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 6,899 篇，第 14 / 138 页

  1. ICLR 2026AUHead: Realistic Emotional Talking Head Generation via Action Units Control
  2. ICLR 2026Aurora: Towards Universal Generative Multimodal Time Series Forecasting
  3. ICLR 2026Autoregressive Visual Decoding from EEG Signals
  4. ICLR 2026Autoregressive-based Progressive Coding for Ultra-Low Bitrate Image Compression
  5. ICLR 2026Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
  6. ICLR 2026Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models
  7. ICLR 2026Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes
  8. ICLR 2026Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
  9. ICLR 2026Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
  10. ICLR 2026Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model
  11. ICLR 2026Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion Models
  12. ICLR 2026BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
  13. ICLR 2026BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
  14. ICLR 2026BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
  15. ICLR 2026Block-wise Adaptive Caching for Accelerating Diffusion Policy
  16. ICLR 2026Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer
  17. ICLR 2026Branched Schrödinger Bridge Matching
  18. ICLR 2026BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
  19. ICLR 2026BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
  20. ICLR 2026Bridging Degradation Discrimination and Generation for Universal Image Restoration
  21. ICLR 2026Bridging Successor Measure and Online Policy Learning with Flow Matching-Based Representations
  22. ICLR 2026Bridging the Distribution Gap to Harness Pretrained Diffusion Priors for Super-Resolution
  23. ICLR 2026Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
  24. ICLR 2026Bures-Wasserstein Flow Matching for Graph Generation
  25. ICLR 2026BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
  26. ICLR 2026Captain Cinema: Towards Short Movie Generation
  27. ICLR 2026Capturing Visual Environment Structure Correlates with Control Performance
  28. ICLR 2026CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models
  29. ICLR 2026Carré du champ flow matching: better quality-generalisation tradeoff in generative models
  30. ICLR 2026CASteer: Cross-Attention Steering for Controllable Concept Erasure
  31. ICLR 2026Causal Score Conditioning for Multi-Resolution Latent Systems
  32. ICLR 2026CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators
  33. ICLR 2026CheckMate! Watermarking Graph Diffusion Models in Polynomial Time
  34. ICLR 2026CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models
  35. ICLR 2026CL-DPS: A Contrastive Learning Approach to Blind Nonlinear Inverse Problem Solving via Diffusion Posterior Sampling
  36. ICLR 2026Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
  37. ICLR 2026Clustering by Denoising: Latent plug-and-play diffusion for single-cell embeddings
  38. ICLR 2026CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow-Map Models
  39. ICLR 2026Co-occurring Associated REtained concepts in Diffusion Unlearning
  40. ICLR 2026CO3: CONTRASTING CONCEPTS COMPOSE BETTER
  41. ICLR 2026CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer
  42. ICLR 2026CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
  43. ICLR 2026CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation
  44. ICLR 2026ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes
  45. ICLR 2026Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
  46. ICLR 2026Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
  47. ICLR 2026Composition of Memory Experts for Diffusion World Models
  48. ICLR 2026Compositional amortized inference for large-scale hierarchical Bayesian models
  49. ICLR 2026Compositional Diffusion with Guided search for Long-Horizon Planning
  50. ICLR 2026Compositional Visual Planning via Inference-Time Diffusion Scaling

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