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 607 篇，第 8 / 13 页

  1. CVPR 2026MoCha End-to-End Video Character Replacement without Structural Guidance
  2. CVPR 2026MoCoDiff A Controllable Autoregressive Diffusion Model for Expressive Motion Generation
  3. CVPR 2026MOS Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification
  4. CVPR 2026MotionEnhancer Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models
  5. CVPR 2026MotionHiFlow Text-to-Motion via Hierarchical Flow Matching
  6. CVPR 2026MR. Illuminate Zero-Shot Low-Light Image Enhancement with Diffusion Prior
  7. CVPR 2026Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion
  8. CVPR 2026MusicInfuser Making Video Diffusion Listen and Dance
  9. CVPR 2026MUST Modality-Specific Representation-Aware Transformer for Diffusion-Enhanced Survival Prediction with Missing
  10. CVPR 2026MV2UV Generating High-quality UV Texture Maps with Multiview Prompts
  11. CVPR 2026NanoSD Edge Efficient Foundation Model for Real Time Image Restoration
  12. CVPR 2026NaTex Seamless Texture Generation as Latent Color Diffusion
  13. CVPR 2026Native and Compact Structured Latents for 3D Generation
  14. CVPR 2026NEC-Diff Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme
  15. CVPR 2026Neighbor GRPO Contrastive ODE Policy Optimization Aligns Flow Models
  16. CVPR 2026Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
  17. CVPR 2026NeuroFlow Toward Unified Visual Encoding and Decoding from Neural Activity
  18. CVPR 2026NexusFlow Unifying Disparate Tasks under Partial Supervision via Invertible Flow
  19. CVPR 2026NIL No-data Imitation Learning
  20. CVPR 2026No Way To Steal My Face Proactive Defense Against Identity-Preserving
  21. CVPR 2026Occluded Human Body Capture with Frequency Domain Denoising Prior
  22. CVPR 2026OMGTex One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance
  23. CVPR 2026Omni2Sound Towards Unified Video-Text-to-Audio Generation
  24. CVPR 2026One Model Many Budgets Elastic Latent Interfaces for Diffusion Transformers
  25. CVPR 2026One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution
  26. CVPR 2026One-to-All Animation Alignment-Free Character Animation and Image Pose Transfer
  27. CVPR 2026OntoAug Rethinking Generative Data Augmentation via Ontology Guidance
  28. CVPR 2026OpenDPR Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for
  29. CVPR 2026Optical Flow Matching Reframing Optical Flow as Continuous Transport Dynamics
  30. CVPR 2026OrthoFuse Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion
  31. CVPR 2026Otil Accelerating Diffusion Model Inference via Communication-Efficient Multi-GPU Parallelism
  32. CVPR 2026Outlier-Robust Diffusion Solvers for Inverse Problems
  33. CVPR 2026PAD-Hand Physics-Aware Diffusion for Hand Motion Recovery
  34. CVPR 2026Pantheon360 Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion
  35. CVPR 2026Parallelised Differentiable Straightest Geodesics for 3D Meshes
  36. CVPR 2026ParaUni Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical
  37. CVPR 2026PartDiffuser Part-wise 3D Mesh Generation via Discrete Diffusion
  38. CVPR 2026PatchScene Patch-based Voxel Diffusion Model for Large-Scale Scene Completion
  39. CVPR 2026Personalized Federated Training of Diffusion Models with Privacy Guarantees
  40. CVPR 2026PG-VTON Single-Pass Training-Free Virtual Try-On via Patch-Guided Reference Alignment
  41. CVPR 2026PHAC Promptable Human Amodal Completion
  42. CVPR 2026Phased DMD Few-step Distribution Matching Distillation via Score Matching within
  43. CVPR 2026PhyCo Learning Controllable Physical Priors for Generative Motion
  44. CVPR 2026PhyOceanCast Global Ocean Forecasting with Physics-Informed Diffusion
  45. CVPR 2026PhysGen Physically Grounded 3D Shape Generation for Industrial Design
  46. CVPR 2026Physical Simulator In-the-Loop Video Generation
  47. CVPR 2026Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction
  48. CVPR 2026Pixel Motion Diffusion is What We Need for Robot Control
  49. CVPR 2026PixelDiT Pixel Diffusion Transformers for Image Generation
  50. CVPR 2026PixelRush Ultra-Fast Training-Free High-Resolution Image Generation via One-step 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