扩散模型论文趋势 2023–2026
扩散、flow matching 与 score-based 生成
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,900 篇被归入该主题的论文。
主要结论
- 扩散模型论文从 2023 年的 660 篇增长到 2026 年的 2,691 篇，三年间扩大到约 4.1 倍。
- NeurIPS 是发扩散模型论文最多的会议，2023–2026 年共 2,202 篇，占四个会议总量的 32%。
- 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 14 篇增至 2026 年的 163 篇。
- 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 1；同组增长最快的深度学习 · foundation models是 2.5 倍，扩散模型是 4.1 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 327 | 86 | 109 | 138 | 660 |
| 2024 | 520 | 260 | 195 | 496 | 1,471 |
| 2025 | 694 | 487 | 346 | 551 | 2,078 |
| 2026 | 661 | 694 | 728 | 608 | 2,691 |
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 2026$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
- ICML 2026“Do Diffusion Models Dream of Electric Planes?” Discrete and Continuous Simulation-Based Inference for Aircraft Design
- ICLR 2026$\alpha$-DPO: Robust Preference Alignment for Diffusion Models via $\alpha$ Divergence
- CVPR 20262ndMatch Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
- NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
- ICML 2025A First-order Generative Bilevel Optimization Framework for Diffusion Models
- ICLR 2025$\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps
- CVPR 20253DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
- NeurIPS 2024$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
- ICML 2024A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
- ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
- CVPR 2024D^4: Dataset Distillation via Disentangled Diffusion Model
- NeurIPS 20233D molecule generation by denoising voxel grids
- ICML 2023A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification
- ICLR 2023(Certified!!) Adversarial Robustness for Free!
- CVPR 20233D Neural Field Generation Using Triplane Diffusion
- NeurIPS 2026$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
- ICML 2026$\sigma$: Sigmoid Modulation for Ultra High Resolution Diffusion
- ICLR 2026$\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
- CVPR 20263D-LATTE Latent Space 3D Editing from Textual Instructions
全部扩散模型论文
共 661 篇，第 6 / 14 页
- NeurIPS 2026ForesightFlow: Self-Guided Flow Matching for Improving Vision-Language-Action Models
- NeurIPS 2026Free Decompression with Algebraic Spectral Curves
- NeurIPS 2026Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models
- NeurIPS 2026FreeOcc: Decoupling Ego-Motion for Efficient 4D Occupancy Forecasting via Continuous Flow Matching
- NeurIPS 2026FreqCa: Accelerating Image generation and editing via Frequency-Aware Caching
- NeurIPS 2026Frequency‑Aware Flow Matching for Continuous and Consistent Robotic Action Generation
- NeurIPS 2026From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
- NeurIPS 2026From Generation to Restoration: Residual Diffusion for Neural Channel Decoding
- NeurIPS 2026From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
- NeurIPS 2026From Static Geometry to Dynamical Singularity: Detecting Memorization in Diffusion Models via Score Evolution
- NeurIPS 2026Full-Atom Cyclic Peptide Design via Test-Time Scaled Autoregressive Flow Matching
- NeurIPS 2026Full-Sequence Masked Diffusion for Generative Recommendation
- NeurIPS 2026GARDO: Reinforcing Diffusion Models without Reward Hacking
- NeurIPS 2026GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction
- NeurIPS 2026GCD: GCM-consistent Diffusion for Zero-shot Downscaling across Heterogeneous GCMs
- NeurIPS 2026Generalization Dynamics of Linear Diffusion Models
- NeurIPS 2026Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
- NeurIPS 2026Generating Financial Time Series by Matching Random Convolutional Features
- NeurIPS 2026Generating Physically Consistent Molecules with Energy-Based Models
- NeurIPS 2026Generative Active Learning via Bayesian Acquisition for Improving the Efficiency of Synthetic Data
- NeurIPS 2026Generative Actor-Critic with Soft Bridge Policies
- NeurIPS 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
- NeurIPS 2026Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows
- NeurIPS 2026Generative Modeling via Drifting
- NeurIPS 2026GenRec: Knowing Where to Reconstruct and Where to Generate
- NeurIPS 2026GeoMemory: Geometry-Indexed Memory for Long-Horizon Interactive Video Generation
- NeurIPS 2026Geometric Velocity Regularity for Flow Matching on Manifold-Concentrated Data
- NeurIPS 2026Geometry over Density: Few-Shot Cross-Domain OOD Detection
- NeurIPS 2026Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds
- NeurIPS 2026GEOPHYS: The Geometry of Physical Plausibility
- NeurIPS 2026GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories
- NeurIPS 2026gfnx: Fast and Scalable Library for Generative Flow Networks in JAX
- NeurIPS 2026Global Context Guidance for Diffusion Large Language Models
- NeurIPS 2026GlycoGen: Crystallizing Flows for De Novo Glycan Structure Prediction
- NeurIPS 2026GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
- NeurIPS 2026GOLIATH: Gradient Inversion of Tabular Diffusion Models
- NeurIPS 2026GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
- NeurIPS 2026Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
- NeurIPS 2026GRASP: Guided Residual Adapters with Sample-wise Partitioning
- NeurIPS 2026Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation
- NeurIPS 2026Guiding Visual Autoregressive Models through Spectrum Weakening
- NeurIPS 2026GWScore: A structural diversity metric for consistent text-to-image generation
- NeurIPS 2026Harmonic Torsional Diffusion for Flexible Protein-Ligand Docking
- NeurIPS 2026Harnessing Image Diffusion Prior for Photo-Realistic Video Restoration
- NeurIPS 2026Heavy-Tailed Flow Matching via Random Clocks
- NeurIPS 2026HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching
- NeurIPS 2026Hierarchical Variational Policies for Reward-Guided Diffusion
- NeurIPS 2026HilbertGen-3D:Hilbert--Multifractal Conditioning for Topology-Aware 3D Generation
- NeurIPS 2026Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
- NeurIPS 2026Horizontal Diffusion Models: Score-based Generative Modeling on Frame-Connection Geometry
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 查扩散模型在 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": "diffusion-models"}
常见问题
- 2023–2026 年四大会议一共有多少篇扩散模型论文？
- 共 6,900 篇，按年份分别是 2023 年 660 篇、2024 年 1,471 篇、2025 年 2,078 篇、2026 年 2,691 篇。
- NeurIPS 2026 有多少篇扩散模型论文？
- NeurIPS 2026 有 661 篇扩散模型论文，上一届是 694 篇。
- ICLR 2026 有多少篇扩散模型论文？
- ICLR 2026 有 694 篇扩散模型论文，上一届是 487 篇。
- ICML 2026 有多少篇扩散模型论文？
- ICML 2026 有 728 篇扩散模型论文，上一届是 346 篇。
- CVPR 2026 有多少篇扩散模型论文？
- CVPR 2026 有 608 篇扩散模型论文，上一届是 551 篇。
- 哪个会议的扩散模型论文最多？
- NeurIPS，2023–2026 年共 2,202 篇。
「深度学习」下的其他主题
- 深度学习 · generative models and autoencoders 4,314
- 深度学习 · large language models 2,334
- 深度学习 · self supervised learning 1,958
- 深度学习 · graph neural networks 1,648
- 深度学习 · optimization 953
- 深度学习 · representation learning 802
- 深度学习 · probabilistic methods 637
- 深度学习 · foundation models 536
- 深度学习 · causal inference 316
- 深度学习 · transfer learning 197