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 134 篇，第 3 / 3 页

101. CVPR 2024Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
102. CVPR 2024SemCity: Semantic Scene Generation with Triplane Diffusion
103. CVPR 2024Shadow Generation for Composite Image Using Diffusion Model
104. CVPR 2024Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior
105. CVPR 2024Single Mesh Diffusion Models with Field Latents for Texture Generation
106. CVPR 2024Single-View Scene Point Cloud Human Grasp Generation
107. CVPR 2024Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models
108. CVPR 2024Spatio-Temporal Turbulence Mitigation: A Translational Perspective
109. CVPR 2024SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream
110. CVPR 2024SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation
111. CVPR 2024Stratified Avatar Generation from Sparse Observations
112. CVPR 2024Style Aligned Image Generation via Shared Attention
113. CVPR 2024StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN
114. CVPR 2024SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis
115. CVPR 2024Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting
116. CVPR 2024Taming Mode Collapse in Score Distillation for Text-to-3D Generation
117. CVPR 2024Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions
118. CVPR 2024Text-Guided 3D Face Synthesis - From Generation to Editing
119. CVPR 2024Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
120. CVPR 2024Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation
121. CVPR 2024TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process
122. CVPR 2024Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation
123. CVPR 2024Towards Automated Movie Trailer Generation
124. CVPR 2024Towards Realistic Scene Generation with LiDAR Diffusion Models
125. CVPR 2024Towards Variable and Coordinated Holistic Co-Speech Motion Generation
126. CVPR 2024Training-Free Pretrained Model Merging
127. CVPR 2024UniGS: Unified Representation for Image Generation and Segmentation
128. CVPR 2024UV-IDM: Identity-Conditioned Latent Diffusion Model for Face UV-Texture Generation
129. CVPR 2024VecFusion: Vector Font Generation with Diffusion
130. CVPR 2024Vector Graphics Generation via Mutually Impulsed Dual-domain Diffusion
131. CVPR 2024Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation
132. CVPR 2024WANDR: Intention-guided Human Motion Generation
133. CVPR 2024Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation
134. CVPR 2024When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation

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。