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 395 篇，第 5 / 8 页

  1. ICML 2025DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
  2. ICML 2025Earley-Driven Dynamic Pruning for Efficient Structured Decoding
  3. ICML 2025EditLord: Learning Code Transformation Rules for Code Editing
  4. ICML 2025EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
  5. ICML 2025EpiCoder: Encompassing Diversity and Complexity in Code Generation
  6. ICML 2025Fast Inference with Kronecker-Sparse Matrices
  7. ICML 2025FreeMesh: Boosting Mesh Generation with Coordinates Merging
  8. ICML 2025From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
  9. ICML 2025Function-to-Style Guidance of LLMs for Code Translation
  10. ICML 2025Generation from Noisy Examples
  11. ICML 2025Geometry Informed Tokenization of Molecules for Language Model Generation
  12. ICML 2025GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code
  13. ICML 2025Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
  14. ICML 2025KernelBench: Can LLMs Write Efficient GPU Kernels?
  15. ICML 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
  16. ICML 2025Language Models over Canonical Byte-Pair Encodings
  17. ICML 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
  18. ICML 2025Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
  19. ICML 2025Logits are All We Need to Adapt Closed Models
  20. ICML 2025Long-Form Speech Generation with Spoken Language Models
  21. ICML 2025LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
  22. ICML 2025Matryoshka Quantization
  23. ICML 2025Multi-Turn Code Generation Through Single-Step Rewards
  24. ICML 2025Multimodal Medical Code Tokenizer
  25. ICML 2025NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits
  26. ICML 2025NICE Data Selection for Instruction Tuning in LLMs with Non-differentiable Evaluation Metric
  27. ICML 2025On Exact Bit-level Reversible Transformers Without Changing Architecture
  28. ICML 2025On the Query Complexity of Verifier-Assisted Language Generation
  29. ICML 2025Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
  30. ICML 2025Overcoming Non-monotonicity in Transducer-based Streaming Generation
  31. ICML 2025polybasic Speculative Decoding Through a Theoretical Perspective
  32. ICML 2025Position: Future Research and Challenges Remain Towards AI for Software Engineering
  33. ICML 2025Prior Knowledge Guided Neural Architecture Generation
  34. ICML 2025ProSec: Fortifying Code LLMs with Proactive Security Alignment
  35. ICML 2025QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
  36. ICML 2025Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
  37. ICML 2025Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment
  38. ICML 2025Representative Language Generation
  39. ICML 2025Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?
  40. ICML 2025Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
  41. ICML 2025Selective Prompt Anchoring for Code Generation
  42. ICML 2025Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
  43. ICML 2025SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
  44. ICML 2025SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
  45. ICML 2025Strategic Planning: A Top-Down Approach to Option Generation
  46. ICML 2025Synthesizing Software Engineering Data in a Test-Driven Manner
  47. ICML 2025The Diffusion Duality
  48. ICML 2025Thinking LLMs: General Instruction Following with Thought Generation
  49. ICML 2025TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
  50. ICML 2025Towards Practical Defect-Focused Automated Code Review

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