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 2,078 篇，第 40 / 42 页

  1. NeurIPS 2025SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
  2. NeurIPS 2025SPMDM: Enhancing Masked Diffusion Models through Simplifing Sampling Path
  3. NeurIPS 2025SPRO: Improving Image Generation via Self-Play
  4. NeurIPS 2025SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
  5. NeurIPS 2025SSIMBaD: Sigma Scaling with SSIM-Guided Balanced Diffusion for AnimeFace Colorization
  6. NeurIPS 2025Stable Matching with Ties: Approximation Ratios and Learning
  7. NeurIPS 2025Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
  8. NeurIPS 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
  9. NeurIPS 2025STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
  10. NeurIPS 2025State Size Independent Statistical Error Bound for Discrete Diffusion Models
  11. NeurIPS 2025State-Covering Trajectory Stitching for Diffusion Planners
  12. NeurIPS 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Models
  13. NeurIPS 2025STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
  14. NeurIPS 2025Steering Generative Models with Experimental Data for Protein Fitness Optimization
  15. NeurIPS 2025STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
  16. NeurIPS 2025Stochastic Process Learning via Operator Flow Matching
  17. NeurIPS 2025Straight-Line Diffusion Model for Efficient 3D Molecular Generation
  18. NeurIPS 2025Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching
  19. NeurIPS 2025Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning
  20. NeurIPS 2025StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
  21. NeurIPS 2025StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
  22. NeurIPS 2025SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios
  23. NeurIPS 2025SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
  24. NeurIPS 2025Synthetic-powered predictive inference
  25. NeurIPS 2025System-Embedded Diffusion Bridge Models
  26. NeurIPS 2025T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
  27. NeurIPS 2025T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
  28. NeurIPS 2025Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
  29. NeurIPS 2025TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics
  30. NeurIPS 2025TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
  31. NeurIPS 2025TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer
  32. NeurIPS 2025Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization
  33. NeurIPS 2025Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models
  34. NeurIPS 2025Test-Time Scaling of Diffusion Models via Noise Trajectory Search
  35. NeurIPS 2025Text to Sketch Generation with Multi-Styles
  36. NeurIPS 2025Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders
  37. NeurIPS 2025Theoretical Benefit and Limitation of Diffusion Language Model
  38. NeurIPS 2025ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation
  39. NeurIPS 2025Time-Embedded Algorithm Unrolling for Computational MRI
  40. NeurIPS 2025TimeWak: Temporal Chained-Hashing Watermark for Time Series Data
  41. NeurIPS 2025Token Perturbation Guidance for Diffusion Models
  42. NeurIPS 2025Topology-aware Graph Diffusion Model with Persistent Homology
  43. NeurIPS 2025Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
  44. NeurIPS 2025Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction
  45. NeurIPS 2025Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations
  46. NeurIPS 2025Towards foundational LiDAR world models with efficient latent flow matching
  47. NeurIPS 2025Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge
  48. NeurIPS 2025Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
  49. NeurIPS 2025Towards Reliable Identification of Diffusion-based Image Manipulations
  50. NeurIPS 2025Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

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