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 6,899 篇，第 19 / 138 页

  1. ICLR 2026Generative View Stitching
  2. ICLR 2026Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
  3. ICLR 2026Geometric Graph Neural Diffusion for Stable Molecular Dynamics
  4. ICLR 2026Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers
  5. ICLR 2026Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
  6. ICLR 2026Geometry-aware Policy Imitation
  7. ICLR 2026GGBall: Graph Generative Model on Poincaré Ball
  8. ICLR 2026GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
  9. ICLR 2026GLASS Flows: Efficient Inference for Reward Alignment of Flow and Diffusion Models
  10. ICLR 2026Global and Local Topology-Aware Graph Generation via Dual Conditioning Diffusion
  11. ICLR 2026GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent System
  12. ICLR 2026GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies
  13. ICLR 2026Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models
  14. ICLR 2026Graph Diffusion Transformers are In-Context Molecular Designers
  15. ICLR 2026Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
  16. ICLR 2026Guidance Watermarking for Diffusion Models
  17. ICLR 2026Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
  18. ICLR 2026H$^3$DP: Triply‑Hierarchical Diffusion Policy for Visuomotor Learning
  19. ICLR 2026Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer
  20. ICLR 2026Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
  21. ICLR 2026HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion Acceleration
  22. ICLR 2026Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion
  23. ICLR 2026Hierarchical Semantic-Acoustic Modeling via Semi-Discrete Residual Representations for Expressive End-to-End Speech Synthesis
  24. ICLR 2026Hierarchy Decoding: A Training-free Parallel Decoding Strategy for Diffusion Large Language Models
  25. ICLR 2026High-dimensional Mean-Field Games by Particle-based Flow Matching
  26. ICLR 2026HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models
  27. ICLR 2026HOG-Diff: Higher-Order Guided Diffusion for Graph Generation
  28. ICLR 2026Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
  29. ICLR 2026Hot Fuzz: Temperature-Tunable Composition of Diffusion models with Fuzzy Logic
  30. ICLR 2026HOTA: Hamiltonian framework for Optimal Transport Advection
  31. ICLR 2026Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
  32. ICLR 2026I-DRUID: Layout to image generation via instance-disentangled representation and unpaired data
  33. ICLR 2026IC-Custom: Diverse Image Customization via In-Context Learning
  34. ICLR 2026ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly Detection
  35. ICLR 2026iFusion: Integrating Dynamic Interest Streams via Diffusion Model for Click-Through Rate Prediction
  36. ICLR 2026Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
  37. ICLR 2026Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis
  38. ICLR 2026Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution
  39. ICLR 2026Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment
  40. ICLR 2026Improving 2D Diffusion Models for 3D Medical Imaging with Inter‑Slice Consistent Stochasticity
  41. ICLR 2026Improving Autoregressive Video Modeling with History Understanding
  42. ICLR 2026Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
  43. ICLR 2026Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation
  44. ICLR 2026Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
  45. ICLR 2026Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
  46. ICLR 2026Incomplete Data, Complete Dynamics: A Diffusion Approach
  47. ICLR 2026Inference-time scaling of diffusion models through classical search
  48. ICLR 2026Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design
  49. ICLR 2026InfoBridge: Mutual Information estimation via Bridge Matching
  50. ICLR 2026Information Estimation with Discrete Diffusion

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