生成流论文趋势 2023–2026

Normalizing flows

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 429 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

生成流论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231817261273
20242918272498
202537352522119
202646373224139

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

全部生成流论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 429 篇，第 5 / 9 页

  1. ICML 2025Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows
  2. ICML 2025Concept-Centric Token Interpretation for Vector-Quantized Generative Models
  3. ICML 2025Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation
  4. ICML 2025Flexible Tails for Normalizing Flows
  5. ICML 2025Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
  6. ICML 2025Hessian Geometry of Latent Space in Generative Models
  7. ICML 2025Importance Corrected Neural JKO Sampling
  8. ICML 2025Improving Consistency Models with Generator-Augmented Flows
  9. ICML 2025Inductive Moment Matching
  10. ICML 2025InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference
  11. ICML 2025Is Noise Conditioning Necessary for Denoising Generative Models?
  12. ICML 2025Learning Distances from Data with Normalizing Flows and Score Matching
  13. ICML 2025Learning Monotonic Probabilities with a Generative Cost Model
  14. ICML 2025Normalizing Flows are Capable Generative Models
  15. ICML 2025Revisiting Unbiased Implicit Variational Inference
  16. ICML 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generators
  17. ICML 2025Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
  18. ICML 2025Stream-level Flow Matching with Gaussian Processes
  19. ICML 2025Temperature-Annealed Boltzmann Generators
  20. ICML 2025Testing Conditional Mean Independence Using Generative Neural Networks
  21. ICML 2025Training Diffusion-based Generative Models with Limited Data
  22. NeurIPS 2025Ambient Diffusion Omni: Training Good Models with Bad Data
  23. NeurIPS 2025Amortized Sampling with Transferable Normalizing Flows
  24. NeurIPS 2025Amortized Variational Transdimensional Inference
  25. NeurIPS 2025Asymptotically exact variational flows via involutive MCMC kernels
  26. NeurIPS 2025Balanced Conic Rectified Flow
  27. NeurIPS 2025Beyond Scores: Proximal Diffusion Models
  28. NeurIPS 2025CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
  29. NeurIPS 2025Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
  30. NeurIPS 2025Counterfactual Identifiability via Dynamic Optimal Transport
  31. NeurIPS 2025DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control
  32. NeurIPS 2025Edit Flows: Variable Length Discrete Flow Matching with Sequence-Level Edit Operations
  33. NeurIPS 2025Enhancing Consistency of Flow-Based Image Editing through Kalman Control
  34. NeurIPS 2025Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
  35. NeurIPS 2025Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
  36. NeurIPS 2025FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
  37. NeurIPS 2025From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
  38. NeurIPS 2025Generative Distribution Embeddings
  39. NeurIPS 2025Gradient Variance Reveals Failure Modes in Flow-Based Generative Models
  40. NeurIPS 2025Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
  41. NeurIPS 2025Learning to Integrate Diffusion ODEs by Averaging the Derivatives
  42. NeurIPS 2025MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
  43. NeurIPS 2025Mean Flows for One-step Generative Modeling
  44. NeurIPS 2025Missing Data Imputation by Reducing Mutual Information with Rectified Flows
  45. NeurIPS 2025Multitask Learning with Stochastic Interpolants
  46. NeurIPS 2025Multivariate Latent Recalibration for Conditional Normalizing Flows
  47. NeurIPS 2025Normalizing Flows are Capable Models for Continuous Control
  48. NeurIPS 2025Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions
  49. NeurIPS 2025Path Gradients after Flow Matching
  50. NeurIPS 2025Riemannian Consistency Model

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查生成流在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "generative-flows"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「概率与贝叶斯」下的其他主题