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 15 / 42 页

  1. ICLR 2025EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing
  2. ICLR 2025EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
  3. ICLR 2025EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing
  4. ICLR 2025Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
  5. ICLR 2025Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching
  6. ICLR 2025Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models
  7. ICLR 2025EG4D: Explicit Generation of 4D Object without Score Distillation
  8. ICLR 2025EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos
  9. ICLR 2025EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal Conditioning
  10. ICLR 2025Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
  11. ICLR 2025Elliptic Loss Regularization
  12. ICLR 2025Elucidating the Preconditioning in Consistency Distillation
  13. ICLR 2025End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler
  14. ICLR 2025Energy-Based Diffusion Language Models for Text Generation
  15. ICLR 2025Energy-Weighted Flow Matching for Offline Reinforcement Learning
  16. ICLR 2025Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions
  17. ICLR 2025Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds
  18. ICLR 2025Ensembling Diffusion Models via Adaptive Feature Aggregation
  19. ICLR 2025Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models
  20. ICLR 2025Erasing Concept Combination from Text-to-Image Diffusion Model
  21. ICLR 2025ET-SEED: EFFICIENT TRAJECTORY-LEVEL SE(3) EQUIVARIANT DIFFUSION POLICY
  22. ICLR 2025Exploring Local Memorization in Diffusion Models via Bright Ending Attention
  23. ICLR 2025FaceShot: Bring Any Character into Life
  24. ICLR 2025Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
  25. ICLR 2025Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
  26. ICLR 2025Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
  27. ICLR 2025Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
  28. ICLR 2025FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
  29. ICLR 2025Feedback Schrödinger Bridge Matching
  30. ICLR 2025Field-DiT: Diffusion Transformer on Unified Video, 3D, and Game Field Generation
  31. ICLR 2025FIG: Flow with Interpolant Guidance for Linear Inverse Problems
  32. ICLR 2025Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
  33. ICLR 2025Flow matching achieves almost minimax optimal convergence
  34. ICLR 2025Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
  35. ICLR 2025Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective
  36. ICLR 2025FlowDec: A flow-based full-band general audio codec with high perceptual quality
  37. ICLR 2025Framer: Interactive Frame Interpolation
  38. ICLR 2025FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
  39. ICLR 2025Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation
  40. ICLR 2025Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs
  41. ICLR 2025FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
  42. ICLR 2025GameGen-X: Interactive Open-world Game Video Generation
  43. ICLR 2025GANDALF: Generative AttentioN based Data Augmentation and predictive modeLing Framework for personalized cancer treatment
  44. ICLR 2025GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation
  45. ICLR 2025GDrag:Towards General-Purpose Interactive Editing with Anti-ambiguity Point Diffusion
  46. ICLR 2025Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
  47. ICLR 2025Generalization through variance: how noise shapes inductive biases in diffusion models
  48. ICLR 2025Generalized Consistency Trajectory Models for Image Manipulation
  49. ICLR 2025Generating Graphs via Spectral Diffusion
  50. ICLR 2025Generating Physical Dynamics under Priors

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