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 661 篇，第 4 / 14 页

  1. NeurIPS 2026Directional Noise Conditioning for Diffusion Models
  2. NeurIPS 2026DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
  3. NeurIPS 2026Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
  4. NeurIPS 2026Discrete Diffusion Playground: A 2D Benchmark for Discrete Generative Models
  5. NeurIPS 2026Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
  6. NeurIPS 2026Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
  7. NeurIPS 2026Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
  8. NeurIPS 2026Disentangled Representation Learning via Flow Matching
  9. NeurIPS 2026Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
  10. NeurIPS 2026Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
  11. NeurIPS 2026DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation
  12. NeurIPS 2026Do Diffusion Models Learn to Generalize Basic Visual Skills?
  13. NeurIPS 2026Don't Match the Noise: Distribution Matching under Unknown Measurement Error with an Audit Sample
  14. NeurIPS 2026Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
  15. NeurIPS 2026Drifting Field Policy: Wasserstein Gradient Flow on Policy Space for Offline-to-Online RL
  16. NeurIPS 2026Drifting Fields are not Conservative
  17. NeurIPS 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
  18. NeurIPS 2026DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
  19. NeurIPS 2026DSSA: Dynamic Sparse Semantic Anchoring for Purifying Protective Perturbations against Diffusion Models
  20. NeurIPS 2026Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
  21. NeurIPS 2026DualDrift: Combining Forward and Reverse Drifts for One-Step Generative Modeling
  22. NeurIPS 2026DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
  23. NeurIPS 2026Dynamic Representation Modeling for Federated Medical Image Domain Generalization
  24. NeurIPS 2026Dynamic Video Generation: Shaping Video Generation Across Time and Space
  25. NeurIPS 2026Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
  26. NeurIPS 2026EDISCO: Equivariant Discrete Diffusion for Euclidean Combinatorial Optimization
  27. NeurIPS 2026Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
  28. NeurIPS 2026Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization
  29. NeurIPS 2026Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
  30. NeurIPS 2026Efficient One-to-many Domain Translation via Diffusive Entropic Optimal Transport
  31. NeurIPS 2026Efficient Retrosynthesis Prediction with Integral Flow Matching and Latent Inversion
  32. NeurIPS 2026EGCA: A Spectral Perspective on Forward Process Design in Diffusion Models
  33. NeurIPS 2026EgoHMP: Achieving Precise Human Motion Prediction in 3D Scenes via Egocentric Cues
  34. NeurIPS 2026Emergence of Distortions in High-Dimensional Guided Diffusion Models
  35. NeurIPS 2026Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers
  36. NeurIPS 2026Enabling Denoising Score Matching Type Training for Manifold Diffusion Model via Momentum and Splitting
  37. NeurIPS 2026Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
  38. NeurIPS 2026Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
  39. NeurIPS 2026End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization
  40. NeurIPS 2026Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
  41. NeurIPS 2026Energy-Tweedie: Score meets Score, Energy meets Energy
  42. NeurIPS 2026Enhanced convergence guarantees of score-based generative models in $\mathcal{W}_2$-distance beyond log-concavity
  43. NeurIPS 2026Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion
  44. NeurIPS 2026Entangled Schrödinger Bridge Matching
  45. NeurIPS 2026EP-Flow: Disordered Crystal Structure Prediction without Site-level Annotation
  46. NeurIPS 2026EpicWorldModel: Exploration-driven Planning with Latent World Models
  47. NeurIPS 2026Epigenomics-Guided Flow Matching for 3D Genome Super-Resolution
  48. NeurIPS 2026Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
  49. NeurIPS 2026Escaping the Curse of Dimensionality in One‑Step Flow-Based Generative Models
  50. NeurIPS 2026ESS-Flow: training-free guidance as Bayesian inference in source space

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