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 36 / 42 页

  1. NeurIPS 2025Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation
  2. NeurIPS 2025MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
  3. NeurIPS 2025Mitigating Occlusions in Virtual Try-On via A Simple-Yet-Effective Mask-Free Framework
  4. NeurIPS 2025Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models
  5. NeurIPS 2025MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning
  6. NeurIPS 2025MoCha: Towards Movie-Grade Talking Character Generation
  7. NeurIPS 2025Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow
  8. NeurIPS 2025MoleBridge: Synthetic Space Projecting with Discrete Markov Bridges
  9. NeurIPS 2025Momentum Multi-Marginal Schrödinger Bridge Matching
  10. NeurIPS 2025More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
  11. NeurIPS 2025MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
  12. NeurIPS 2025MotionBind: Multi-Modal Human Motion Alignment for Retrieval, Recognition, and Generation
  13. NeurIPS 2025MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
  14. NeurIPS 2025MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
  15. NeurIPS 2025MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans
  16. NeurIPS 2025Multitask Learning with Stochastic Interpolants
  17. NeurIPS 2025Multivariate Latent Recalibration for Conditional Normalizing Flows
  18. NeurIPS 2025Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
  19. NeurIPS 2025Native-Resolution Image Synthesis
  20. NeurIPS 2025Neural Entropy
  21. NeurIPS 2025Neural Hamiltonian Diffusions for Modeling Structured Geometric Dynamics
  22. NeurIPS 2025Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction
  23. NeurIPS 2025Neural-Driven Image Editing
  24. NeurIPS 2025NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models
  25. NeurIPS 2025NeuroRenderedFake: A Challenging Benchmark to Detect Fake Images Generated by Advanced Neural Rendering Methods
  26. NeurIPS 2025Neurosymbolic Diffusion Models
  27. NeurIPS 2025Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
  28. NeurIPS 2025No Object Is an Island: Enhancing 3D Semantic Segmentation Generalization with Diffusion Models
  29. NeurIPS 2025Noise Consistency Training: A Native Approach for One-step Generator in Learning Additional Controls
  30. NeurIPS 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
  31. NeurIPS 2025Noise Matters: Optimizing Matching Noise for Diffusion Classifiers
  32. NeurIPS 2025Noisy Multi-Label Learning through Co-Occurrence-Aware Diffusion
  33. NeurIPS 2025Non-equilibrium Annealed Adjoint Sampler
  34. NeurIPS 2025Non-Markovian Discrete Diffusion with Causal Language Models
  35. NeurIPS 2025Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
  36. NeurIPS 2025Normalizing Flows are Capable Models for Continuous Control
  37. NeurIPS 2025Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
  38. NeurIPS 2025NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
  39. NeurIPS 2025NUTS: Eddy-Robust Reconstruction of Surface Ocean Nutrients via Two-Scale Modeling
  40. NeurIPS 2025ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation
  41. NeurIPS 2025OCTDiff: Bridged Diffusion Model for Portable OCT Super-Resolution and Enhancement
  42. NeurIPS 2025OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
  43. NeurIPS 2025OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data
  44. NeurIPS 2025Omnidirectional 3D Scene Reconstruction from Single Image
  45. NeurIPS 2025OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers
  46. NeurIPS 2025OmniTry: Virtual Try-On Anything without Masks
  47. NeurIPS 2025OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions
  48. NeurIPS 2025On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
  49. NeurIPS 2025On Inductive Biases That Enable Generalization in Diffusion Transformers
  50. NeurIPS 2025On scalable and efficient training of diffusion samplers

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