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 395 篇，第 8 / 8 页

  1. ICML 2024Switchable Decision: Dynamic Neural Generation Networks
  2. ICML 2024Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion
  3. ICML 2024The Illusion of State in State-Space Models
  4. ICML 2024tinyBenchmarks: evaluating LLMs with fewer examples
  5. ICML 2024tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)
  6. ICML 2024To the Max: Reinventing Reward in Reinforcement Learning
  7. ICML 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
  8. ICML 2024Unsupervised Episode Generation for Graph Meta-learning
  9. ICML 2024Unsupervised Evaluation of Code LLMs with Round-Trip Correctness
  10. ICML 2024UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers
  11. ICML 2024Value-Evolutionary-Based Reinforcement Learning
  12. ICML 2024Watermark Stealing in Large Language Models
  13. ICML 2024When Will Gradient Regularization Be Harmful?
  14. ICML 2024X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation
  15. ICML 2023Autoregressive Diffusion Model for Graph Generation
  16. ICML 2023Can Large Language Models Reason about Program Invariants?
  17. ICML 2023CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language Models
  18. ICML 2023Coder Reviewer Reranking for Code Generation
  19. ICML 2023CRISP: Curriculum based Sequential neural decoders for Polar code family
  20. ICML 2023Dirichlet Diffusion Score Model for Biological Sequence Generation
  21. ICML 2023DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
  22. ICML 2023Exploring Chemical Space with Score-based Out-of-distribution Generation
  23. ICML 2023Extrapolative Controlled Sequence Generation via Iterative Refinement
  24. ICML 2023FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
  25. ICML 2023Geometric Latent Diffusion Models for 3D Molecule Generation
  26. ICML 2023Hierarchical Neural Coding for Controllable CAD Model Generation
  27. ICML 2023How Does Information Bottleneck Help Deep Learning?
  28. ICML 2023Image generation with shortest path diffusion
  29. ICML 2023LEVER: Learning to Verify Language-to-Code Generation with Execution
  30. ICML 2023Measuring the Impact of Programming Language Distribution
  31. ICML 2023Model-based Offline Reinforcement Learning with Count-based Conservatism
  32. ICML 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation
  33. ICML 2023OpenFE: Automated Feature Generation with Expert-level Performance
  34. ICML 2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
  35. ICML 2023PAL: Program-aided Language Models
  36. ICML 2023Probabilistic Concept Bottleneck Models
  37. ICML 2023Protecting Language Generation Models via Invisible Watermarking
  38. ICML 2023R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents
  39. ICML 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
  40. ICML 2023Repository-Level Prompt Generation for Large Language Models of Code
  41. ICML 2023Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flows
  42. ICML 2023Slot-VAE: Object-Centric Scene Generation with Slot Attention
  43. ICML 2023Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
  44. ICML 2023TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation
  45. ICML 2023Von Mises Mixture Distributions for Molecular Conformation Generation

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