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 53 / 54 页

  1. NeurIPS 2026Temporal Concentration from Rollout Errors: Implicit Preference Optimization For Text-to-Video Diffusion
  2. NeurIPS 2026Temporal Pair Consistency for Flow Matching
  3. NeurIPS 2026Temporal Selective Exploration for Reinforcement Learning-Guided Continuous-Discrete Flow Matching in 3D Molecular Design
  4. NeurIPS 2026TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured Latents
  5. NeurIPS 2026Tessellations of Semi-Discrete Flow Matching
  6. NeurIPS 2026Test-Time Conditioning with Representation-Aligned Visual Features
  7. NeurIPS 2026Test-time Scaling of Diffusions with Flow Maps
  8. NeurIPS 2026Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
  9. NeurIPS 2026Test-Time Sequential Steering of Diffusion Models via Preconditioned Crank-Nicolson
  10. NeurIPS 2026Tethered Predictive-Inertial Proposals with Objective Verification for Diffusion-Prior Inverse Problems
  11. NeurIPS 2026The balance between feature learning and collapse in generative dynamical systems
  12. NeurIPS 2026The Block Catastrophe of Marginal Calibration in Certified Requirements Traceability
  13. NeurIPS 2026The Design Space of Tri-Modal Masked Diffusion Models
  14. NeurIPS 2026The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
  15. NeurIPS 2026The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
  16. NeurIPS 2026The Quiet Prompt: Erasing Ineffable Styles from Diffusion Models via Concept Leakage-aware Negative Guidance
  17. NeurIPS 2026The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL.
  18. NeurIPS 2026The Score Kalman Filter
  19. NeurIPS 2026TIDE: Trajectory-Aware Watermark Propagation for Text-to-Image Diffusion Models
  20. NeurIPS 2026Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration
  21. NeurIPS 2026TokenRepel: Generating Diverse Image Sets Without Sacrificing Quality
  22. NeurIPS 2026ToLD: Efficient Time Series Forecasting via Tokenized Truncated Latent Diffusion
  23. NeurIPS 2026Too Aligned to be Real: Detecting AI-Generated Images via Cross-modal Alignment Shift
  24. NeurIPS 2026Tools as Continuous Flow for Evolving Agentic Reasoning
  25. NeurIPS 2026TORNADO: Adaptive Latent Stochastic Transport for Calibrated Probabilistic PDE Forecasting
  26. NeurIPS 2026Towards Closing the Autoregressive Gap in Language Modeling via Entropy-Gated Continuous Bitstream Diffusion
  27. NeurIPS 2026Towards more general control of diffusion models using Jeffrey Guidance
  28. NeurIPS 2026TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
  29. NeurIPS 2026Track4D: Representing Dense 3D Tracking for Video Diffusion Models
  30. NeurIPS 2026Train-free Data Poisoning Attack against Retrieval-augmented Diffusion Models
  31. NeurIPS 2026Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
  32. NeurIPS 2026Training Optimal Large Diffusion Language Models
  33. NeurIPS 2026Training-Free Generative Sampling via Moment-Matched Score Smoothing
  34. NeurIPS 2026Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
  35. NeurIPS 2026Trajectory-Consistent Diffusion Policies for Offline Reinforcement Learning
  36. NeurIPS 2026Transforming Image Editors into Video Editors
  37. NeurIPS 2026Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse
  38. NeurIPS 2026Tree-Sliced Orlicz Integral Probability Metric
  39. NeurIPS 2026Tri-Prompting: Controllable Video Generation with Scene, Subject, and Motion Prompts
  40. NeurIPS 2026Trivialized Generative Models on Lie Groups
  41. NeurIPS 2026Trustworthy and Efficient Map-free LiDAR Localization via Scan-Pose Alignment and Flow Matching
  42. NeurIPS 2026TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
  43. NeurIPS 2026Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
  44. NeurIPS 2026Two-Sided Learning in Matching Markets with Interviews
  45. NeurIPS 2026Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
  46. NeurIPS 2026Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
  47. NeurIPS 2026Unaligned Image Guided Denoising via Cross-modal Conditional Flow Matching
  48. NeurIPS 2026Uncertainty Quantification for Large Language Diffusion Models
  49. NeurIPS 2026Understanding diffusion models requires rethinking (again) generalization
  50. NeurIPS 2026UniCustom: Unified Visual Conditioning for Multi-reference Image Generation

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