代码生成论文趋势 2023–2026

主要结论

• 代码生成论文从 2023 年的 210 篇增长到 2026 年的 860 篇，三年间扩大到约 4.1 倍。
• NeurIPS 是发代码生成论文最多的会议，2023–2026 年共 630 篇，占四个会议总量的 29%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的检索增强生成是 5.4 倍，代码生成是 4.1 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 2026A Theoretical Analysis of Test-Driven Code Generation
• ICML 2026$A_2$DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program Trees
• ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
• CVPR 2026ACPV-Net All-Class Polygonal Vectorization for Seamless Vector Map Generation from
• NeurIPS 2025$\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
• ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
• ICLR 2025Automated Proof Generation for Rust Code via Self-Evolution
• CVPR 2025ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
• NeurIPS 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
• ICML 2024ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
• ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
• CVPR 2024Desigen: A Pipeline for Controllable Design Template Generation
• NeurIPS 2023ANPL: Towards Natural Programming with Interactive Decomposition
• ICML 2023Can Large Language Models Reason about Program Invariants?
• ICLR 2023Binding Language Models in Symbolic Languages
• CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
• ICLR 2026AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
• CVPR 2026Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

全部代码生成论文

共 172 篇，第 2 / 4 页

51. CVPR 2025EditAR: Unified Conditional Generation with Autoregressive Models
52. CVPR 2025Empowering LLMs to Understand and Generate Complex Vector Graphics
53. CVPR 2025EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space
54. CVPR 2025Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation
55. CVPR 2025Enhancing Creative Generation on Stable Diffusion-based Models
56. CVPR 2025Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration
57. CVPR 2025ETAP: Event-based Tracking of Any Point
58. CVPR 2025Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation
59. CVPR 2025EVPGS: Enhanced View Prior Guidance for Splatting-based Extrapolated View Synthesis
60. CVPR 2025FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Models
61. CVPR 2025FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
62. CVPR 2025Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation
63. CVPR 2025Few-shot Implicit Function Generation via Equivariance
64. CVPR 2025Finding Local Diffusion Schrodinger Bridge using Kolmogorov-Arnold Network
65. CVPR 2025FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance
66. CVPR 2025FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
67. CVPR 2025Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation
68. CVPR 2025FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation
69. CVPR 2025From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models
70. CVPR 2025From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
71. CVPR 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
72. CVPR 2025Generative Inbetweening through Frame-wise Conditions-Driven Video Generation
73. CVPR 2025Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
74. CVPR 2025GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis
75. CVPR 2025GPS as a Control Signal for Image Generation
76. CVPR 2025Hierarchical Gaussian Mixture Model Splatting for Efficient and Part Controllable 3D Generation
77. CVPR 2025HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
78. CVPR 2025HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation
79. CVPR 2025HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
80. CVPR 2025IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
81. CVPR 2025Illumination Spectrum Estimation for Multispectral Images via Surface Reflectance Modeling and Spatial-Spectral Feature Generation
82. CVPR 2025Image Generation Diversity Issues and How to Tame Them
83. CVPR 2025Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation
84. CVPR 2025Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
85. CVPR 2025Improving Editability in Image Generation with Layer-wise Memory
86. CVPR 2025Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models
87. CVPR 2025LaTexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending
88. CVPR 2025Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene
89. CVPR 2025Learning Flow Fields in Attention for Controllable Person Image Generation
90. CVPR 2025Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing
91. CVPR 2025Learning to Filter Outlier Edges in Global SfM
92. CVPR 2025Learning to Normalize on the SPD Manifold under Bures-Wasserstein Geometry
93. CVPR 2025Learning-enabled Polynomial Lyapunov Function Synthesis via High-Accuracy Counterexample-Guided Framework
94. CVPR 2025LLM-driven Multimodal and Multi-Identity Listening Head Generation
95. CVPR 2025Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation
96. CVPR 2025Masking meets Supervision: A Strong Learning Alliance
97. CVPR 2025MC^2: Multi-concept Guidance for Customized Multi-concept Generation
98. CVPR 2025MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
99. CVPR 2025MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
100. CVPR 2025MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities

常见问题

2023–2026 年四大会议一共有多少篇代码生成论文？

共 2,161 篇，按年份分别是 2023 年 210 篇、2024 年 446 篇、2025 年 645 篇、2026 年 860 篇。

NeurIPS 2026 有多少篇代码生成论文？

NeurIPS 2026 有 236 篇代码生成论文，上一届是 230 篇。

ICLR 2026 有多少篇代码生成论文？

ICLR 2026 有 241 篇代码生成论文，上一届是 164 篇。

ICML 2026 有多少篇代码生成论文？

ICML 2026 有 174 篇代码生成论文，上一届是 79 篇。

CVPR 2026 有多少篇代码生成论文？

CVPR 2026 有 209 篇代码生成论文，上一届是 172 篇。

哪个会议的代码生成论文最多？

NeurIPS，2023–2026 年共 630 篇。