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

每年论文数

各会议论文数

按年份和会议统计

代码生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202329553195210
202413566111134446
202523016479172645
2026236241174209860

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

全部代码生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 2,161 篇，第 42 / 44 页

  1. ICLR 2023BigVGAN: A Universal Neural Vocoder with Large-Scale Training
  2. ICLR 2023Binding Language Models in Symbolic Languages
  3. ICLR 2023Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint
  4. ICLR 2023Calibrating Sequence likelihood Improves Conditional Language Generation
  5. ICLR 2023CASR: Generating Complex Sequences with Autoregressive Self-Boost Refinement
  6. ICLR 2023Code Translation with Compiler Representations
  7. ICLR 2023CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
  8. ICLR 2023CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
  9. ICLR 2023CodeT: Code Generation with Generated Tests
  10. ICLR 2023De Novo Molecular Generation via Connection-aware Motif Mining
  11. ICLR 2023Decompositional Generation Process for Instance-Dependent Partial Label Learning
  12. ICLR 2023Denoising Diffusion Error Correction Codes
  13. ICLR 2023DiGress: Discrete Denoising diffusion for graph generation
  14. ICLR 2023Dilated convolution with learnable spacings
  15. ICLR 2023DocPrompting: Generating Code by Retrieving the Docs
  16. ICLR 2023EVA3D: Compositional 3D Human Generation from 2D Image Collections
  17. ICLR 2023Evidential Uncertainty and Diversity Guided Active Learning for Scene Graph Generation
  18. ICLR 2023Few-shot Cross-domain Image Generation via Inference-time Latent-code Learning
  19. ICLR 2023FunkNN: Neural Interpolation for Functional Generation
  20. ICLR 2023Generating Sequences by Learning to Self-Correct
  21. ICLR 2023Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules
  22. ICLR 2023InCoder: A Generative Model for Code Infilling and Synthesis
  23. ICLR 2023IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION?
  24. ICLR 2023Iterative Circuit Repair Against Formal Specifications
  25. ICLR 2023Language Models are Realistic Tabular Data Generators
  26. ICLR 2023Language Models Can Teach Themselves to Program Better
  27. ICLR 2023Learning to Generate Columns with Application to Vertex Coloring
  28. ICLR 2023Learning with Stochastic Orders
  29. ICLR 2023Molecule Generation For Target Protein Binding with Structural Motifs
  30. ICLR 2023Multi-domain image generation and translation with identifiability guarantees
  31. ICLR 2023Multi-lingual Evaluation of Code Generation Models
  32. ICLR 2023Non-parametric Outlier Synthesis
  33. ICLR 2023Offline RL for Natural Language Generation with Implicit Language Q Learning
  34. ICLR 2023On the Perils of Cascading Robust Classifiers
  35. ICLR 2023On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation
  36. ICLR 2023Out-of-Distribution Detection and Selective Generation for Conditional Language Models
  37. ICLR 2023Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
  38. ICLR 2023Planning with Large Language Models for Code Generation
  39. ICLR 2023PV3D: A 3D Generative Model for Portrait Video Generation
  40. ICLR 2023Re-parameterizing Your Optimizers rather than Architectures
  41. ICLR 2023Recitation-Augmented Language Models
  42. ICLR 2023Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
  43. ICLR 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
  44. ICLR 2023SketchKnitter: Vectorized Sketch Generation with Diffusion Models
  45. ICLR 2023Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
  46. ICLR 2023Tailoring Language Generation Models under Total Variation Distance
  47. ICLR 2023Trainability Preserving Neural Pruning
  48. ICLR 2023Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis
  49. ICLR 2023TypeT5: Seq2seq Type Inference using Static Analysis
  50. ICLR 2023Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「自然语言」下的其他主题