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 230 篇，第 2 / 5 页

51. NeurIPS 2025CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
52. NeurIPS 2025DeltaFormer: Unlock the state space of Transformer
53. NeurIPS 2025Diffusion Beats Autoregressive in Data-Constrained Settings
54. NeurIPS 2025DINGO: Constrained Inference for Diffusion LLMs
55. NeurIPS 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
56. NeurIPS 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
57. NeurIPS 2025Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
58. NeurIPS 2025Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
59. NeurIPS 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
60. NeurIPS 2025DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform
61. NeurIPS 2025Document Summarization with Conformal Importance Guarantees
62. NeurIPS 2025DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel
63. NeurIPS 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoning
64. NeurIPS 2025EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
65. NeurIPS 2025Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs
66. NeurIPS 2025Efficient semantic uncertainty quantification in language models via diversity-steered sampling
67. NeurIPS 2025EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation
68. NeurIPS 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
69. NeurIPS 2025EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents
70. NeurIPS 2025EVODiff: Entropy-aware Variance Optimized Diffusion Inference
71. NeurIPS 2025Execution Guided Line-by-Line Code Generation
72. NeurIPS 2025FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training
73. NeurIPS 2025Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
74. NeurIPS 2025FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis
75. NeurIPS 2025Feedback Guidance of Diffusion Models
76. NeurIPS 2025FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation
77. NeurIPS 2025Flatten Graphs as Sequences: Transformers are Scalable Graph Generators
78. NeurIPS 2025Flexible MOF Generation with Torsion-Aware Flow Matching
79. NeurIPS 2025FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration
80. NeurIPS 2025Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals
81. NeurIPS 2025Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation
82. NeurIPS 2025Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image Generation
83. NeurIPS 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
84. NeurIPS 2025FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
85. NeurIPS 2025From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
86. NeurIPS 2025FuncGenFoil: Airfoil Generation and Editing Model in Function Space
87. NeurIPS 2025Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
88. NeurIPS 2025Generating Computational Cognitive models using Large Language Models
89. NeurIPS 2025GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
90. NeurIPS 2025GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
91. NeurIPS 2025Greed is Good: A Unifying Perspective on Guided Generation
92. NeurIPS 2025HairFree: Compositional 2D Head Prior for Text-Driven 360° Bald Texture Synthesis
93. NeurIPS 2025Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
94. NeurIPS 2025HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs
95. NeurIPS 2025Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
96. NeurIPS 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
97. NeurIPS 2025Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
98. NeurIPS 2025HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis
99. NeurIPS 2025Improving Regret Approximation for Unsupervised Dynamic Environment Generation
100. NeurIPS 2025Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity

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。