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 8 / 14 页

  1. NeurIPS 2026Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
  2. NeurIPS 2026LLM Is a Good Conditioner: End-to-End Sign Language Video Generation with VQ-Diffusion
  3. NeurIPS 2026Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
  4. NeurIPS 2026Locality-Controlled OOD Guidance for Robust Regulatory DNA Sequence Design
  5. NeurIPS 2026Localizing Concepts in Visual Autoregressive Models
  6. NeurIPS 2026Looped Diffusion Language Models
  7. NeurIPS 2026LoRAtorio: An intrinsic approach to LoRA Skill Composition
  8. NeurIPS 2026LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
  9. NeurIPS 2026Machine Unlearning in Diffusion LLMs
  10. NeurIPS 2026MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
  11. NeurIPS 2026Mamba Flow Matching Neural Processes: Linear-Time Inference for Irregularly Observed Spatial Fields
  12. NeurIPS 2026Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
  13. NeurIPS 2026Manifold-Aligned Adversarial Perturbation for Anti-Customization under Diffusion-based Purification
  14. NeurIPS 2026ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts
  15. NeurIPS 2026Map-Guided Caching: A Global Perspective for Efficient Diffusion Transformer
  16. NeurIPS 2026Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking
  17. NeurIPS 2026Mask-Conditioned Gradient Masking for Fine-Tuning Mixture-of-Experts Diffusion Language Models
  18. NeurIPS 2026Masked Generative Pretraining Improves Cross-Dataset Transfer in Pixel-Space Diffusion
  19. NeurIPS 2026MaterialsSaddles: 34 Million Transition States and a Flow-Matching Saddle-Point Predictor for Materials
  20. NeurIPS 2026MCM-DM: Towards Better Spatio-Temporal Event Representation Learning via Discrete Morse Theory
  21. NeurIPS 2026Mean-Field Parallel Decoding for Discrete Diffusion Language Models
  22. NeurIPS 2026Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
  23. NeurIPS 2026Metric Depth Estimation from Arbitrarily Degraded Low-Resolution Depth Prompts
  24. NeurIPS 2026Metropolis-Adjusted Diffusion Models
  25. NeurIPS 2026MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow Matching
  26. NeurIPS 2026MiCo: Microstructure-Consistent Flow Matching for Diffusion MRI Angular Super-Resolution
  27. NeurIPS 2026MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation
  28. NeurIPS 2026MissPath-FM: Flow Matching with Structured Priors for Partially Observed Time Series
  29. NeurIPS 2026Mitigating Compounding Errors in Online Reinforcement Learning via Optimal Transport Regularized Flow Matching
  30. NeurIPS 2026Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
  31. NeurIPS 2026Mix-Opt: Mixed Optimization for Memory-Efficient Personalization of Text-to-Image Diffusion Models
  32. NeurIPS 2026Mixed-Curvature Geometric Latent Diffusion Model for Graph Generation
  33. NeurIPS 2026MobileWan: Closing the Quality Gap for Mobile Video Diffusion
  34. NeurIPS 2026MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
  35. NeurIPS 2026MonarchRT: Efficient Attention for Real-Time Video Generation
  36. NeurIPS 2026MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
  37. NeurIPS 2026MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer
  38. NeurIPS 2026Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
  39. NeurIPS 2026Multilevel and Sequential Monte Carlo for Training-Free Diffusion Guidance
  40. NeurIPS 2026MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
  41. NeurIPS 2026My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization
  42. NeurIPS 2026NAGO: Noise-Aware Generative Operator via Flow Matching
  43. NeurIPS 2026Nahual: A Sequence Model for Language and Atoms
  44. NeurIPS 2026NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation
  45. NeurIPS 2026NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
  46. NeurIPS 2026Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
  47. NeurIPS 2026Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries
  48. NeurIPS 2026Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
  49. NeurIPS 2026Normalizing Flows are Capable Trajectory Planners
  50. NeurIPS 2026Normalizing Trajectory 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