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 4 / 13 页

  1. ICML 2026ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning
  2. ICML 2026Rethinking 3D Shape Generation: Diffusion over Superquadrics
  3. ICML 2026Rethinking Generative Image Pretraining: How Far Are We From Scaling Up Next-Pixel Prediction?
  4. ICML 2026Riemannian MeanFlow for One-Step Generation on Manifolds
  5. ICML 2026RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
  6. ICML 2026Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
  7. ICML 2026RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
  8. ICML 2026S-Quant: Rethinking Weight Quantization with Seed-Based Generation
  9. ICML 2026Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
  10. ICML 2026SAMT: Generating Structured Avatar Meshes and Textures from a Single Image
  11. ICML 2026Scalable Single-Cell Gene Expression Generation with Latent Diffusion Models
  12. ICML 2026ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation
  13. ICML 2026ScalingAR: Scaling Confidence for Autoregressive Image Generation
  14. ICML 2026Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
  15. ICML 2026Semantic Granularity Navigation in Image Editing
  16. ICML 2026Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
  17. ICML 2026SEPS: Semantic-Enhanced Patch Slimming Framework for Fine-Grained Cross-Modal Alignment
  18. ICML 2026Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought
  19. ICML 2026Show, Don't Tell: Morphing Latent Reasoning into Image Generation
  20. ICML 2026SJD-SV: Speculative Jacobi Decoding with Semantics Verification for Autoregressive Image Generation
  21. ICML 2026Skipping the Zeros in Diffusion Models for Sparse Data Generation
  22. ICML 2026Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
  23. ICML 2026Spectrally-Guided Diffusion Noise Schedules
  24. ICML 2026Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
  25. ICML 2026SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion
  26. ICML 2026SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks
  27. ICML 2026SSDCN: Spatial-Spectral Dual-Clustering-based Network for Hyperspectral Image Super-resolution
  28. ICML 2026STD-Former: Image-Conditioned Texture Dictionary Encoding with Sparse Topological Supervision for Texture Recognition
  29. ICML 2026Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions
  30. ICML 2026Stop When Further Reasoning Won’t Help: Attention-State Adaptive Generation in Reasoning Models
  31. ICML 2026StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation
  32. ICML 2026StructMAR: Structure-Aware Masked Autoregression for Explicit Layout Alignment in Text-to-Image Generation
  33. ICML 2026StyleDistillation: A New Insight of Image Style Enables Personalized Aesthetic Manipulation
  34. ICML 2026SuperHype: Hypergraph Generation via Graph-Superposition Decomposition
  35. ICML 2026SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
  36. ICML 2026SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment
  37. ICML 2026Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors
  38. ICML 2026TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment
  39. ICML 2026Taylor-Gaussians-Flow: Towards Non-uniform Motion for Novel View Synthesis from Monocular Video
  40. ICML 2026TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
  41. ICML 2026TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation
  42. ICML 2026Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space
  43. ICML 2026TextAtlas5M: A Large-Scale Dataset for Long Text Image Generation
  44. ICML 2026TextMesh4D: Zero-shot Text-to-4D Mesh Generation
  45. ICML 2026TFTF: Training-Free Targeted Flow for Conditional Sampling
  46. ICML 2026The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution
  47. ICML 2026The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
  48. ICML 2026The Safety-Aware Denoiser for Text Diffusion Models
  49. ICML 2026The Velocity Deficit: Initial Energy Injection for Flow Matching
  50. ICML 2026TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity

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