图像生成论文趋势 2023–2026

文生图与图像合成

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,184 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

图像生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202317011874418780
20243181991565431,216
20254302781476121,467
20264533492306891,721

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

全部图像生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,721 篇，第 28 / 35 页

  1. NeurIPS 2026Contextual Flow Matching for High-quality Visual Content Generation
  2. NeurIPS 2026Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
  3. NeurIPS 2026Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
  4. NeurIPS 2026Continuous Personalized Diffusion Model via Spinor-Component Forward Geometry
  5. NeurIPS 2026Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
  6. NeurIPS 2026Contrastive Identification and Generation in the Limit
  7. NeurIPS 2026Controllable Road Marking Generation
  8. NeurIPS 2026CoScan: Multi-Scale Content-Adaptive Space-Filling Scans for Causal State-Space Image Restoration
  9. NeurIPS 2026Coupled Guidance for Flow Matching
  10. NeurIPS 2026Coupling Models for One-Step Discrete Generation
  11. NeurIPS 2026CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
  12. NeurIPS 2026CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait Generation
  13. NeurIPS 2026CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation
  14. NeurIPS 2026DARE: Dual-Level Adversarial Learning with Domain-Aware Regularization for Whole Slide Image Classification
  15. NeurIPS 2026Dataset Collections: Challenges of Large-Scale Data Aggregation in 3D Medical Image Datasets
  16. NeurIPS 2026Debiased Counterfactual Generation via Flow Matching from Observations
  17. NeurIPS 2026Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
  18. NeurIPS 2026DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection
  19. NeurIPS 2026DeepfakeGenome: Toward Next-Generation Deepfake Attribution
  20. NeurIPS 2026DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models
  21. NeurIPS 2026Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
  22. NeurIPS 2026Denoising Time Matters: Diverse Generation in Diffusion Language Models
  23. NeurIPS 2026DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
  24. NeurIPS 2026Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation
  25. NeurIPS 2026Diffusion Language Models Can Approximate Optimal Infilling Lengths Implicitly
  26. NeurIPS 2026Diffusion Models without Classifier-free Guidance
  27. NeurIPS 2026DiPhon: Diffusion on Graphons for Scalable Graph Generation
  28. NeurIPS 2026Directional Noise Conditioning for Diffusion Models
  29. NeurIPS 2026DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
  30. NeurIPS 2026Discovering Unseen Degradations to Adapt Open-World Image Restoration
  31. NeurIPS 2026Discrete Stochastic Localization for Non-autoregressive Generation
  32. NeurIPS 2026Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
  33. NeurIPS 2026Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
  34. NeurIPS 2026Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing
  35. NeurIPS 2026Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
  36. NeurIPS 2026Drifting Fields are not Conservative
  37. NeurIPS 2026DriftWeight: Repulsive Drift in Mean-Flow Space for Neural Network Weight Generation
  38. NeurIPS 2026DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
  39. NeurIPS 2026Duality Models: An Embarrassingly Simple One-step Generation Paradigm
  40. NeurIPS 2026Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
  41. NeurIPS 2026Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
  42. NeurIPS 2026DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time
  43. NeurIPS 2026EditFlowSR: Revisable Expression Generation for Symbolic Regression
  44. NeurIPS 2026EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth
  45. NeurIPS 2026Efficient Image Synthesis with Sphere Latent Encoder
  46. NeurIPS 2026Elastic Representations via Hyperbolic Geometry
  47. NeurIPS 2026ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
  48. NeurIPS 2026Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
  49. NeurIPS 2026Ensembling Language Models with Sequential Monte Carlo
  50. NeurIPS 2026Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization

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 查图像生成在 CVPR 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": "image-generation"}

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图像生成论文？
共 5,184 篇，按年份分别是 2023 年 780 篇、2024 年 1,216 篇、2025 年 1,467 篇、2026 年 1,721 篇。
NeurIPS 2026 有多少篇图像生成论文？
NeurIPS 2026 有 453 篇图像生成论文，上一届是 430 篇。
ICLR 2026 有多少篇图像生成论文？
ICLR 2026 有 349 篇图像生成论文，上一届是 278 篇。
ICML 2026 有多少篇图像生成论文？
ICML 2026 有 230 篇图像生成论文，上一届是 147 篇。
CVPR 2026 有多少篇图像生成论文？
CVPR 2026 有 689 篇图像生成论文，上一届是 612 篇。
哪个会议的图像生成论文最多？
CVPR，2023–2026 年共 2,262 篇。

「计算机视觉」下的其他主题