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 12 / 13 页

  1. NeurIPS 2025NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
  2. NeurIPS 2025OmniGen-AR: AutoRegressive Any-to-Image Generation
  3. NeurIPS 2025OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
  4. NeurIPS 2025OmniSVG: A Unified Scalable Vector Graphics Generation Model
  5. NeurIPS 2025OmniTry: Virtual Try-On Anything without Masks
  6. NeurIPS 2025On the Entropy Calibration of Language Models
  7. NeurIPS 2025On Union-Closedness of Language Generation
  8. NeurIPS 2025OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization
  9. NeurIPS 2025ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
  10. NeurIPS 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
  11. NeurIPS 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding
  12. NeurIPS 2025Personalized Visual Content Generation in Conversational Systems
  13. NeurIPS 2025PF∆: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations
  14. NeurIPS 2025PhysX-3D: Physical-Grounded 3D Asset Generation
  15. NeurIPS 2025PoE-World: Compositional World Modeling with Products of Programmatic Experts
  16. NeurIPS 2025PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis
  17. NeurIPS 2025Practical and Effective Code Watermarking for Large Language Models
  18. NeurIPS 2025PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
  19. NeurIPS 2025Preventing Shortcuts in Adapter Training via Providing the Shortcuts
  20. NeurIPS 2025Program Synthesis via Test-Time Transduction
  21. NeurIPS 2025PyraMotion: Attentional Pyramid-Structured Motion Integration for Co-Speech 3D Gesture Synthesis
  22. NeurIPS 2025QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation
  23. NeurIPS 2025QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
  24. NeurIPS 2025QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
  25. NeurIPS 2025QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
  26. NeurIPS 2025Quantifying Elicitation of Latent Capabilities in Language Models
  27. NeurIPS 2025Quartet: Native FP4 Training Can Be Optimal for Large Language Models
  28. NeurIPS 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
  29. NeurIPS 2025Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion
  30. NeurIPS 2025Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
  31. NeurIPS 2025Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning
  32. NeurIPS 2025Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation
  33. NeurIPS 2025RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation
  34. NeurIPS 2025Repo2Run: Automated Building Executable Environment for Code Repository at Scale
  35. NeurIPS 2025Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
  36. NeurIPS 2025ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
  37. NeurIPS 2025Rethinking Verification for LLM Code Generation: From Generation to Testing
  38. NeurIPS 2025Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization
  39. NeurIPS 2025RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-Net
  40. NeurIPS 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
  41. NeurIPS 2025Safety Pretraining: Toward the Next Generation of Safe AI
  42. NeurIPS 2025Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures
  43. NeurIPS 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
  44. NeurIPS 2025Scaling Diffusion Transformers Efficiently via $\mu$P
  45. NeurIPS 2025Scaling Up Parameter Generation: A Recurrent Diffusion Approach
  46. NeurIPS 2025SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
  47. NeurIPS 2025SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAI
  48. NeurIPS 2025SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
  49. NeurIPS 2025Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
  50. NeurIPS 2025SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

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