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

每年论文数

各会议论文数

按年份和会议统计

扩散模型论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202332786109138660
20245202601954961,471
20256944873465512,078
20266616947286082,691

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

全部扩散模型论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 2,690 篇，第 22 / 54 页

  1. ICLR 2026On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
  2. ICLR 2026On the Design of One-step Diffusion via Shortcutting Flow Paths
  3. ICLR 2026On the Interpolation Effect of Score Smoothing in Diffusion Models
  4. ICLR 2026On the Reasoning Abilities of Masked Diffusion Language Models
  5. ICLR 2026One step further with Monte-Carlo sampler to guide diffusion better
  6. ICLR 2026One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs
  7. ICLR 2026One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning
  8. ICLR 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image
  9. ICLR 2026Overshoot and Shrinkage in Classifier-Free Guidance: From Theory to Practice
  10. ICLR 2026OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction
  11. ICLR 2026P3D: Highly Scalable 3D Neural Surrogates for Physics Simulations with Global Context
  12. ICLR 2026PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models
  13. ICLR 2026Pallatom-Ligand: an All-Atom Diffusion Model for Designing Ligand-Binding Proteins
  14. ICLR 2026Parallel Multimodal Diffusion Language Models for Thinking-Aware Editing and Generation
  15. ICLR 2026Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
  16. ICLR 2026ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
  17. ICLR 2026Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
  18. ICLR 2026Partition Generative Modeling: Masked Modeling Without Masks
  19. ICLR 2026Patronus: Interpretable Diffusion Models with Prototypes
  20. ICLR 2026PepTri: Tri-Guided All-Atom Diffusion for Peptide Design via Physics, Evolution, and Mutual Information
  21. ICLR 2026Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection
  22. ICLR 2026Physics vs Distributions: Pareto Optimal Flow Matching with Physics Constraints
  23. ICLR 2026Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems
  24. ICLR 2026pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
  25. ICLR 2026PI-Light: Physics-Inspired Diffusion for Full-Image Relighting
  26. ICLR 2026PICS: Pairwise Image Compositing with Spatial Interactions
  27. ICLR 2026PINFDiT: Energy-Based Physics-Informed Diffusion Transformers for General-purpose Time Series Tasks
  28. ICLR 2026Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation
  29. ICLR 2026Pixel-Perfect Puppetry: Precision-Guided Enhancement for Face Image and Video Editing
  30. ICLR 2026PixNerd: Pixel Neural Field Diffusion
  31. ICLR 2026Planned Diffusion
  32. ICLR 2026Planner Aware Path Learning in Diffusion Language Models Training
  33. ICLR 2026Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization
  34. ICLR 2026Point Prompting: Counterfactual Tracking with Video Diffusion Models
  35. ICLR 2026PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning
  36. ICLR 2026Polynomial Convergence of Riemannian Diffusion Models
  37. ICLR 2026PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
  38. ICLR 2026Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
  39. ICLR 2026Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective
  40. ICLR 2026PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference
  41. ICLR 2026PRISM: Controllable Diffusion for Compound Image Restoration with Scientific Fidelity
  42. ICLR 2026PRO-MOF: Policy Optimization with Universal Atomistic Models for Controllable MOF Generation
  43. ICLR 2026Product-Quantised Image Representation for High-Quality Image Synthesis
  44. ICLR 2026Projected Coupled Diffusion for Test-Time Constrained Joint Generation
  45. ICLR 2026ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
  46. ICLR 2026Provable Separations between Memorization and Generalization in Diffusion Models
  47. ICLR 2026Proximal Diffusion Neural Sampler
  48. ICLR 2026Purrception: Variational Flow Matching for Vector-Quantized Image Generation
  49. ICLR 2026Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
  50. ICLR 2026Pyramid Patchification Flow for Visual Generation

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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