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 2,202 篇，第 30 / 45 页

  1. NeurIPS 2024Constrained Diffusion with Trust Sampling
  2. NeurIPS 2024Constrained Synthesis with Projected Diffusion Models
  3. NeurIPS 2024Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective
  4. NeurIPS 2024COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
  5. NeurIPS 2024COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
  6. NeurIPS 2024Cryptographic Hardness of Score Estimation
  7. NeurIPS 2024Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
  8. NeurIPS 2024D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning
  9. NeurIPS 2024Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
  10. NeurIPS 2024DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
  11. NeurIPS 2024DeBaRA: Denoising-Based 3D Room Arrangement Generation
  12. NeurIPS 2024DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release
  13. NeurIPS 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
  14. NeurIPS 2024DEFT: Efficient Fine-tuning of Diffusion Models by Learning the Generalised $h$-transform
  15. NeurIPS 2024DenoiseRep: Denoising Model for Representation Learning
  16. NeurIPS 2024Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
  17. NeurIPS 2024DePLM: Denoising Protein Language Models for Property Optimization
  18. NeurIPS 2024DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
  19. NeurIPS 2024DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
  20. NeurIPS 2024DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
  21. NeurIPS 2024Differentially Private Graph Diffusion with Applications in Personalized PageRanks
  22. NeurIPS 2024DiffGS: Functional Gaussian Splatting Diffusion
  23. NeurIPS 2024DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
  24. NeurIPS 2024DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
  25. NeurIPS 2024DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
  26. NeurIPS 2024DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
  27. NeurIPS 2024DiffPO: A causal diffusion model for learning distributions of potential outcomes
  28. NeurIPS 2024DiffSF: Diffusion Models for Scene Flow Estimation
  29. NeurIPS 2024DiffuBox: Refining 3D Object Detection with Point Diffusion
  30. NeurIPS 2024DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge
  31. NeurIPS 2024DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
  32. NeurIPS 2024DiffuserLite: Towards Real-time Diffusion Planning
  33. NeurIPS 2024Diffusing Differentiable Representations
  34. NeurIPS 2024Diffusion Actor-Critic with Entropy Regulator
  35. NeurIPS 2024Diffusion for World Modeling: Visual Details Matter in Atari
  36. NeurIPS 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
  37. NeurIPS 2024Diffusion Imitation from Observation
  38. NeurIPS 2024Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
  39. NeurIPS 2024Diffusion Models are Certifiably Robust Classifiers
  40. NeurIPS 2024Diffusion Models With Learned Adaptive Noise
  41. NeurIPS 2024Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
  42. NeurIPS 2024Diffusion PID: Interpreting Diffusion via Partial Information Decomposition
  43. NeurIPS 2024Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning
  44. NeurIPS 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
  45. NeurIPS 2024Diffusion Priors for Variational Likelihood Estimation and Image Denoising
  46. NeurIPS 2024Diffusion Spectral Representation for Reinforcement Learning
  47. NeurIPS 2024Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
  48. NeurIPS 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generation
  49. NeurIPS 2024Diffusion-based Curriculum Reinforcement Learning
  50. NeurIPS 2024Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection

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