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 944 篇，第 11 / 19 页

  1. ICLR 2025Information Theoretic Text-to-Image Alignment
  2. ICLR 2025InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
  3. ICLR 2025Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
  4. ICLR 2025InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling
  5. ICLR 2025Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks
  6. ICLR 2025IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts
  7. ICLR 2025IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
  8. ICLR 2025IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
  9. ICLR 2025IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
  10. ICLR 2025JetFormer: An autoregressive generative model of raw images and text
  11. ICLR 2025LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning
  12. ICLR 2025Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint
  13. ICLR 2025Learning General-purpose Biomedical Volume Representations using Randomized Synthesis
  14. ICLR 2025Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
  15. ICLR 2025Learning Mask Invariant Mutual Information for Masked Image Modeling
  16. ICLR 2025Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models
  17. ICLR 2025Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
  18. ICLR 2025Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
  19. ICLR 2025LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
  20. ICLR 2025Local Patterns Generalize Better for Novel Anomalies
  21. ICLR 2025Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
  22. ICLR 2025Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation
  23. ICLR 2025MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
  24. ICLR 2025MagicPIG: LSH Sampling for Efficient LLM Generation
  25. ICLR 2025MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds
  26. ICLR 2025MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval
  27. ICLR 2025Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
  28. ICLR 2025Measuring And Improving Engagement of Text-to-Image Generation Models
  29. ICLR 2025Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
  30. ICLR 2025MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
  31. ICLR 2025Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid
  32. ICLR 2025Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models
  33. ICLR 2025MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
  34. ICLR 2025Morphing Tokens Draw Strong Masked Image Models
  35. ICLR 2025MotionClone: Training-Free Motion Cloning for Controllable Video Generation
  36. ICLR 2025MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
  37. ICLR 2025Multi-Reward as Condition for Instruction-based Image Editing
  38. ICLR 2025Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
  39. ICLR 2025Natural Language Inference Improves Compositionality in Vision-Language Models
  40. ICLR 2025Neural networks on Symmetric Spaces of Noncompact Type
  41. ICLR 2025Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models
  42. ICLR 2025OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes
  43. ICLR 2025OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
  44. ICLR 2025OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
  45. ICLR 2025On Disentangled Training for Nonlinear Transform in Learned Image Compression
  46. ICLR 2025One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
  47. ICLR 2025One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
  48. ICLR 2025OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
  49. ICLR 2025Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model
  50. ICLR 2025PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction

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