based Diffusion Model
23. ICLR 2026Mitigating Noise Shift in Denoising Generative Models with Noise Awareness Guidance
24. ICLR 2026Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
25. ICLR 2026Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
26. ICLR 2026Refine Drugs, Don’t Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discovery
27. ICLR 2026Regulating Internal Evidence Flows for Robust Learning Under Spurious Correlations
28. ICLR 2026Reliable Probabilistic Forecasting of Irregular Time Series through Marginalization-Consistent Flows
29. ICLR 2026SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flows
30. ICLR 2026Shrinking Proteins with Diffusion
31. ICLR 2026Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models
32. ICLR 2026Terminal Velocity Matching
33. ICLR 2026ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
34. ICLR 2026Topological Flow Matching
35. ICLR 2026TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
36. ICLR 2026What happens when generative AI models train recursively on each others' outputs?
37. ICLR 2026Why We Need New Benchmarks for Local Intrinsic Dimension Estimation
38. ICLR 2025Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
39. ICLR 2025Boosting Latent Diffusion with Perceptual Objectives
40. ICLR 2025Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
41. ICLR 2025COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation
42. ICLR 2025CoInD: Enabling Logical Compositions in Diffusion Models
43. ICLR 2025Consistency Models Made Easy
44. ICLR 2025CONTRA: Conformal Prediction Region via Normalizing Flow Transformation
45. ICLR 2025CryoGEN: Generative Energy-based Models for Cryogenic Electron Tomography Reconstruction
46. ICLR 2025cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM
47. ICLR 2025Data Unlearning in Diffusion Models
48. ICLR 2025Deep MMD Gradient Flow without adversarial training
49. ICLR 2025Designing Mechanical Meta-Materials by Learning Equivariant Flows
50. ICLR 2025Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete Generators

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。