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 446 篇，第 7 / 9 页

  1. ICML 2024tinyBenchmarks: evaluating LLMs with fewer examples
  2. ICML 2024tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)
  3. ICML 2024To the Max: Reinventing Reward in Reinforcement Learning
  4. ICML 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
  5. ICML 2024Unsupervised Episode Generation for Graph Meta-learning
  6. ICML 2024Unsupervised Evaluation of Code LLMs with Round-Trip Correctness
  7. ICML 2024UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers
  8. ICML 2024Value-Evolutionary-Based Reinforcement Learning
  9. ICML 2024Watermark Stealing in Large Language Models
  10. ICML 2024When Will Gradient Regularization Be Harmful?
  11. ICML 2024X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation
  12. NeurIPS 2024$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
  13. NeurIPS 2024Accelerating Blockwise Parallel Language Models with Draft Refinement
  14. NeurIPS 2024ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
  15. NeurIPS 2024Action Imitation in Common Action Space for Customized Action Image Synthesis
  16. NeurIPS 2024Ad Auctions for LLMs via Retrieval Augmented Generation
  17. NeurIPS 2024AdjointDEIS: Efficient Gradients for Diffusion Models
  18. NeurIPS 2024AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
  19. NeurIPS 2024Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
  20. NeurIPS 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
  21. NeurIPS 2024An Analysis of Tokenization: Transformers under Markov Data
  22. NeurIPS 2024AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
  23. NeurIPS 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
  24. NeurIPS 2024Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
  25. NeurIPS 2024Benchmarking Counterfactual Image Generation
  26. NeurIPS 2024Benchmarking LLMs via Uncertainty Quantification
  27. NeurIPS 2024Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency
  28. NeurIPS 2024Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
  29. NeurIPS 2024Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
  30. NeurIPS 2024Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?
  31. NeurIPS 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?
  32. NeurIPS 2024ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
  33. NeurIPS 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
  34. NeurIPS 2024CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
  35. NeurIPS 2024CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
  36. NeurIPS 2024CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
  37. NeurIPS 2024ComBack: A Versatile Dataset for Enhancing Compiler Backend Development Efficiency
  38. NeurIPS 2024Conditional Synthesis of 3D Molecules with Time Correction Sampler
  39. NeurIPS 2024Confidence Regulation Neurons in Language Models
  40. NeurIPS 2024ContextCite: Attributing Model Generation to Context
  41. NeurIPS 2024DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
  42. NeurIPS 2024DataComp-LM: In search of the next generation of training sets for language models
  43. NeurIPS 2024DF40: Toward Next-Generation Deepfake Detection
  44. NeurIPS 2024DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
  45. NeurIPS 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generation
  46. NeurIPS 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
  47. NeurIPS 2024Discrete-state Continuous-time Diffusion for Graph Generation
  48. NeurIPS 2024Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
  49. NeurIPS 2024DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
  50. NeurIPS 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs

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