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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 18 | 17 | 26 | 12 | 73 |
| 2024 | 29 | 18 | 27 | 24 | 98 |
| 2025 | 37 | 35 | 25 | 22 | 119 |
| 2026 | 46 | 37 | 32 | 24 | 139 |
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 35 篇，第 1 / 1 页
- ICLR 2025Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
- ICLR 2025Boosting Latent Diffusion with Perceptual Objectives
- ICLR 2025Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
- ICLR 2025COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation
- ICLR 2025CoInD: Enabling Logical Compositions in Diffusion Models
- ICLR 2025Consistency Models Made Easy
- ICLR 2025CONTRA: Conformal Prediction Region via Normalizing Flow Transformation
- ICLR 2025CryoGEN: Generative Energy-based Models for Cryogenic Electron Tomography Reconstruction
- ICLR 2025cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM
- ICLR 2025Data Unlearning in Diffusion Models
- ICLR 2025Deep MMD Gradient Flow without adversarial training
- ICLR 2025Designing Mechanical Meta-Materials by Learning Equivariant Flows
- ICLR 2025Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete Generators
- ICLR 2025FaceShot: Bring Any Character into Life
- ICLR 2025Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
- ICLR 2025Flow matching achieves almost minimax optimal convergence
- ICLR 2025Generative Flows on Synthetic Pathway for Drug Design
- ICLR 2025GMValuator: Similarity-based Data Valuation for Generative Models
- ICLR 2025Heavy-Tailed Diffusion Models
- ICLR 2025Injective flows for star-like manifolds
- ICLR 2025Latent Bayesian Optimization via Autoregressive Normalizing Flows
- ICLR 2025Multilevel Generative Samplers for Investigating Critical Phenomena
- ICLR 2025MuPT: A Generative Symbolic Music Pretrained Transformer
- ICLR 2025Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry
- ICLR 2025No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
- ICLR 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generation
- ICLR 2025NRGBoost: Energy-Based Generative Boosted Trees
- ICLR 2025ParetoFlow: Guided Flows in Multi-Objective Optimization
- ICLR 2025PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation
- ICLR 2025Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?
- ICLR 2025Restructuring Vector Quantization with the Rotation Trick
- ICLR 2025Think while You Generate: Discrete Diffusion with Planned Denoising
- ICLR 2025Topological Schrödinger Bridge Matching
- ICLR 2025Towards Hierarchical Rectified Flow
- ICLR 2025Truncated Consistency Models
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"}
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。