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 2,161 篇，第 2 / 44 页

51. CVPR 2026ExPose Reinforcing Video Generation Models for Extreme Pose Estimation
52. CVPR 2026ExpPortrait Expressive Portrait Generation via Personalized Representation
53. CVPR 2026Extend3D Town-Scale 3D Generation
54. CVPR 2026Extending One-Step Image Generation from Class Labels to Text via
55. CVPR 2026F2-Assist Multi-Phase Fetal Growth Forecast and Report Generation from Ultrasound
56. CVPR 2026FabricGen Microstructure-Aware Woven Fabric Generation
57. CVPR 2026FaithFusion Harmonizing Reconstruction and Generation via Pixel-wise Information Gain
58. CVPR 2026FastHybrid Accelerating Hybrid Autoregressive Image Generation with Lookahead and Guided
59. CVPR 2026FastLightGen Fast and Light Video Generation with Fewer Steps and
60. CVPR 2026FlashMesh Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
61. CVPR 2026FloodDiffusion Tailored Diffusion Forcing for Streaming Motion Generation
62. CVPR 2026FlowFixer Towards Detail-Preserving Subject-Driven Generation
63. CVPR 2026FMPose3D monocular 3D pose estimation via flow matching
64. CVPR 2026FontCrafter High-Fidelity Element-Driven Artistic Font Creation with Visual In-Context Generation
65. CVPR 2026FrankenMotion Part-level Human Motion Generation and Composition
66. CVPR 2026FreeScale Scaling 3D Scenes via Certainty-Aware Free-View Generation
67. CVPR 2026Frequency-Aware Flow Matching for High-Quality Image Generation
68. CVPR 2026Gen3R 3D Scene Generation Meets Feed-Forward Reconstruction
69. CVPR 2026GeoSANE Learning Geospatial Representations from Models Not Data
70. CVPR 2026GeoTikzBridge Advancing Multimodal Code Generation for Geometric Perception and Reasoning
71. CVPR 2026Group Diffusion Enhancing Image Generation by Unlocking Cross-Sample Collaboration
72. CVPR 2026GROW Watermark Generation with Progressive Guidance for Diffusion Models
73. CVPR 2026HandX Scaling Bimanual Motion and Interaction Generation
74. CVPR 2026Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation
75. CVPR 2026HG-Lane High-Fidelity Generation of Lane Scenes under Adverse Weather and
76. CVPR 2026Hierarchical Enhancement of Semantic Priors for Disentangled Text-Driven Motion Generation
77. CVPR 2026HiFi-BRep High-Fidelity Latent Representation for Robust B-Rep Generation
78. CVPR 2026Hint2Gen Bridging Understanding and Generation via Code-structured Hints
79. CVPR 2026Human Geometry Distribution for 3D Animation Generation
80. CVPR 2026I-Scene 3D Instance Models are Implicit Generalizable Spatial Learners
81. CVPR 2026IDperturb Enhancing Variation in Synthetic Face Generation via Angular Perturbations
82. CVPR 2026IGen Scalable Data Generation for Robot Learning from Open-World Images
83. CVPR 2026Image Generation from Contextually-Contradictory Prompts
84. CVPR 2026iMontage Unified Versatile Highly Dynamic Many-to-many Image Generation
85. CVPR 2026Improving Controllable Generation Faster Training and Better Performance via x0-Supervision
86. CVPR 2026InnoAds-Composer Efficient Condition Composition for E-Commerce Poster Generation
87. CVPR 2026Is Bin Generation Indispensable A Bin-Generation-Free Dataset Quantization via Semantic
88. CVPR 2026LAM Language Articulated Object Modelers
89. CVPR 2026LaMoGen Language to Motion Generation Through LLM-Guided Symbolic Inference
90. CVPR 2026LAMP Language-Assisted Motion Planning for Controllable Video Generation
91. CVPR 2026LATTICE Democratize High-Fidelity 3D Generation at Scale
92. CVPR 2026LeapAlign Post-training Flow Matching Models at Any Generation Step by
93. CVPR 2026Learning Hierarchical Hyperbolic Mixture Model for Part-aware 3D Generation
94. CVPR 2026Learning Straight Flows Variational Flow Matching for Efficient Generation
95. CVPR 2026Learning to Learn Weight Generation via Local Consistency Diffusion
96. CVPR 2026LogCD Local-to-global Consistency Distillation for Few-step Image Generation
97. CVPR 2026LumiX Structured and Coherent Text-to-Intrinsic Generation
98. CVPR 2026Lynx Towards High-Fidelity Personalized Video Generation
99. CVPR 2026MajutsuCity Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and
100. CVPR 2026Markovian Scale Prediction A New Era of Visual Autoregressive 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。