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 860 篇，第 9 / 18 页

  1. ICLR 2026Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief Generation
  2. ICLR 2026SciTS: Scientific Time Series Understanding and Generation with LLMs
  3. ICLR 2026SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
  4. ICLR 2026ShapeGen4D: Towards High Quality 4D Shape Generation from Videos
  5. ICLR 2026ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code
  6. ICLR 2026ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
  7. ICLR 2026Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People
  8. ICLR 2026SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  9. ICLR 2026SketchEvo: Leveraging Drawing Dynamics for Enhanced Image Synthesis
  10. ICLR 2026SliderQuant: Accurate Post-Training Quantization for LLMs
  11. ICLR 2026Soft-Di[M]O: Improved one-step Image Discrete Model
  12. ICLR 2026Soft-Masked Diffusion Language Models
  13. ICLR 2026SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation
  14. ICLR 2026SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables
  15. ICLR 2026SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation
  16. ICLR 2026Steering Autoregressive Music Generation with Recursive Feature Machines
  17. ICLR 2026Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution
  18. ICLR 2026Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
  19. ICLR 2026StoryAlign: Evaluating and Training Reward Models for Story Generation
  20. ICLR 2026Streaming Autoregressive Video Generation via Diagonal Distillation
  21. ICLR 2026String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
  22. ICLR 2026StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
  23. ICLR 2026SWERank: Software Issue Localization with Code Ranking
  24. ICLR 2026SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving
  25. ICLR 2026SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation
  26. ICLR 2026Tell me Habibi, is it Real or Fake?
  27. ICLR 2026Test-Time Alignment for Large Language Models via Textual Model Predictive Control
  28. ICLR 2026The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software Evolution
  29. ICLR 2026The Natural Geometry of Code: Hyperbolic Representation Learning for Program Reasoning
  30. ICLR 2026The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
  31. ICLR 2026Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation
  32. ICLR 2026TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning
  33. ICLR 2026ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
  34. ICLR 2026Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silk
  35. ICLR 2026Toward Complex-Valued Neural Networks for Waveform Generation
  36. ICLR 2026TrajTok: What makes for a good trajectory tokenizer in behavior generation?
  37. ICLR 2026TROLL: Trust Regions Improve Reinforcement Learning for Large Language Models
  38. ICLR 2026Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
  39. ICLR 2026UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy
  40. ICLR 2026VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code
  41. ICLR 2026VERINA: Benchmarking Verifiable Code Generation
  42. ICLR 2026VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation
  43. ICLR 2026VisCoder2: Building Multi-Language Visualization Coding Agents
  44. ICLR 2026VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
  45. ICLR 2026VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip
  46. ICLR 2026What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation
  47. ICLR 2026Why is Your Language Model a Poor Implicit Reward Model?
  48. ICLR 2026WithAnyone: Toward Controllable and ID Consistent Image Generation
  49. ICLR 2026Zephyrus: An Agentic Framework for Weather Science
  50. ICLR 2026ZIP-RC: Zero-overhead Inference-time Prediction of Reward and Cost for Adaptive and Interpretable 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