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 34 / 44 页

  1. ICLR 2024Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
  2. ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
  3. ICLR 2024CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
  4. ICLR 2024Coeditor: Leveraging Repo-level Diffs for Code Auto-editing
  5. ICLR 2024Controlled Text Generation via Language Model Arithmetic
  6. ICLR 2024DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
  7. ICLR 2024DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
  8. ICLR 2024Don't Play Favorites: Minority Guidance for Diffusion Models
  9. ICLR 2024DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
  10. ICLR 2024Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
  11. ICLR 2024Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
  12. ICLR 2024ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
  13. ICLR 2024Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
  14. ICLR 2024Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
  15. ICLR 2024GenSim: Generating Robotic Simulation Tasks via Large Language Models
  16. ICLR 2024Graph Generation with $K^2$-trees
  17. ICLR 2024Guess & Sketch: Language Model Guided Transpilation
  18. ICLR 2024Is Self-Repair a Silver Bullet for Code Generation?
  19. ICLR 2024L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
  20. ICLR 2024LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
  21. ICLR 2024Learning Performance-Improving Code Edits
  22. ICLR 2024Lemur: Harmonizing Natural Language and Code for Language Agents
  23. ICLR 2024LILO: Learning Interpretable Libraries by Compressing and Documenting Code
  24. ICLR 2024LLM Augmented LLMs: Expanding Capabilities through Composition
  25. ICLR 2024LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
  26. ICLR 2024LLM-Assisted Code Cleaning For Training Accurate Code Generators
  27. ICLR 2024MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
  28. ICLR 2024MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
  29. ICLR 2024Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
  30. ICLR 2024MixSATGEN: Learning Graph Mixing for SAT Instance Generation
  31. ICLR 2024Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  32. ICLR 2024MVDream: Multi-view Diffusion for 3D Generation
  33. ICLR 2024NOLA: Compressing LoRA using Linear Combination of Random Basis
  34. ICLR 2024OctoPack: Instruction Tuning Code Large Language Models
  35. ICLR 2024PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
  36. ICLR 2024Personalize Segment Anything Model with One Shot
  37. ICLR 2024PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
  38. ICLR 2024Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
  39. ICLR 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
  40. ICLR 2024RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
  41. ICLR 2024Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
  42. ICLR 2024Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
  43. ICLR 2024Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
  44. ICLR 2024Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
  45. ICLR 2024Spatially-Aware Transformers for Embodied Agents
  46. ICLR 2024Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
  47. ICLR 2024Teaching Large Language Models to Self-Debug
  48. ICLR 2024Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
  49. ICLR 2024The Consensus Game: Language Model Generation via Equilibrium Search
  50. ICLR 2024The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”

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