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

共 2,078 篇,第 23 / 42 页

  1. ICML 2025Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models
  2. ICML 2025Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts
  3. ICML 2025DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples
  4. ICML 2025Differentiable Solver Search for Fast Diffusion Sampling
  5. ICML 2025DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra
  6. ICML 2025Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
  7. ICML 2025Diffusion Adversarial Post-Training for One-Step Video Generation
  8. ICML 2025Diffusion Counterfactual Generation with Semantic Abduction
  9. ICML 2025Diffusion Instruction Tuning
  10. ICML 2025Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation
  11. ICML 2025Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors
  12. ICML 2025Diffusion on Language Model Encodings for Protein Sequence Generation
  13. ICML 2025Diffusion Sampling Correction via Approximately 10 Parameters
  14. ICML 2025Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
  15. ICML 2025DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
  16. ICML 2025DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
  17. ICML 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
  18. ICML 2025Distillation of Discrete Diffusion through Dimensional Correlations
  19. ICML 2025Distributional Diffusion Models with Scoring Rules
  20. ICML 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
  21. ICML 2025Diversified Flow Matching with Translation Identifiability
  22. ICML 2025DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis
  23. ICML 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
  24. ICML 2025Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space
  25. ICML 2025DRAG: Data Reconstruction Attack using Guided Diffusion
  26. ICML 2025DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
  27. ICML 2025DS-VLM: Diffusion Supervision Vision Language Model
  28. ICML 2025DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger Bridge
  29. ICML 2025EasyInv: Toward Fast and Better DDIM Inversion
  30. ICML 2025EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
  31. ICML 2025EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery
  32. ICML 2025Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
  33. ICML 2025Effective and Efficient Masked Image Generation Models
  34. ICML 2025Efficient Diffusion Models for Symmetric Manifolds
  35. ICML 2025Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
  36. ICML 2025Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
  37. ICML 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
  38. ICML 2025Efficient Online Reinforcement Learning for Diffusion Policy
  39. ICML 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
  40. ICML 2025Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers
  41. ICML 2025Emotional Face-to-Speech
  42. ICML 2025Energy-Based Flow Matching for Generating 3D Molecular Structure
  43. ICML 2025Ensemble Distribution Distillation via Flow Matching
  44. ICML 2025Epsilon-VAE: Denoising as Visual Decoding
  45. ICML 2025EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
  46. ICML 2025Ergodic Generative Flows
  47. ICML 2025ETTA: Elucidating the Design Space of Text-to-Audio Models
  48. ICML 2025Event-Customized Image Generation
  49. ICML 2025Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
  50. ICML 2025Exponential Family Variational Flow Matching for Tabular Data 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