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 17 / 138 页

  1. ICLR 2026Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation
  2. ICLR 2026Dual-Path Condition Alignment for Diffusion Transformers
  3. ICLR 2026Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction
  4. ICLR 2026Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
  5. ICLR 2026Dynamic Classifier-Free Diffusion Guidance via Online Feedback
  6. ICLR 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
  7. ICLR 2026EA3D: Event-Augmented 3D Diffusion for Generalizable Novel View Synthesis
  8. ICLR 2026EasyCreator: Empowering 4D Creation through Video Inpainting
  9. ICLR 2026EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
  10. ICLR 2026EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model
  11. ICLR 2026EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer
  12. ICLR 2026Edit-Based Flow Matching for Temporal Point Processes
  13. ICLR 2026Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators
  14. ICLR 2026Efficient Zero-shot Inpainting with Decoupled Diffusion Guidance
  15. ICLR 2026EffiVMT: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning
  16. ICLR 2026EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations
  17. ICLR 2026EigenScore: OOD Detection using Posterior Covariance in Diffusion Models
  18. ICLR 2026Eliminating VAE for Fast and High-Resolution Generative Detail Restoration
  19. ICLR 2026Enhancing Diffusion-Based Sampling with Molecular Collective Variables
  20. ICLR 2026Entering the Era of Discrete Diffusion Models: A Benchmark for Schrödinger Bridges and Entropic Optimal Transport
  21. ICLR 2026EnvSocial-Diff: A Diffusion-Based Crowd Simulation Model with Environmental Conditioning and Individual-Group Interaction
  22. ICLR 2026Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance
  23. ICLR 2026ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
  24. ICLR 2026ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
  25. ICLR 2026Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
  26. ICLR 2026Event-T2M: Event-level Conditioning for Complex Text-to-Motion Synthesis
  27. ICLR 2026Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model
  28. ICLR 2026Exploratory Diffusion Model for Unsupervised Reinforcement Learning
  29. ICLR 2026Exploring Cross-Modal Flows for Few-Shot Learning
  30. ICLR 2026Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection
  31. ICLR 2026Exploring the Design Space of Transition Matching
  32. ICLR 2026EXPO: Stable Reinforcement Learning with Expressive Policies
  33. ICLR 2026FACM: Flow-Anchored Consistency Models
  34. ICLR 2026Faithfulness Under the Distribution: A New Look at Attribution Evaluation
  35. ICLR 2026FALCON: Few-step Accurate Likelihoods for Continuous Flows
  36. ICLR 2026FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
  37. ICLR 2026Fast-dLLM v2: Efficient Block-Diffusion LLM
  38. ICLR 2026Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
  39. ICLR 2026FAST‑DIPS: Adjoint‑Free Analytic Steps and Hard‑Constrained Likelihood Correction for Diffusion‑Prior Inverse Problems
  40. ICLR 2026FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference
  41. ICLR 2026FastVMT: Eliminating Redundancy in Video Motion Transfer
  42. ICLR 2026FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring
  43. ICLR 2026Fine-Tuning Diffusion Models via Intermediate Distribution Shaping
  44. ICLR 2026Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
  45. ICLR 2026FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
  46. ICLR 2026FlashWorld: High-quality 3D Scene Generation within Seconds
  47. ICLR 2026FlexProtein: Joint Sequence and Structure Pretraining for Protein Modeling
  48. ICLR 2026floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
  49. ICLR 2026Flow Actor-Critic for Offline Reinforcement Learning
  50. ICLR 2026Flow Along the $K$-Amplitude for Generative Modeling

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