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 11 / 14 页
- NeurIPS 2026Robust Diffusion Models via Divergence-Induced Weighted Denoising
- NeurIPS 2026Robust Flow Matching under Target Corruption and Label Noise
- NeurIPS 2026Robust Graph Diffusion Model
- NeurIPS 2026Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
- NeurIPS 2026Rotations on Latent Hyperspheres: a Geometry-Aware Guiding Framework for Diffusion Models
- NeurIPS 2026RotVLA: Rotational Latent Action for Vision-Language-Action Model
- NeurIPS 2026RxDiff: Discrete Diffusion for Medication Recommendation with Inference-Time Safety Control
- NeurIPS 2026S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation
- NeurIPS 2026Safe Few-Step Generation via Velocity Editing
- NeurIPS 2026Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
- NeurIPS 2026Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
- NeurIPS 2026SARA: Step-Adaptive Rank Adjustment for Diffusion Inference Acceleration
- NeurIPS 2026Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models
- NeurIPS 2026scShapeBench: Discovering geometry from high dimensional scRNAseq data
- NeurIPS 2026SCULPT: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis.
- NeurIPS 2026SDFlow: Similarity-Driven Flow Matching for Time Series Generation
- NeurIPS 2026Search-Augmented Masked Diffusion Models for Constrained Generation
- NeurIPS 2026Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
- NeurIPS 2026Seed-Your-Motion: Householder Orthogonal Noise for Motion-Controllable Video Diffusion Models
- NeurIPS 2026Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
- NeurIPS 2026SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
- NeurIPS 2026Self-Cleaning Diffusion Models
- NeurIPS 2026SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
- NeurIPS 2026SemISP: Semantic-Consistent Diffusion for Cross-Camera RAW-to-sRGB Generation
- NeurIPS 2026SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
- NeurIPS 2026Show Me What You Don’t Know: Efficient Sampling from Invariant Sets for Model Validation
- NeurIPS 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues
- NeurIPS 2026SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language Models
- NeurIPS 2026SiliciclasticReservoirs: A Million-Reservoir Dataset and Flow-Matching Foundation Model for 3D Siliciclastic Reservoir Generation
- NeurIPS 2026SimSD: Simple Speculative Decoding in Diffusion Language Models
- NeurIPS 2026Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty
- NeurIPS 2026Single Shot HDR Recovery via a Video Diffusion Prior
- NeurIPS 2026SkipSR: Faster Super-Resolution with Token Skipping
- NeurIPS 2026Smoothed Score Queries and the Complexity of Sampling
- NeurIPS 2026Space Group Conditional Flow Matching
- NeurIPS 2026Sparse Biological Features Reveal Early Functional Commitment in Diffusion Protein Language Models
- NeurIPS 2026Sparse blind deconvolution via thresholded Wirtinger flow
- NeurIPS 2026Sparsely Supervised Diffusion
- NeurIPS 2026Spatially-Grounded Long Video Generation with Self Geometry Forcing
- NeurIPS 2026Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling
- NeurIPS 2026Spectral Progressive Diffusion for Efficient Image and Video Generation
- NeurIPS 2026Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views
- NeurIPS 2026SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants
- NeurIPS 2026ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
- NeurIPS 2026Stability and Diversity of Networked Self-Consuming Generative Ecosystems
- NeurIPS 2026StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation
- NeurIPS 2026StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching
- NeurIPS 2026StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining
- NeurIPS 2026State Augmented Flows
- NeurIPS 2026Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
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