代码生成论文趋势 2023–2026
程序合成与代码 LLM
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,161 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 29 | 55 | 31 | 95 | 210 |
| 2024 | 135 | 66 | 111 | 134 | 446 |
| 2025 | 230 | 164 | 79 | 172 | 645 |
| 2026 | 236 | 241 | 174 | 209 | 860 |
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 526 篇，第 10 / 11 页
- ICLR 2024PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
- ICLR 2024Personalize Segment Anything Model with One Shot
- ICLR 2024PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
- ICLR 2024Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
- ICLR 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
- ICLR 2024RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
- ICLR 2024Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- ICLR 2024Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
- ICLR 2024Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
- ICLR 2024Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
- ICLR 2024Spatially-Aware Transformers for Embodied Agents
- ICLR 2024Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
- ICLR 2024Teaching Large Language Models to Self-Debug
- ICLR 2024Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
- ICLR 2024The Consensus Game: Language Model Generation via Equilibrium Search
- ICLR 2024The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
- ICLR 2024Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
- ICLR 2024Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
- ICLR 2024TUVF: Learning Generalizable Texture UV Radiance Fields
- ICLR 2024WizardCoder: Empowering Code Large Language Models with Evol-Instruct
- ICLR 2024Zero Bubble (Almost) Pipeline Parallelism
- ICLR 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
- ICLR 20233D generation on ImageNet
- ICLR 2023An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- ICLR 2023Ask Me Anything: A simple strategy for prompting language models
- ICLR 2023BigVGAN: A Universal Neural Vocoder with Large-Scale Training
- ICLR 2023Binding Language Models in Symbolic Languages
- ICLR 2023Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint
- ICLR 2023Calibrating Sequence likelihood Improves Conditional Language Generation
- ICLR 2023CASR: Generating Complex Sequences with Autoregressive Self-Boost Refinement
- ICLR 2023Code Translation with Compiler Representations
- ICLR 2023CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
- ICLR 2023CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
- ICLR 2023CodeT: Code Generation with Generated Tests
- ICLR 2023De Novo Molecular Generation via Connection-aware Motif Mining
- ICLR 2023Decompositional Generation Process for Instance-Dependent Partial Label Learning
- ICLR 2023Denoising Diffusion Error Correction Codes
- ICLR 2023DiGress: Discrete Denoising diffusion for graph generation
- ICLR 2023Dilated convolution with learnable spacings
- ICLR 2023DocPrompting: Generating Code by Retrieving the Docs
- ICLR 2023EVA3D: Compositional 3D Human Generation from 2D Image Collections
- ICLR 2023Evidential Uncertainty and Diversity Guided Active Learning for Scene Graph Generation
- ICLR 2023Few-shot Cross-domain Image Generation via Inference-time Latent-code Learning
- ICLR 2023FunkNN: Neural Interpolation for Functional Generation
- ICLR 2023Generating Sequences by Learning to Self-Correct
- ICLR 2023Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules
- ICLR 2023InCoder: A Generative Model for Code Infilling and Synthesis
- ICLR 2023IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION?
- ICLR 2023Iterative Circuit Repair Against Formal Specifications
- ICLR 2023Language Models are Realistic Tabular Data Generators
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查代码生成在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "code-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。