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 1 / 5 页

1. CVPR 20233D Neural Field Generation Using Triplane Diffusion
2. CVPR 2023Adaptive Data-Free Quantization
3. CVPR 2023AdaptiveMix: Improving GAN Training via Feature Space Shrinkage
4. CVPR 2023ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction
5. CVPR 2023AnchorFormer: Point Cloud Completion From Discriminative Nodes
6. CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
7. CVPR 2023Backdoor Cleansing With Unlabeled Data
8. CVPR 2023BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields
9. CVPR 2023CF-Font: Content Fusion for Few-Shot Font Generation
10. CVPR 2023CFA: Class-Wise Calibrated Fair Adversarial Training
11. CVPR 2023CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes From Natural Language
12. CVPR 2023Collaborative Diffusion for Multi-Modal Face Generation and Editing
13. CVPR 2023Computational Flash Photography Through Intrinsics
14. CVPR 2023Conditional Image-to-Video Generation With Latent Flow Diffusion Models
15. CVPR 2023Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching
16. CVPR 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Models
17. CVPR 2023DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization
18. CVPR 2023DAA: A Delta Age AdaIN Operation for Age Estimation via Binary Code Transformer
19. CVPR 2023DeepVecFont-v2: Exploiting Transformers To Synthesize Vector Fonts With Higher Quality
20. CVPR 2023Devil's on the Edges: Selective Quad Attention for Scene Graph Generation
21. CVPR 2023DiffCollage: Parallel Generation of Large Content With Diffusion Models
22. CVPR 2023Diffusion-Based Signed Distance Fields for 3D Shape Generation
23. CVPR 2023Dimensionality-Varying Diffusion Process
24. CVPR 2023DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis
25. CVPR 2023Disentangling Writer and Character Styles for Handwriting Generation
26. CVPR 2023DrapeNet: Garment Generation and Self-Supervised Draping
27. CVPR 2023Dual-Bridging With Adversarial Noise Generation for Domain Adaptive rPPG Estimation
28. CVPR 2023DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation
29. CVPR 2023Executing Your Commands via Motion Diffusion in Latent Space
30. CVPR 2023Feature Representation Learning With Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition
31. CVPR 2023FeatureBooster: Boosting Feature Descriptors With a Lightweight Neural Network
32. CVPR 2023FLAG3D: A 3D Fitness Activity Dataset With Language Instruction
33. CVPR 2023Freestyle Layout-to-Image Synthesis
34. CVPR 2023Graph Transformer GANs for Graph-Constrained House Generation
35. CVPR 2023High-Fidelity 3D Face Generation From Natural Language Descriptions
36. CVPR 2023High-Fidelity and Freely Controllable Talking Head Video Generation
37. CVPR 2023High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning
38. CVPR 2023HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising
39. CVPR 2023Human Guided Ground-Truth Generation for Realistic Image Super-Resolution
40. CVPR 2023Identity-Preserving Talking Face Generation With Landmark and Appearance Priors
41. CVPR 2023Implicit Neural Head Synthesis via Controllable Local Deformation Fields
42. CVPR 2023Infinite Photorealistic Worlds Using Procedural Generation
43. CVPR 2023Interactive and Explainable Region-Guided Radiology Report Generation
44. CVPR 2023IterativePFN: True Iterative Point Cloud Filtering
45. CVPR 2023KD-DLGAN: Data Limited Image Generation via Knowledge Distillation
46. CVPR 2023LANA: A Language-Capable Navigator for Instruction Following and Generation
47. CVPR 2023LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation
48. CVPR 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generation
49. CVPR 2023LayoutDM: Transformer-Based Diffusion Model for Layout Generation
50. CVPR 2023LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction

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。