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 15 / 44 页

  1. NeurIPS 2026Exploring Advertising Manipulation in Diffusion Image Generation
  2. NeurIPS 2026Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
  3. NeurIPS 2026Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
  4. NeurIPS 2026Feeling of Knowing in Large Language Models
  5. NeurIPS 2026FlexCover: Flexible Cover Song Generation via Symbolic Lead Sheet Control
  6. NeurIPS 2026FloatDoor: Platform triggered Backdoors in LLMs
  7. NeurIPS 2026Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
  8. NeurIPS 2026FracTS: Hierarchical and Autoregressive Time Series Generation
  9. NeurIPS 2026Frequency‑Aware Flow Matching for Continuous and Consistent Robotic Action Generation
  10. NeurIPS 2026From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts
  11. NeurIPS 2026From Generation to Restoration: Residual Diffusion for Neural Channel Decoding
  12. NeurIPS 2026From I/O to Code with Discovery Agent
  13. NeurIPS 2026From Ideas to Code: Tree-structured Policy Optimization for Automated Algorithm Design with LLMs
  14. NeurIPS 2026FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
  15. NeurIPS 2026G-Zero: Self-Play for Open-Ended Generation from Zero Data
  16. NeurIPS 2026Generation-Drift-Guided Block Pruning for Large Language Models
  17. NeurIPS 2026GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond Caching
  18. NeurIPS 2026GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
  19. NeurIPS 2026GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
  20. NeurIPS 2026Guarding the Life Code: Preserving Membership Privacy in Genomic Foundation Models
  21. NeurIPS 2026Guided Data Generation for Understanding Model Behavior
  22. NeurIPS 2026Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
  23. NeurIPS 2026Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality
  24. NeurIPS 2026HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow Generation
  25. NeurIPS 2026How LLMs Distinguish Threats from Offers
  26. NeurIPS 2026How Much is Left? LLMs Linearly Encode Their Remaining Output Length
  27. NeurIPS 2026Hypergraph Generation with Latent Diffusion
  28. NeurIPS 2026HyperNSDE: Personalized Neural SDEs for Joint Static—Longitudinal Clinical Data Generation
  29. NeurIPS 2026Hypothesis generation and updating in large language models
  30. NeurIPS 2026IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
  31. NeurIPS 2026Imagine Before You Draw: Visual Prompt Engineering for Image Generation
  32. NeurIPS 2026In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
  33. NeurIPS 2026IndustryCode: A Benchmark for Industry Code Generation
  34. NeurIPS 2026Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
  35. NeurIPS 2026Information Parity for Code: The Scope of Transfer in Multilingual Code Models
  36. NeurIPS 2026Instantiation of Human Values in Image Generation
  37. NeurIPS 2026IntegrityBench: Can LLMs Be Trusted as Co-Scientists? A Research Integrity Benchmark
  38. NeurIPS 2026Intent Factored Generation: Unleashing the Diversity in Your Language Model
  39. NeurIPS 2026Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation
  40. NeurIPS 2026Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
  41. NeurIPS 2026JEDI: Real-Time Jailbreak Defense for LLMs via In-Generation Detection and Intervention
  42. NeurIPS 2026LADDERS: Length-Aware Data Distribution and Existing-Response Speculation for Fast RL Rollout Generation
  43. NeurIPS 2026Layout Before Pixels: Topology-Anchored Transcriptome-to-Histology Generation
  44. NeurIPS 2026LayoutBridge: Anisotropic Brownian Bridges for Public Indoor Floorplan Generation
  45. NeurIPS 2026LEAP: Library-driven Evolutionary Abstraction Paradigm for Large Language Models
  46. NeurIPS 2026Learning Cultural Vectors for Cross-Cultural Generation
  47. NeurIPS 2026Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
  48. NeurIPS 2026LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models
  49. NeurIPS 2026LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
  50. NeurIPS 2026LLMs Keep Thinking When Told Not To

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