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 6 / 9 页

  1. NeurIPS 2025SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories
  2. NeurIPS 2025Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models
  3. NeurIPS 2025Sequence Modeling with Spectral Mean Flows
  4. NeurIPS 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
  5. NeurIPS 2025STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
  6. NeurIPS 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
  7. NeurIPS 2025Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
  8. NeurIPS 2025When Models Don’t Collapse: On the Consistency of Iterative MLE
  9. CVPR 2024All Rivers Run to the Sea: Private Learning with Asymmetric Flows
  10. CVPR 2024Boosting Flow-based Generative Super-Resolution Models via Learned Prior
  11. CVPR 2024CityDreamer: Compositional Generative Model of Unbounded 3D Cities
  12. CVPR 2024DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
  13. CVPR 2024Distributionally Generative Augmentation for Fair Facial Attribute Classification
  14. CVPR 2024DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
  15. CVPR 2024En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data
  16. CVPR 2024G3DR: Generative 3D Reconstruction in ImageNet
  17. CVPR 2024Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing
  18. CVPR 2024Generative Multimodal Models are In-Context Learners
  19. CVPR 2024Generative Powers of Ten
  20. CVPR 2024Generative Quanta Color Imaging
  21. CVPR 2024Generative Unlearning for Any Identity
  22. CVPR 2024Learning Large-Factor EM Image Super-Resolution with Generative Priors
  23. CVPR 2024MaskPLAN: Masked Generative Layout Planning from Partial Input
  24. CVPR 2024MMM: Generative Masked Motion Model
  25. CVPR 2024Mosaic-SDF for 3D Generative Models
  26. CVPR 2024NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows
  27. CVPR 2024NeRFiller: Completing Scenes via Generative 3D Inpainting
  28. CVPR 2024Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling
  29. CVPR 2024Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata
  30. CVPR 2024PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
  31. CVPR 2024Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection
  32. CVPR 2024Would Deep Generative Models Amplify Bias in Future Models?
  33. ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
  34. ICLR 2024Bespoke Solvers for Generative Flow Models
  35. ICLR 2024Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
  36. ICLR 2024Emu: Generative Pretraining in Multimodality
  37. ICLR 2024Fast and unified path gradient estimators for normalizing flows
  38. ICLR 2024GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
  39. ICLR 2024Generative Sliced MMD Flows with Riesz Kernels
  40. ICLR 2024Idempotent Generative Network
  41. ICLR 2024Kernelised Normalising Flows
  42. ICLR 2024Lifting Architectural Constraints of Injective Flows
  43. ICLR 2024Light Schrödinger Bridge
  44. ICLR 2024LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
  45. ICLR 2024Modelling complex vector drawings with stroke-clouds
  46. ICLR 2024On the Stability of Iterative Retraining of Generative Models on their own Data
  47. ICLR 2024Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
  48. ICLR 2024SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
  49. ICLR 2024sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
  50. ICLR 2024The Generative AI Paradox: “What It Can Create, It May Not Understand”

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