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 446 篇，第 2 / 9 页

51. CVPR 2024Generating Non-Stationary Textures using Self-Rectification
52. CVPR 2024GLACE: Global Local Accelerated Coordinate Encoding
53. CVPR 2024High-fidelity Person-centric Subject-to-Image Synthesis
54. CVPR 2024HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
55. CVPR 2024Holodeck: Language Guided Generation of 3D Embodied AI Environments
56. CVPR 2024HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation
57. CVPR 2024HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion
58. CVPR 2024HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation
59. CVPR 2024Hyperspherical Classification with Dynamic Label-to-Prototype Assignment
60. CVPR 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation
61. CVPR 2024Instance-level Expert Knowledge and Aggregate Discriminative Attention for Radiology Report Generation
62. CVPR 2024InstanceDiffusion: Instance-level Control for Image Generation
63. CVPR 2024InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning
64. CVPR 2024Interactive3D: Create What You Want by Interactive 3D Generation
65. CVPR 2024InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion
66. CVPR 2024JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients
67. CVPR 2024Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints
68. CVPR 2024Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis
69. CVPR 2024Learned Representation-Guided Diffusion Models for Large-Image Generation
70. CVPR 2024Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
71. CVPR 2024Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis
72. CVPR 2024LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example
73. CVPR 2024Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
74. CVPR 2024Leveraging Predicate and Triplet Learning for Scene Graph Generation
75. CVPR 2024LLMs are Good Action Recognizers
76. CVPR 2024LLMs are Good Sign Language Translators
77. CVPR 2024Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives
78. CVPR 2024MAS: Multi-view Ancestral Sampling for 3D Motion Generation Using 2D Diffusion
79. CVPR 2024MatFuse: Controllable Material Generation with Diffusion Models
80. CVPR 2024MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
81. CVPR 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis
82. CVPR 2024ModaVerse: Efficiently Transforming Modalities with LLMs
83. CVPR 2024Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
84. CVPR 2024MPOD123: One Image to 3D Content Generation Using Mask-enhanced Progressive Outline-to-Detail Optimization
85. CVPR 2024NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
86. CVPR 2024OED: Towards One-stage End-to-End Dynamic Scene Graph Generation
87. CVPR 2024OmniMotionGPT: Animal Motion Generation with Limited Data
88. CVPR 2024On the Scalability of Diffusion-based Text-to-Image Generation
89. CVPR 2024One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion
90. CVPR 2024PEEKABOO: Interactive Video Generation via Masked-Diffusion
91. CVPR 2024POPDG: Popular 3D Dance Generation with PopDanceSet
92. CVPR 2024Programmable Motion Generation for Open-Set Motion Control Tasks
93. CVPR 2024Rapid 3D Model Generation with Intuitive 3D Input
94. CVPR 2024RepAn: Enhanced Annealing through Re-parameterization
95. CVPR 2024Residual Denoising Diffusion Models
96. CVPR 2024Restoration by Generation with Constrained Priors
97. CVPR 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation
98. CVPR 2024Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
99. CVPR 2024Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion
100. CVPR 2024SCoFT: Self-Contrastive Fine-Tuning for Equitable 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。