图像生成论文趋势 2023–2026

主要结论

• 图像生成论文从 2023 年的 780 篇增长到 2026 年的 1,721 篇，三年间扩大到约 2.2 倍。
• CVPR 是发图像生成论文最多的会议，2023–2026 年共 2,262 篇，占四个会议总量的 44%。
• 交叉方向里涨得最快的是深度学习 · generative models and autoencoders：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 150 篇。
• 在「计算机视觉」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的视频理解是 2.6 倍，图像生成是 2.2 倍。

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

• NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026Klein Hyperbolic Metric Learning
• ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
• CVPR 2026Adaptive Learned Image Compression with Graph Neural Networks
• NeurIPS 2025Alchemist: Turning Public Text-to-Image Data into Generative Gold
• ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
• ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
• CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
• NeurIPS 2024Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
• ICML 2024Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
• ICLR 2024AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
• CVPR 2024DemoCaricature: Democratising Caricature Generation with a Rough Sketch
• NeurIPS 20234D Panoptic Scene Graph Generation
• ICML 2023Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
• ICLR 2023Accurate Image Restoration with Attention Retractable Transformer
• CVPR 20233D GAN Inversion With Facial Symmetry Prior
• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026Noisy-Channel Minimum Bayes Risk Decoding
• ICLR 2026All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
• CVPR 2026AIMDepth Asymmetric Image-Event Mamba for Monocular Depth Estimation

全部图像生成论文

共 607 篇，第 1 / 13 页

1. ICML 2026A Flat Vocabulary or a Rich Hierarchy? Re-introducing Intrinsic Structure Transforms the Autoregressive Image Generation
2. ICML 2026AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation
3. ICML 2026ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
4. ICML 2026Addressing Semantic Blind Spots in Text-to-SQL via Component Pre-generation and AST Matching Rewards
5. ICML 2026AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms
6. ICML 2026AlignVid: Taming Visual Dominance via Training-Free Attention Modulation in Text-guided Image-to-Video Generation
7. ICML 2026Anomaly-Preference Image Generation
8. ICML 2026AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors
9. ICML 2026AnyCanvas: Potential Field Guidance for Training-Free Spatial Control in Text-to-Image Diffusion
10. ICML 2026Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
11. ICML 2026AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters
12. ICML 2026Autoregressive Image Generation with Masked Bit Modeling
13. ICML 2026Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
14. ICML 2026Backward SDE–Based Diffusion for Physics-Constrained Generation
15. ICML 2026Balancing Understanding and Generation in Discrete Diffusion Models
16. ICML 2026Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering
17. ICML 2026Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
18. ICML 2026Boost the Identity-Preserving Embedding for Consistent Visual Generation
19. ICML 2026Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
20. ICML 2026BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language
21. ICML 2026Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation
22. ICML 2026Bridging Tokens and Geometry: Token-wise 3D Supervision for CAD Generation
23. ICML 2026Bridging Your Imagination with Audio-Video Generation via a Unified Director
24. ICML 2026CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
25. ICML 2026CamGeo: Sparse Camera-Conditioned Image-to-Video Generation with 3D Geometry Priors
26. ICML 2026Categorical Flow Maps
27. ICML 2026Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
28. ICML 2026Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
29. ICML 2026Characterizing the Effect of Noise in Language Generation in the Limit
30. ICML 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
31. ICML 2026CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation
32. ICML 2026CoFrGeNet: Continued Fraction Architectures for Language Generation
33. ICML 2026Comp-Attn: Present-and-Align Attention for Compositional Video Generation
34. ICML 2026Concept Removal for Frontier Image Generative Models
35. ICML 2026Concept-Guided Tokenization: Closing the Gap Between Reconstruction and Generation
36. ICML 2026Conformal Reliability: A New Evaluation Metric for Conditional Generation
37. ICML 2026ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation
38. ICML 2026CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
39. ICML 2026CountsDiff: A diffusion model on the natural numbers for generation and imputation of count-based data
40. ICML 2026Cross-Modal Semantic Decoupling and Transfer for Text-to-Visible-Infrared Person Re-Identification
41. ICML 2026CSD: Content-aware Speculative Decoding for Efficient Image Generation
42. ICML 2026DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation
43. ICML 2026Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
44. ICML 2026DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
45. ICML 2026Deterministic Component Mining for Multi-Framework UI2Code Generation
46. ICML 2026DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
47. ICML 2026Difference-Aware Decision Learning for Multimodal Image Fusion
48. ICML 2026Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
49. ICML 2026Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
50. ICML 2026Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

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。