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 526 篇，第 9 / 11 页

  1. ICLR 2025What Makes Large Language Models Reason in (Multi-Turn) Code Generation?
  2. ICLR 2025What's New in My Data? Novelty Exploration via Contrastive Generation
  3. ICLR 2025When Attention Sink Emerges in Language Models: An Empirical View
  4. ICLR 2025WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
  5. ICLR 2025You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
  6. ICLR 2024$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
  7. ICLR 2024A Branching Decoder for Set Generation
  8. ICLR 2024A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
  9. ICLR 2024A Simple and Scalable Representation for Graph Generation
  10. ICLR 2024Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
  11. ICLR 2024An interpretable error correction method for enhancing code-to-code translation
  12. ICLR 2024Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations
  13. ICLR 2024At Which Training Stage Does Code Data Help LLMs Reasoning?
  14. ICLR 2024AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
  15. ICLR 2024Batched Low-Rank Adaptation of Foundation Models
  16. ICLR 2024Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
  17. ICLR 2024Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
  18. ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
  19. ICLR 2024CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
  20. ICLR 2024Coeditor: Leveraging Repo-level Diffs for Code Auto-editing
  21. ICLR 2024Controlled Text Generation via Language Model Arithmetic
  22. ICLR 2024DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
  23. ICLR 2024DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
  24. ICLR 2024Don't Play Favorites: Minority Guidance for Diffusion Models
  25. ICLR 2024DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
  26. ICLR 2024Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
  27. ICLR 2024Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
  28. ICLR 2024ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
  29. ICLR 2024Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
  30. ICLR 2024Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
  31. ICLR 2024GenSim: Generating Robotic Simulation Tasks via Large Language Models
  32. ICLR 2024Graph Generation with $K^2$-trees
  33. ICLR 2024Guess & Sketch: Language Model Guided Transpilation
  34. ICLR 2024Is Self-Repair a Silver Bullet for Code Generation?
  35. ICLR 2024L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
  36. ICLR 2024LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
  37. ICLR 2024Learning Performance-Improving Code Edits
  38. ICLR 2024Lemur: Harmonizing Natural Language and Code for Language Agents
  39. ICLR 2024LILO: Learning Interpretable Libraries by Compressing and Documenting Code
  40. ICLR 2024LLM Augmented LLMs: Expanding Capabilities through Composition
  41. ICLR 2024LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
  42. ICLR 2024LLM-Assisted Code Cleaning For Training Accurate Code Generators
  43. ICLR 2024MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
  44. ICLR 2024MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
  45. ICLR 2024Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
  46. ICLR 2024MixSATGEN: Learning Graph Mixing for SAT Instance Generation
  47. ICLR 2024Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  48. ICLR 2024MVDream: Multi-view Diffusion for 3D Generation
  49. ICLR 2024NOLA: Compressing LoRA using Linear Combination of Random Basis
  50. ICLR 2024OctoPack: Instruction Tuning Code Large Language Models

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