扩散模型论文趋势 2023–2026

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。

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 487 篇，第 10 / 10 页

451. ICLR 2025Trajectory attention for fine-grained video motion control
452. ICLR 2025Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
453. ICLR 2025Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers
454. ICLR 2025Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy
455. ICLR 2025Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
456. ICLR 2025Truncated Consistency Models
457. ICLR 2025Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
458. ICLR 2025TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation
459. ICLR 2025U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models
460. ICLR 2025UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition
461. ICLR 2025Underdamped Diffusion Bridges with Applications to Sampling
462. ICLR 2025UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models
463. ICLR 2025Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers
464. ICLR 2025UniGEM: A Unified Approach to Generation and Property Prediction for Molecules
465. ICLR 2025UniRestore3D: A Scalable Framework For General Shape Restoration
466. ICLR 2025Unlocking Guidance for Discrete State-Space Diffusion and Flow Models
467. ICLR 2025Unlocking Point Processes through Point Set Diffusion
468. ICLR 2025Variational Diffusion Posterior Sampling with Midpoint Guidance
469. ICLR 2025VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
470. ICLR 2025VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning
471. ICLR 2025Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
472. ICLR 2025ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler
473. ICLR 2025VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing
474. ICLR 2025ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
475. ICLR 2025VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
476. ICLR 2025Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models
477. ICLR 2025VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
478. ICLR 2025Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion Models
479. ICLR 2025Wavelet Diffusion Neural Operator
480. ICLR 2025What Makes a Good Diffusion Planner for Decision Making?
481. ICLR 2025What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
482. ICLR 2025What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
483. ICLR 2025X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios
484. ICLR 2025You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
485. ICLR 2025Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
486. ICLR 2025ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning
487. ICLR 2025Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

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。