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 645 篇，第 7 / 13 页

  1. ICLR 2025SFS: Smarter Code Space Search improves LLM Inference Scaling
  2. ICLR 2025Shh, don't say that! Domain Certification in LLMs
  3. ICLR 2025Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
  4. ICLR 2025SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects
  5. ICLR 2025Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
  6. ICLR 2025Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
  7. ICLR 2025Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
  8. ICLR 2025STAR: Synthesis of Tailored Architectures
  9. ICLR 2025STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
  10. ICLR 2025Steering Large Language Models between Code Execution and Textual Reasoning
  11. ICLR 2025Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
  12. ICLR 2025SysBench: Can LLMs Follow System Message?
  13. ICLR 2025Taming Overconfidence in LLMs: Reward Calibration in RLHF
  14. ICLR 2025TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice
  15. ICLR 2025Teaching LLMs How to Learn with Contextual Fine-Tuning
  16. ICLR 2025Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency
  17. ICLR 2025TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark
  18. ICLR 2025The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
  19. ICLR 2025The KoLMogorov Test: Compression by Code Generation
  20. ICLR 2025The Ramanujan Library - Automated Discovery on the Hypergraph of Integer Relations
  21. ICLR 2025The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
  22. ICLR 2025ThinK: Thinner Key Cache by Query-Driven Pruning
  23. ICLR 2025To Code or Not To Code? Exploring Impact of Code in Pre-training
  24. ICLR 2025Towards Realistic Data Generation for Real-World Super-Resolution
  25. ICLR 2025Training Language Models on Synthetic Edit Sequences Improves Code Synthesis
  26. ICLR 2025TULIP: Token-length Upgraded CLIP
  27. ICLR 2025Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs
  28. ICLR 2025Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization
  29. ICLR 2025Uncertainty-Aware Decoding with Minimum Bayes Risk
  30. ICLR 2025Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
  31. ICLR 2025Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
  32. ICLR 2025What Makes Large Language Models Reason in (Multi-Turn) Code Generation?
  33. ICLR 2025What's New in My Data? Novelty Exploration via Contrastive Generation
  34. ICLR 2025When Attention Sink Emerges in Language Models: An Empirical View
  35. ICLR 2025WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
  36. ICLR 2025You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
  37. ICML 2025AAAR-1.0: Assessing AI’s Potential to Assist Research
  38. ICML 2025Agent-as-a-Judge: Evaluate Agents with Agents
  39. ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
  40. ICML 2025An Online Learning Approach to Prompt-based Selection of Generative Models and LLMs
  41. ICML 2025AuPair: Golden Example Pairs for Code Repair
  42. ICML 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation
  43. ICML 2025Automated Benchmark Generation for Repository-Level Coding Tasks
  44. ICML 2025BaxBench: Can LLMs Generate Correct and Secure Backends?
  45. ICML 2025Black-Box Adversarial Attacks on LLM-Based Code Completion
  46. ICML 2025BoA: Attention-aware Post-training Quantization without Backpropagation
  47. ICML 2025Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
  48. ICML 2025Can Large Language Models Understand Intermediate Representations in Compilers?
  49. ICML 2025CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction
  50. ICML 2025CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

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