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 38 / 44 页

  1. NeurIPS 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
  2. NeurIPS 2024Discrete-state Continuous-time Diffusion for Graph Generation
  3. NeurIPS 2024Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
  4. NeurIPS 2024DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
  5. NeurIPS 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
  6. NeurIPS 2024EffiBench: Benchmarking the Efficiency of Automatically Generated Code
  7. NeurIPS 2024EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization
  8. NeurIPS 2024EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity
  9. NeurIPS 2024Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
  10. NeurIPS 2024ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
  11. NeurIPS 2024Equivariant Neural Diffusion for Molecule Generation
  12. NeurIPS 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
  13. NeurIPS 2024Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
  14. NeurIPS 2024EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
  15. NeurIPS 2024Exploring DCN-like architecture for fast image generation with arbitrary resolution
  16. NeurIPS 2024Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
  17. NeurIPS 2024FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
  18. NeurIPS 2024From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
  19. NeurIPS 2024FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
  20. NeurIPS 2024GAVEL: Generating Games via Evolution and Language Models
  21. NeurIPS 2024Gorilla: Large Language Model Connected with Massive APIs
  22. NeurIPS 2024Grammar-Aligned Decoding
  23. NeurIPS 2024Grasp as You Say: Language-guided Dexterous Grasp Generation
  24. NeurIPS 2024Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
  25. NeurIPS 2024Guiding a Diffusion Model with a Bad Version of Itself
  26. NeurIPS 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
  27. NeurIPS 2024Hierarchical Programmatic Option Framework
  28. NeurIPS 2024Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
  29. NeurIPS 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
  30. NeurIPS 2024Hypothesis Testing the Circuit Hypothesis in LLMs
  31. NeurIPS 2024IaC-Eval: A Code Generation Benchmark for Cloud Infrastructure-as-Code Programs
  32. NeurIPS 2024IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
  33. NeurIPS 2024IF-Font: Ideographic Description Sequence-Following Font Generation
  34. NeurIPS 2024Image Understanding Makes for A Good Tokenizer for Image Generation
  35. NeurIPS 2024IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
  36. NeurIPS 2024Improved Distribution Matching Distillation for Fast Image Synthesis
  37. NeurIPS 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMs
  38. NeurIPS 2024INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
  39. NeurIPS 2024InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
  40. NeurIPS 2024IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
  41. NeurIPS 2024IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
  42. NeurIPS 2024Is Programming by Example Solved by LLMs?
  43. NeurIPS 2024kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution
  44. NeurIPS 2024Language Generation in the Limit
  45. NeurIPS 2024Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading
  46. NeurIPS 2024Language-Driven Interactive Traffic Trajectory Generation
  47. NeurIPS 2024Learning to Reason via Program Generation, Emulation, and Search
  48. NeurIPS 2024LeDex: Training LLMs to Better Self-Debug and Explain Code
  49. NeurIPS 2024LLMDFA: Analyzing Dataflow in Code with Large Language Models
  50. NeurIPS 2024Mercury: A Code Efficiency Benchmark for 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