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 26 / 35 页

  1. ICML 2026UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
  2. ICML 2026Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows
  3. ICML 2026Unifying Deep Stochastic Processes for Image Enhancement
  4. ICML 2026Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration
  5. ICML 2026Unifying Masked Diffusion Models with Various Generation Orders and Beyond
  6. ICML 2026UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis
  7. ICML 2026UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
  8. ICML 2026Unlocking Speech–Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
  9. ICML 2026Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers
  10. ICML 2026Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
  11. ICML 2026Variational Learning for Insertion-based Generation
  12. ICML 2026ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models
  13. ICML 2026WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation
  14. ICML 2026When Attributes Disagree: Gradient Conflict in Image Aesthetic Assessment
  15. ICML 2026Winformer: Transcending Pairwise Similarity for Time-series Generation
  16. ICML 2026WISE: World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
  17. ICML 2026World-Shaper: A Unified Framework for 360° Panoramic Editing
  18. ICML 2026You Don’t Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
  19. NeurIPS 2026$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
  20. NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
  21. NeurIPS 2026$\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics
  22. NeurIPS 2026$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
  23. NeurIPS 2026$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation
  24. NeurIPS 20263D Consistency Tokens
  25. NeurIPS 2026A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models
  26. NeurIPS 2026A Favorable Regime Between ODE and SDE for Few-Step Diffusion Sampling
  27. NeurIPS 2026A Hierarchical World Model for Driving
  28. NeurIPS 2026A Theoretical Analysis of Test-Driven Code Generation
  29. NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
  30. NeurIPS 2026A Unified Image and Video Encoder for Multimodal LLMs
  31. NeurIPS 2026A World Model of Radiologist Reading for Medical Image Representation Learning
  32. NeurIPS 2026A2I: Adjacency-to-Image Structural Encodings for Graph Learning
  33. NeurIPS 2026AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation
  34. NeurIPS 2026Accelerated Image Editing via Consistency-Aware Source Token Pruning
  35. NeurIPS 2026Accelerating Rectified Flow Models via Trajectory-Aware Caching
  36. NeurIPS 2026AdaPCLA: Curriculum Prior Internalization For Long-Tailed Longitudinal EHR Generation
  37. NeurIPS 2026Addressable Memory for Video World Models
  38. NeurIPS 2026Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
  39. NeurIPS 2026AegisFlow: Training-free Non-myopic Path-safe Guided Flow Matching
  40. NeurIPS 2026Affine-Image Propagation for Tight and Scalable $\ell_{2}$ Neural Network Verification
  41. NeurIPS 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
  42. NeurIPS 2026AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
  43. NeurIPS 2026AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
  44. NeurIPS 2026AIR: Rethinking Image-Text Offset Alignment in Multimodal Contrastive Representation Space
  45. NeurIPS 2026Amortized Guidance for Image Inpainting with Pretrained Diffusion Models
  46. NeurIPS 2026AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation
  47. NeurIPS 2026AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding
  48. NeurIPS 2026Anchoring LLM-based Chest X-ray Report Generation via Diffusion Language Planning
  49. NeurIPS 2026Antibody Generation via Redistributed Latent Diffusion
  50. NeurIPS 2026Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning

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