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 607 篇，第 11 / 13 页

  1. ICML 2024Revisiting Context Aggregation for Image Matting
  2. ICML 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
  3. ICML 2024Robust Universal Adversarial Perturbations
  4. ICML 2024Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
  5. ICML 2024Scalable Pre-training of Large Autoregressive Image Models
  6. ICML 2024Scale-Free Image Keypoints Using Differentiable Persistent Homology
  7. ICML 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
  8. ICML 2024Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
  9. ICML 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
  10. ICML 2024See More Details: Efficient Image Super-Resolution by Experts Mining
  11. ICML 2024Self-Infilling Code Generation
  12. ICML 2024Semantic-Aware Human Object Interaction Image Generation
  13. ICML 2024Sharpness-Aware Data Generation for Zero-shot Quantization
  14. ICML 2024Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once
  15. ICML 2024Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis
  16. ICML 2024Stochastic positional embeddings improve masked image modeling
  17. ICML 2024StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis
  18. ICML 2024Successor Features for Efficient Multi-Subject Controlled Text Generation
  19. ICML 2024Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
  20. ICML 2024Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
  21. ICML 2024Switchable Decision: Dynamic Neural Generation Networks
  22. ICML 2024Test-Time Degradation Adaptation for Open-Set Image Restoration
  23. ICML 2024The Perception-Robustness Tradeoff in Deterministic Image Restoration
  24. ICML 2024The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
  25. ICML 2024Time Weaver: A Conditional Time Series Generation Model
  26. ICML 2024To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
  27. ICML 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
  28. ICML 2024Unifying Image Processing as Visual Prompting Question Answering
  29. ICML 2024Unsupervised Episode Generation for Graph Meta-learning
  30. ICML 2024UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers
  31. ICML 2024UPOCR: Towards Unified Pixel-Level OCR Interface
  32. ICML 2024WAVES: Benchmarking the Robustness of Image Watermarks
  33. ICML 2024X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation
  34. ICML 2023A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
  35. ICML 2023Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
  36. ICML 2023Attributing Image Generative Models using Latent Fingerprints
  37. ICML 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
  38. ICML 2023Autoregressive Diffusion Model for Graph Generation
  39. ICML 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
  40. ICML 2023CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
  41. ICML 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
  42. ICML 2023CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language Models
  43. ICML 2023Coder Reviewer Reranking for Code Generation
  44. ICML 2023Composer: Creative and Controllable Image Synthesis with Composable Conditions
  45. ICML 2023Controlled Text Generation with Natural Language Instructions
  46. ICML 2023Data Representations' Study of Latent Image Manifolds
  47. ICML 2023Deep Latent State Space Models for Time-Series Generation
  48. ICML 2023Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations
  49. ICML 2023Dirichlet Diffusion Score Model for Biological Sequence Generation
  50. ICML 2023Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference

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