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 130 篇，第 2 / 3 页

  1. NeurIPS 2025Balanced Conic Rectified Flow
  2. NeurIPS 2025Beyond Scores: Proximal Diffusion Models
  3. NeurIPS 2025CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
  4. NeurIPS 2025Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
  5. NeurIPS 2025Counterfactual Identifiability via Dynamic Optimal Transport
  6. NeurIPS 2025DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control
  7. NeurIPS 2025Edit Flows: Variable Length Discrete Flow Matching with Sequence-Level Edit Operations
  8. NeurIPS 2025Enhancing Consistency of Flow-Based Image Editing through Kalman Control
  9. NeurIPS 2025Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
  10. NeurIPS 2025Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
  11. NeurIPS 2025FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
  12. NeurIPS 2025From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
  13. NeurIPS 2025Generative Distribution Embeddings
  14. NeurIPS 2025Gradient Variance Reveals Failure Modes in Flow-Based Generative Models
  15. NeurIPS 2025Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
  16. NeurIPS 2025Learning to Integrate Diffusion ODEs by Averaging the Derivatives
  17. NeurIPS 2025MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
  18. NeurIPS 2025Mean Flows for One-step Generative Modeling
  19. NeurIPS 2025Missing Data Imputation by Reducing Mutual Information with Rectified Flows
  20. NeurIPS 2025Multitask Learning with Stochastic Interpolants
  21. NeurIPS 2025Multivariate Latent Recalibration for Conditional Normalizing Flows
  22. NeurIPS 2025Normalizing Flows are Capable Models for Continuous Control
  23. NeurIPS 2025Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions
  24. NeurIPS 2025Path Gradients after Flow Matching
  25. NeurIPS 2025Riemannian Consistency Model
  26. NeurIPS 2025SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories
  27. NeurIPS 2025Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models
  28. NeurIPS 2025Sequence Modeling with Spectral Mean Flows
  29. NeurIPS 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
  30. NeurIPS 2025STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
  31. NeurIPS 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
  32. NeurIPS 2025Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
  33. NeurIPS 2025When Models Don’t Collapse: On the Consistency of Iterative MLE
  34. NeurIPS 2024A Generative Model of Symmetry Transformations
  35. NeurIPS 2024ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
  36. NeurIPS 2024AirSketch: Generative Motion to Sketch
  37. NeurIPS 2024ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
  38. NeurIPS 2024Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
  39. NeurIPS 2024CRAG - Comprehensive RAG Benchmark
  40. NeurIPS 2024Dynamic Conditional Optimal Transport through Simulation-Free Flows
  41. NeurIPS 2024Estimating the Hallucination Rate of Generative AI
  42. NeurIPS 2024Exogenous Matching: Learning Good Proposals for Tractable Counterfactual Estimation
  43. NeurIPS 2024FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
  44. NeurIPS 2024Fine-grained Control of Generative Data Augmentation in IoT Sensing
  45. NeurIPS 2024Functional Gradient Flows for Constrained Sampling
  46. NeurIPS 2024Generalized Eigenvalue Problems with Generative Priors
  47. NeurIPS 2024Generative Forests
  48. NeurIPS 2024Generative Fractional Diffusion Models
  49. NeurIPS 2024Hamiltonian Score Matching and Generative Flows
  50. NeurIPS 2024Improving the Training of Rectified Flows

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