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 860 篇，第 7 / 18 页

  1. ICLR 2026Gradient-Based Program Synthesis with Neurally Interpreted Languages
  2. ICLR 2026GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
  3. ICLR 2026Gumbel Distillation for Parallel Text Generation
  4. ICLR 2026HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithimic Coding
  5. ICLR 2026Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
  6. ICLR 2026Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents
  7. ICLR 2026HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
  8. ICLR 2026HiddenEcho: Mitigating Noise Amplification in Differentially Private LLMs with Hidden-State Correction
  9. ICLR 2026HOG-Diff: Higher-Order Guided Diffusion for Graph Generation
  10. ICLR 2026How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective
  11. ICLR 2026Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
  12. ICLR 2026Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
  13. ICLR 2026Improving Code Localization with Repository Memory
  14. ICLR 2026InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement
  15. ICLR 2026InfGen: Scenario Generation as Next Token Group Prediction
  16. ICLR 2026Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing
  17. ICLR 2026JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
  18. ICLR 2026JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
  19. ICLR 2026jqBench: a benchmark for reading and editing JSON from natural language and/or examples
  20. ICLR 2026KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
  21. ICLR 2026Kevin: Multi-Turn RL for Generating CUDA Kernels
  22. ICLR 2026Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
  23. ICLR 2026Learning to Generate Unit Test via Adversarial Reinforcement Learning
  24. ICLR 2026Let's Explore Step by Step: Generating Provable Formal Statements with Deductive Exploration
  25. ICLR 2026Leveraging Pretrained Knowledge at Inference Time: LoRA-Gated Contrastive Decoding for Multilingual Factual Language Generation in Adapted LLMs
  26. ICLR 2026LightMem: Lightweight and Efficient Memory-Augmented Generation
  27. ICLR 2026LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
  28. ICLR 2026LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis
  29. ICLR 2026LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design
  30. ICLR 2026Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
  31. ICLR 2026LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
  32. ICLR 2026LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals
  33. ICLR 2026M4PQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
  34. ICLR 2026MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
  35. ICLR 2026Making, Not Taking, the Best of N
  36. ICLR 2026MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
  37. ICLR 2026MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization
  38. ICLR 2026Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers
  39. ICLR 2026Massive Editing for Large Language Models Based on Dynamic Weight Generation
  40. ICLR 2026Mastering Sparse CUDA Generation through Pretrained Models and Deep Reinforcement Learning
  41. ICLR 2026mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules
  42. ICLR 2026Measuring LLM Novelty As The Frontier Of Original And High-Quality Output
  43. ICLR 2026MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
  44. ICLR 2026Metis: Training LLMs with FP4 Quantization
  45. ICLR 2026Modeling Others' Minds as Code
  46. ICLR 2026MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
  47. ICLR 2026Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages
  48. ICLR 2026MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
  49. ICLR 2026Next Visual Granularity Generation
  50. ICLR 2026NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

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