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 694 篇，第 14 / 14 页
- ICLR 2026UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy
- ICLR 2026UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
- ICLR 2026Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Diffusion Diffusion Process
- ICLR 2026Unified In-Context Video Editing
- ICLR 2026Uniform Discrete Diffusion with Metric Path for Video Generation
- ICLR 2026UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modeling
- ICLR 2026UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
- ICLR 2026Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)
- ICLR 2026Universal Multi-Domain Translation via Diffusion Routers
- ICLR 2026Unveiling the Potential of Diffusion Large Language Model in Controllable Generation
- ICLR 2026UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections
- ICLR 2026Value Flows
- ICLR 2026Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation
- ICLR 2026Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
- ICLR 2026VFScale: Intrinsic Reasoning through Verifier-Free Test-time Scalable Diffusion Model
- ICLR 2026Vid2World: Crafting Video Diffusion Models to Interactive World Models
- ICLR 2026Video Unlearning via Low-Rank Refusal Vector
- ICLR 2026Video-GPT via Next Clip Diffusion
- ICLR 2026VINCIE: Unlocking In-context Image Editing from Video
- ICLR 2026ViPO: Visual Preference Optimization at Scale
- ICLR 2026Visual Autoregressive Modeling for Instruction-Guided Image Editing
- ICLR 2026VisualPrompter: Semantic-Aware Prompt Optimization with Visual Feedback for Text-to-Image Synthesis
- ICLR 2026VITA: Vision-to-Action Flow Matching Policy
- ICLR 2026Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
- ICLR 2026VLM-Guided Adaptive Negative Prompting for Creative Generation
- ICLR 2026VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis
- ICLR 2026VMoBA: Mixture-of-Block Attention for Video Diffusion Models
- ICLR 2026VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip
- ICLR 2026W-EDIT: A Wavelet-Based Frequency-Aware Framework for Text-Driven Image Editing
- ICLR 2026Watermarking Diffusion Language Models
- ICLR 2026WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
- ICLR 2026wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
- ICLR 2026Weak-to-Strong Diffusion
- ICLR 2026WFR-FM: Simulation-Free Dynamic Unbalanced Optimal Transport
- ICLR 2026What Exactly Does Guidance Do in Masked Discrete Diffusion Models
- ICLR 2026What Happens Next? Anticipating Future Motion by Generating Point Trajectories
- ICLR 2026When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
- ICLR 2026Why Adversarially Train Diffusion Models?
- ICLR 2026Why We Need New Benchmarks for Local Intrinsic Dimension Estimation
- ICLR 2026Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
- ICLR 2026WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data
- ICLR 2026WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving
- ICLR 2026Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
- ICLR 2026Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers
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