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 1,467 篇，第 19 / 30 页

901. ICML 2025BOOD: Boundary-based Out-Of-Distribution Data Generation
902. ICML 2025Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation
903. ICML 2025Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models
904. ICML 2025Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
905. ICML 2025CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
906. ICML 2025CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models
907. ICML 2025CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
908. ICML 2025CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
909. ICML 2025Compressed Image Generation with Denoising Diffusion Codebook Models
910. ICML 2025Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
911. ICML 2025Contrastive Localized Language-Image Pre-Training
912. ICML 2025Contrastive Visual Data Augmentation
913. ICML 2025Control and Realism: Best of Both Worlds in Layout-to-Image without Training
914. ICML 2025Controllable Data Generation with Hierarchical Neural Representations
915. ICML 2025CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
916. ICML 2025DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
917. ICML 2025DEALing with Image Reconstruction: Deep Attentive Least Squares
918. ICML 2025Deep Unsupervised Hashing via External Guidance
919. ICML 2025DeFoG: Discrete Flow Matching for Graph Generation
920. ICML 2025Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models
921. ICML 2025Diffusion Adversarial Post-Training for One-Step Video Generation
922. ICML 2025Diffusion Counterfactual Generation with Semantic Abduction
923. ICML 2025Dimension-Independent Rates for Structured Neural Density Estimation
924. ICML 2025Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning
925. ICML 2025Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective
926. ICML 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
927. ICML 2025Effective and Efficient Masked Image Generation Models
928. ICML 2025EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
929. ICML 2025Elucidating the design space of language models for image generation
930. ICML 2025Enforcing Idempotency in Neural Networks
931. ICML 2025Enhancing Visual Localization with Cross-Domain Image Generation
932. ICML 2025EpiCoder: Encompassing Diversity and Complexity in Code Generation
933. ICML 2025Epsilon-VAE: Denoising as Visual Decoding
934. ICML 2025EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
935. ICML 2025Event-Customized Image Generation
936. ICML 2025Exponential Family Variational Flow Matching for Tabular Data Generation
937. ICML 2025FDGen: A Fairness-Aware Graph Generation Model
938. ICML 2025Feature out! Let Raw Image as Your Condition for Blind Face Restoration
939. ICML 2025FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
940. ICML 2025FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation
941. ICML 2025FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
942. ICML 2025FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
943. ICML 2025FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
944. ICML 2025FrameBridge: Improving Image-to-Video Generation with Bridge Models
945. ICML 2025FreeMesh: Boosting Mesh Generation with Coordinates Merging
946. ICML 2025Generation from Noisy Examples
947. ICML 2025Geometry Informed Tokenization of Molecules for Language Model Generation
948. ICML 2025Graph Generative Pre-trained Transformer
949. ICML 2025GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation
950. ICML 2025Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

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。