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 117 / 138 页

  1. NeurIPS 2024CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
  2. NeurIPS 2024Coherent 3D Scene Diffusion From a Single RGB Image
  3. NeurIPS 2024Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
  4. NeurIPS 2024CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
  5. NeurIPS 2024Compositional 3D-aware Video Generation with LLM Director
  6. NeurIPS 2024Conditional Controllable Image Fusion
  7. NeurIPS 2024Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
  8. NeurIPS 2024Conditional Synthesis of 3D Molecules with Time Correction Sampler
  9. NeurIPS 2024Conditioning non-linear and infinite-dimensional diffusion processes
  10. NeurIPS 2024Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data
  11. NeurIPS 2024Consistency Diffusion Bridge Models
  12. NeurIPS 2024Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
  13. NeurIPS 2024Constant Acceleration Flow
  14. NeurIPS 2024Constrained Diffusion Models via Dual Training
  15. NeurIPS 2024Constrained Diffusion with Trust Sampling
  16. NeurIPS 2024Constrained Synthesis with Projected Diffusion Models
  17. NeurIPS 2024Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective
  18. NeurIPS 2024COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
  19. NeurIPS 2024COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
  20. NeurIPS 2024Cryptographic Hardness of Score Estimation
  21. NeurIPS 2024Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
  22. NeurIPS 2024D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning
  23. NeurIPS 2024Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
  24. NeurIPS 2024DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
  25. NeurIPS 2024DeBaRA: Denoising-Based 3D Room Arrangement Generation
  26. NeurIPS 2024DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release
  27. NeurIPS 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
  28. NeurIPS 2024DEFT: Efficient Fine-tuning of Diffusion Models by Learning the Generalised $h$-transform
  29. NeurIPS 2024DenoiseRep: Denoising Model for Representation Learning
  30. NeurIPS 2024Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
  31. NeurIPS 2024DePLM: Denoising Protein Language Models for Property Optimization
  32. NeurIPS 2024DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
  33. NeurIPS 2024DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
  34. NeurIPS 2024DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
  35. NeurIPS 2024Differentially Private Graph Diffusion with Applications in Personalized PageRanks
  36. NeurIPS 2024DiffGS: Functional Gaussian Splatting Diffusion
  37. NeurIPS 2024DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
  38. NeurIPS 2024DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
  39. NeurIPS 2024DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
  40. NeurIPS 2024DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
  41. NeurIPS 2024DiffPO: A causal diffusion model for learning distributions of potential outcomes
  42. NeurIPS 2024DiffSF: Diffusion Models for Scene Flow Estimation
  43. NeurIPS 2024DiffuBox: Refining 3D Object Detection with Point Diffusion
  44. NeurIPS 2024DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge
  45. NeurIPS 2024DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
  46. NeurIPS 2024DiffuserLite: Towards Real-time Diffusion Planning
  47. NeurIPS 2024Diffusing Differentiable Representations
  48. NeurIPS 2024Diffusion Actor-Critic with Entropy Regulator
  49. NeurIPS 2024Diffusion for World Modeling: Visual Details Matter in Atari
  50. NeurIPS 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence 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