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 23 / 44 页

  1. ICLR 2025InCoDe: Interpretable Compressed Descriptions For Image Generation
  2. ICLR 2025Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps
  3. ICLR 2025InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
  4. ICLR 2025InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
  5. ICLR 2025IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
  6. ICLR 2025Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
  7. ICLR 2025It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
  8. ICLR 2025IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
  9. ICLR 2025Large Language Models are Interpretable Learners
  10. ICLR 2025LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
  11. ICLR 2025Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
  12. ICLR 2025Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
  13. ICLR 2025Let the Code LLM Edit Itself When You Edit the Code
  14. ICLR 2025LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
  15. ICLR 2025Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  16. ICLR 2025LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
  17. ICLR 2025LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
  18. ICLR 2025MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
  19. ICLR 2025MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
  20. ICLR 2025MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
  21. ICLR 2025MagicPIG: LSH Sampling for Efficient LLM Generation
  22. ICLR 2025MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds
  23. ICLR 2025Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
  24. ICLR 2025McEval: Massively Multilingual Code Evaluation
  25. ICLR 2025Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
  26. ICLR 2025Measuring memorization in RLHF for code completion
  27. ICLR 2025MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
  28. ICLR 2025Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
  29. ICLR 2025NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
  30. ICLR 2025ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
  31. ICLR 2025OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
  32. ICLR 2025OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs
  33. ICLR 2025One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
  34. ICLR 2025OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?
  35. ICLR 2025OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
  36. ICLR 2025PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation
  37. ICLR 2025Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
  38. ICLR 2025PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance
  39. ICLR 2025PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance
  40. ICLR 2025Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming
  41. ICLR 2025Planning in Natural Language Improves LLM Search for Code Generation
  42. ICLR 2025Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
  43. ICLR 2025Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
  44. ICLR 2025Procedural Synthesis of Synthesizable Molecules
  45. ICLR 2025RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
  46. ICLR 2025Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
  47. ICLR 2025Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation
  48. ICLR 2025Real2Code: Reconstruct Articulated Objects via Code Generation
  49. ICLR 2025Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
  50. ICLR 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code

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