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 1,216 篇，第 18 / 25 页

  1. ICML 2024Position: Towards Implicit Prompt For Text-To-Image Models
  2. ICML 2024Position: What makes an image realistic?
  3. ICML 2024Post-hoc Part-Prototype Networks
  4. ICML 2024Probabilistic Generating Circuits - Demystified
  5. ICML 2024Prompt Sketching for Large Language Models
  6. ICML 2024Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
  7. ICML 2024Protein Conformation Generation via Force-Guided SE(3) Diffusion Models
  8. ICML 2024Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency
  9. ICML 2024Quantum Implicit Neural Representations
  10. ICML 2024RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
  11. ICML 2024Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion
  12. ICML 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractions
  13. ICML 2024Rejuvenating image-GPT as Strong Visual Representation Learners
  14. ICML 2024Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration
  15. ICML 2024Retrieval-Augmented Score Distillation for Text-to-3D Generation
  16. ICML 2024Revisiting Context Aggregation for Image Matting
  17. ICML 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
  18. ICML 2024Robust Universal Adversarial Perturbations
  19. ICML 2024Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
  20. ICML 2024Scalable Pre-training of Large Autoregressive Image Models
  21. ICML 2024Scale-Free Image Keypoints Using Differentiable Persistent Homology
  22. ICML 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
  23. ICML 2024Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
  24. ICML 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
  25. ICML 2024See More Details: Efficient Image Super-Resolution by Experts Mining
  26. ICML 2024Self-Infilling Code Generation
  27. ICML 2024Semantic-Aware Human Object Interaction Image Generation
  28. ICML 2024Sharpness-Aware Data Generation for Zero-shot Quantization
  29. ICML 2024Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once
  30. ICML 2024Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis
  31. ICML 2024Stochastic positional embeddings improve masked image modeling
  32. ICML 2024StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis
  33. ICML 2024Successor Features for Efficient Multi-Subject Controlled Text Generation
  34. ICML 2024Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
  35. ICML 2024Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
  36. ICML 2024Switchable Decision: Dynamic Neural Generation Networks
  37. ICML 2024Test-Time Degradation Adaptation for Open-Set Image Restoration
  38. ICML 2024The Perception-Robustness Tradeoff in Deterministic Image Restoration
  39. ICML 2024The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
  40. ICML 2024Time Weaver: A Conditional Time Series Generation Model
  41. ICML 2024To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
  42. ICML 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
  43. ICML 2024Unifying Image Processing as Visual Prompting Question Answering
  44. ICML 2024Unsupervised Episode Generation for Graph Meta-learning
  45. ICML 2024UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers
  46. ICML 2024UPOCR: Towards Unified Pixel-Level OCR Interface
  47. ICML 2024WAVES: Benchmarking the Robustness of Image Watermarks
  48. ICML 2024X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation
  49. NeurIPS 2024$\textit{Bifr\"ost}$: 3D-Aware Image Compositing with Language Instructions
  50. NeurIPS 20242DQuant: Low-bit Post-Training Quantization for Image Super-Resolution

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