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 2,690 篇，第 52 / 54 页

  1. NeurIPS 2026Self-Cleaning Diffusion Models
  2. NeurIPS 2026SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
  3. NeurIPS 2026SemISP: Semantic-Consistent Diffusion for Cross-Camera RAW-to-sRGB Generation
  4. NeurIPS 2026SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
  5. NeurIPS 2026Show Me What You Don’t Know: Efficient Sampling from Invariant Sets for Model Validation
  6. NeurIPS 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues
  7. NeurIPS 2026SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language Models
  8. NeurIPS 2026SiliciclasticReservoirs: A Million-Reservoir Dataset and Flow-Matching Foundation Model for 3D Siliciclastic Reservoir Generation
  9. NeurIPS 2026SimSD: Simple Speculative Decoding in Diffusion Language Models
  10. NeurIPS 2026Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty
  11. NeurIPS 2026Single Shot HDR Recovery via a Video Diffusion Prior
  12. NeurIPS 2026SkipSR: Faster Super-Resolution with Token Skipping
  13. NeurIPS 2026Smoothed Score Queries and the Complexity of Sampling
  14. NeurIPS 2026Space Group Conditional Flow Matching
  15. NeurIPS 2026Sparse Biological Features Reveal Early Functional Commitment in Diffusion Protein Language Models
  16. NeurIPS 2026Sparse blind deconvolution via thresholded Wirtinger flow
  17. NeurIPS 2026Sparsely Supervised Diffusion
  18. NeurIPS 2026Spatially-Grounded Long Video Generation with Self Geometry Forcing
  19. NeurIPS 2026Spectral Adaptive Repositioning for Flow-Based Single-Cell Perturbation Modeling
  20. NeurIPS 2026Spectral Progressive Diffusion for Efficient Image and Video Generation
  21. NeurIPS 2026Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views
  22. NeurIPS 2026SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants
  23. NeurIPS 2026ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
  24. NeurIPS 2026Stability and Diversity of Networked Self-Consuming Generative Ecosystems
  25. NeurIPS 2026StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation
  26. NeurIPS 2026StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching
  27. NeurIPS 2026StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining
  28. NeurIPS 2026State Augmented Flows
  29. NeurIPS 2026Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
  30. NeurIPS 2026SteerVTE: Seamless Video Text Editing with Style and Glyph Control
  31. NeurIPS 2026Stein Transport for Generative Modeling
  32. NeurIPS 2026Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference
  33. NeurIPS 2026Sticky Jump Diffusions: A Unifying Framework for Discrete, Continuous, and Hybrid Diffusion
  34. NeurIPS 2026Stitched Value Model for Diffusion Alignment
  35. NeurIPS 2026StitchEdit: Stitching Depth Priors into Image Editors via Per-Layer Gradient Probing
  36. NeurIPS 2026Stochastic Heat Diffusion Models
  37. NeurIPS 2026Stochastic Interpolants via Conditional Dependent Coupling
  38. NeurIPS 2026Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram Synthesis
  39. NeurIPS 2026Structured Coupling for Flow Matching
  40. NeurIPS 2026Structured Masked Diffusion for Joint Multiuser Decoding
  41. NeurIPS 2026StyleRoute: Diffusion Style Transfer via Regional Routing and Conflict-aware Projection
  42. NeurIPS 2026Support Before Frequency in Discrete Diffusion
  43. NeurIPS 2026Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow Models
  44. NeurIPS 2026TailDiff: Elicitable Tail-Guided Diffusion for Risk-Sensitive Generation
  45. NeurIPS 2026Taming Generative Co-Folding Prior for Molecular Docking with Diffusion Bridge
  46. NeurIPS 2026Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling
  47. NeurIPS 2026TaxaAdapter: Scaling Fine-grained Species Image Generation To the Tree of Life
  48. NeurIPS 2026Temperature-Regulated Stochastic Sampling for Diffusion-Based High-Quality Molecular Generation
  49. NeurIPS 2026Tempered Guided Diffusion
  50. NeurIPS 2026Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models

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