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 1,378 篇，第 17 / 28 页

  1. ICML 2025Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors
  2. ICML 2025Diffusion on Language Model Encodings for Protein Sequence Generation
  3. ICML 2025Diffusion Sampling Correction via Approximately 10 Parameters
  4. ICML 2025Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
  5. ICML 2025DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
  6. ICML 2025DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
  7. ICML 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
  8. ICML 2025Distillation of Discrete Diffusion through Dimensional Correlations
  9. ICML 2025Distributional Diffusion Models with Scoring Rules
  10. ICML 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
  11. ICML 2025Diversified Flow Matching with Translation Identifiability
  12. ICML 2025DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis
  13. ICML 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
  14. ICML 2025Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space
  15. ICML 2025DRAG: Data Reconstruction Attack using Guided Diffusion
  16. ICML 2025DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
  17. ICML 2025DS-VLM: Diffusion Supervision Vision Language Model
  18. ICML 2025DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger Bridge
  19. ICML 2025EasyInv: Toward Fast and Better DDIM Inversion
  20. ICML 2025EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
  21. ICML 2025EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery
  22. ICML 2025Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
  23. ICML 2025Effective and Efficient Masked Image Generation Models
  24. ICML 2025Efficient Diffusion Models for Symmetric Manifolds
  25. ICML 2025Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
  26. ICML 2025Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
  27. ICML 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
  28. ICML 2025Efficient Online Reinforcement Learning for Diffusion Policy
  29. ICML 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
  30. ICML 2025Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers
  31. ICML 2025Emotional Face-to-Speech
  32. ICML 2025Energy-Based Flow Matching for Generating 3D Molecular Structure
  33. ICML 2025Ensemble Distribution Distillation via Flow Matching
  34. ICML 2025Epsilon-VAE: Denoising as Visual Decoding
  35. ICML 2025EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
  36. ICML 2025Ergodic Generative Flows
  37. ICML 2025ETTA: Elucidating the Design Space of Text-to-Audio Models
  38. ICML 2025Event-Customized Image Generation
  39. ICML 2025Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
  40. ICML 2025Exponential Family Variational Flow Matching for Tabular Data Generation
  41. ICML 2025Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization
  42. ICML 2025Falcon: Fast Visuomotor Policies via Partial Denoising
  43. ICML 2025Fast Video Generation with Sliding Tile Attention
  44. ICML 2025Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization
  45. ICML 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
  46. ICML 2025Finite-Time Analysis of Discrete-Time Stochastic Interpolants
  47. ICML 2025Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
  48. ICML 2025FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation
  49. ICML 2025Flexibility-conditioned protein structure design with flow matching
  50. ICML 2025FlexiClip: Locality-Preserving Free-Form Character Animation

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