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 111 篇，第 1 / 3 页

1. ICML 2024Accelerating PDE Data Generation via Differential Operator Action in Solution Space
2. ICML 2024Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
3. ICML 2024ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
4. ICML 2024Adaptive Stabilization Based on Machine Learning for Column Generation
5. ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
6. ICML 2024Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning
7. ICML 2024Amortizing Pragmatic Program Synthesis with Rankings
8. ICML 2024AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
9. ICML 2024Autoformalizing Euclidean Geometry
10. ICML 2024Behavior Generation with Latent Actions
11. ICML 2024BetterV: Controlled Verilog Generation with Discriminative Guidance
12. ICML 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
13. ICML 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models
14. ICML 2024CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources
15. ICML 2024Case-Based or Rule-Based: How Do Transformers Do the Math?
16. ICML 2024Causality Based Front-door Defense Against Backdoor Attack on Language Models
17. ICML 2024Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
18. ICML 2024Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
19. ICML 2024Code as Reward: Empowering Reinforcement Learning with VLMs
20. ICML 2024CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
21. ICML 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
22. ICML 2024Cross-view Masked Diffusion Transformers for Person Image Synthesis
23. ICML 2024CuTS: Customizable Tabular Synthetic Data Generation
24. ICML 2024DAG-Based Column Generation for Adversarial Team Games
25. ICML 2024Data-Efficient Molecular Generation with Hierarchical Textual Inversion
26. ICML 2024Debating with More Persuasive LLMs Leads to More Truthful Answers
27. ICML 2024DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning
28. ICML 2024DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation
29. ICML 2024Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation
30. ICML 2024Disentangled 3D Scene Generation with Layout Learning
31. ICML 2024Distinguishing the Knowable from the Unknowable with Language Models
32. ICML 2024Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
33. ICML 2024DPZero: Private Fine-Tuning of Language Models without Backpropagation
34. ICML 2024Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
35. ICML 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
36. ICML 2024Emergent Representations of Program Semantics in Language Models Trained on Programs
37. ICML 2024Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation
38. ICML 2024Evaluating Quantized Large Language Models
39. ICML 2024Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
40. ICML 2024Executable Code Actions Elicit Better LLM Agents
41. ICML 2024Exploiting Code Symmetries for Learning Program Semantics
42. ICML 2024Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization
43. ICML 2024FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering
44. ICML 2024GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
45. ICML 2024GPTSwarm: Language Agents as Optimizable Graphs
46. ICML 2024Graph Generation with Diffusion Mixture
47. ICML 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
48. ICML 2024Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
49. ICML 2024HumanTOMATO: Text-aligned Whole-body Motion Generation
50. ICML 2024Hyperbolic Geometric Latent Diffusion Model for Graph 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。