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 210 篇，第 2 / 5 页

51. CVPR 2023Learning Compact Representations for LiDAR Completion and Generation
52. CVPR 2023LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook
53. CVPR 2023MAGE: MAsked Generative Encoder To Unify Representation Learning and Image Synthesis
54. CVPR 2023Make-a-Story: Visual Memory Conditioned Consistent Story Generation
55. CVPR 2023MaskSketch: Unpaired Structure-Guided Masked Image Generation
56. CVPR 2023MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation
57. CVPR 2023METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens
58. CVPR 2023MIME: Human-Aware 3D Scene Generation
59. CVPR 2023MoDi: Unconditional Motion Synthesis From Diverse Data
60. CVPR 2023MoStGAN-V: Video Generation With Temporal Motion Styles
61. CVPR 2023Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis
62. CVPR 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects
63. CVPR 2023Neural Scene Chronology
64. CVPR 2023Neural Texture Synthesis With Guided Correspondence
65. CVPR 2023Neural Transformation Fields for Arbitrary-Styled Font Generation
66. CVPR 2023NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models
67. CVPR 2023NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs
68. CVPR 2023Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation
69. CVPR 2023OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis
70. CVPR 2023Patch-Based 3D Natural Scene Generation From a Single Example
71. CVPR 2023Picture That Sketch: Photorealistic Image Generation From Abstract Sketches
72. CVPR 2023Private Image Generation With Dual-Purpose Auxiliary Classifier
73. CVPR 2023Prototype-Based Embedding Network for Scene Graph Generation
74. CVPR 2023QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation
75. CVPR 2023Randomized Adversarial Training via Taylor Expansion
76. CVPR 2023Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration
77. CVPR 2023ReCo: Region-Controlled Text-to-Image Generation
78. CVPR 2023Representing Volumetric Videos As Dynamic MLP Maps
79. CVPR 2023RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts
80. CVPR 2023Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
81. CVPR 2023SeaThru-NeRF: Neural Radiance Fields in Scattering Media
82. CVPR 2023Seeing a Rose in Five Thousand Ways
83. CVPR 2023SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation
84. CVPR 2023Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions
85. CVPR 2023SpaText: Spatio-Textual Representation for Controllable Image Generation
86. CVPR 2023TAPS3D: Text-Guided 3D Textured Shape Generation From Pseudo Supervision
87. CVPR 2023Topology-Guided Multi-Class Cell Context Generation for Digital Pathology
88. CVPR 2023Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization
89. CVPR 2023Towards Unified Scene Text Spotting Based on Sequence Generation
90. CVPR 2023UDE: A Unified Driving Engine for Human Motion Generation
91. CVPR 2023Unbiased Scene Graph Generation in Videos
92. CVPR 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
93. CVPR 2023Unifying Layout Generation With a Decoupled Diffusion Model
94. CVPR 2023VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization
95. CVPR 2023Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization
96. ICLR 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
97. ICLR 20233D generation on ImageNet
98. ICLR 2023An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
99. ICLR 2023Ask Me Anything: A simple strategy for prompting language models
100. ICLR 2023BigVGAN: A Universal Neural Vocoder with Large-Scale Training

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。