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
- 代码生成论文从 2023 年的 210 篇增长到 2026 年的 860 篇，三年间扩大到约 4.1 倍。
- NeurIPS 是发代码生成论文最多的会议，2023–2026 年共 630 篇，占四个会议总量的 29%。
- 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
- 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的检索增强生成是 5.4 倍，代码生成是 4.1 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 29 | 55 | 31 | 95 | 210 |
| 2024 | 135 | 66 | 111 | 134 | 446 |
| 2025 | 230 | 164 | 79 | 172 | 645 |
| 2026 | 236 | 241 | 174 | 209 | 860 |
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
- NeurIPS 2026A Theoretical Analysis of Test-Driven Code Generation
- ICML 2026$A_2$DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program Trees
- ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
- CVPR 2026ACPV-Net All-Class Polygonal Vectorization for Seamless Vector Map Generation from
- NeurIPS 2025$\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
- ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
- ICLR 2025Automated Proof Generation for Rust Code via Self-Evolution
- CVPR 2025ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
- NeurIPS 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
- ICML 2024ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
- ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
- CVPR 2024Desigen: A Pipeline for Controllable Design Template Generation
- NeurIPS 2023ANPL: Towards Natural Programming with Interactive Decomposition
- ICML 2023Can Large Language Models Reason about Program Invariants?
- ICLR 2023Binding Language Models in Symbolic Languages
- CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
- NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
- ICML 2026Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
- ICLR 2026AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
- CVPR 2026Animator-Centric Skeleton Generation on Objects with Fine-Grained Details
全部代码生成论文
共 630 篇，第 10 / 13 页
- NeurIPS 2025Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
- NeurIPS 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
- NeurIPS 2025Unified all-atom molecule generation with neural fields
- NeurIPS 2025Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation
- NeurIPS 2025Vector Quantization in the Brain: Grid-like Codes in World Models
- NeurIPS 2025VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
- NeurIPS 2025VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification
- NeurIPS 2025VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
- NeurIPS 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
- NeurIPS 2025vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models
- NeurIPS 2025VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
- NeurIPS 2025ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics Synthesis
- NeurIPS 2025Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
- NeurIPS 2025WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
- NeurIPS 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
- NeurIPS 2025Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
- NeurIPS 2024$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
- NeurIPS 2024Accelerating Blockwise Parallel Language Models with Draft Refinement
- NeurIPS 2024ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
- NeurIPS 2024Action Imitation in Common Action Space for Customized Action Image Synthesis
- NeurIPS 2024Ad Auctions for LLMs via Retrieval Augmented Generation
- NeurIPS 2024AdjointDEIS: Efficient Gradients for Diffusion Models
- NeurIPS 2024AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
- NeurIPS 2024Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
- NeurIPS 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
- NeurIPS 2024An Analysis of Tokenization: Transformers under Markov Data
- NeurIPS 2024AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
- NeurIPS 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
- NeurIPS 2024Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
- NeurIPS 2024Benchmarking Counterfactual Image Generation
- NeurIPS 2024Benchmarking LLMs via Uncertainty Quantification
- NeurIPS 2024Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency
- NeurIPS 2024Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
- NeurIPS 2024Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
- NeurIPS 2024Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?
- NeurIPS 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?
- NeurIPS 2024ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
- NeurIPS 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
- NeurIPS 2024CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
- NeurIPS 2024CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
- NeurIPS 2024CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
- NeurIPS 2024ComBack: A Versatile Dataset for Enhancing Compiler Backend Development Efficiency
- NeurIPS 2024Conditional Synthesis of 3D Molecules with Time Correction Sampler
- NeurIPS 2024Confidence Regulation Neurons in Language Models
- NeurIPS 2024ContextCite: Attributing Model Generation to Context
- NeurIPS 2024DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
- NeurIPS 2024DataComp-LM: In search of the next generation of training sets for language models
- NeurIPS 2024DF40: Toward Next-Generation Deepfake Detection
- NeurIPS 2024DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
- NeurIPS 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generation
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"}
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。