代码生成论文趋势 2023–2026

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。

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 2,161 篇，第 3 / 44 页

101. CVPR 2026Match-and-Fuse Consistent Generation from Unstructured Image Sets
102. CVPR 2026MatLat Material Latent Space for PBR Texture Generation
103. CVPR 2026MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion
104. CVPR 2026MeshMosaic Scaling Artist Mesh Generation via Local-to-Global Assembly
105. CVPR 2026MeshRipple Structured Autoregressive Generation of Artist-Meshes
106. CVPR 2026MeshWeaver Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
107. CVPR 2026MICON-Bench Benchmarking and Enhancing Multi-Image Context Image Generation in Unified
108. CVPR 2026Mirai Autoregressive Visual Generation Needs Foresight
109. CVPR 2026Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning
110. CVPR 2026MLLM-HWSI A Multimodal Large Language Model for Hierarchical Whole Slide
111. CVPR 2026MM-ACT Learn from Multimodal Parallel Generation to Act
112. CVPR 2026MM-ReCoder Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction
113. CVPR 2026MMFace-DiT A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation
114. CVPR 2026mmWaveFlow Unified Enhancement and Generation of mmWave Human Point Clouds
115. CVPR 2026MoCoDiff A Controllable Autoregressive Diffusion Model for Expressive Motion Generation
116. CVPR 2026MoLingo Motion-Language Alignment for Text-to-Human Motion Generation
117. CVPR 2026MotionMaster Generalizable Text-Driven Motion Generation and Editing
118. CVPR 2026Multi-Scale Local Speculative Decoding for Image Generation
119. CVPR 2026Multi-view Consistent 3D Gaussian Head Avatars without Multi-view Generation
120. CVPR 2026NAMI Efficient Image Generation via Bridged Progressive Rectified Flow Transformers
121. CVPR 2026Native and Compact Structured Latents for 3D Generation
122. CVPR 2026Nestwork Conditional 3D Furnished House Layout Generation through Latent Heterogeneous
123. CVPR 2026Next-Scale Autoregressive Models for Text-to-Motion Generation
124. CVPR 2026NI-Tex Non-isometric Image-based Garment Texture Generation
125. CVPR 2026Not All Birds Look The Same Identity-Preserving Generation For Birds
126. CVPR 2026OmniDocLayout Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
127. CVPR 2026OmniGen2 Towards Instruction-Aligned Multimodal Generation
128. CVPR 2026One-to-More High-Fidelity Training-Free Anomaly Generation with Attention Control
129. CVPR 2026Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware
130. CVPR 2026OpenDance Multimodal Controllable 3D Dance Generation with Large-scale Internet Data
131. CVPR 2026OpenT2M No-frill Motion Generation with Open-source Large-scale High-quality Data
132. CVPR 2026OPRO Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image Generation
133. CVPR 2026Order Matters 3D Shape Generation from Sequential VR Sketches
134. CVPR 2026ORV 4D Occupancy-centric Robot Video Generation
135. CVPR 2026PaCo-RL Advancing Reinforcement Learning for Consistent Image Generation with Pairwise
136. CVPR 2026PAMotion Physics-Aware Motion Generation for Full-Body Interaction with Multiple Objects
137. CVPR 2026Pano3DComposer Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image
138. CVPR 2026Parallel Jacobi Decoding for Fast Autoregressive Image Generation
139. CVPR 2026PartDiffuser Part-wise 3D Mesh Generation via Discrete Diffusion
140. CVPR 2026PersonaVLM Long-Term Personalized Multimodal LLMs
141. CVPR 2026PG-VTON Single-Pass Training-Free Virtual Try-On via Patch-Guided Reference Alignment
142. CVPR 2026Photo3D Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement
143. CVPR 2026Phrase-grounded APO for Improving Chest X-ray Report Generation
144. CVPR 2026PhysGen Physically Grounded 3D Shape Generation for Industrial Design
145. CVPR 2026PixelDiT Pixel Diffusion Transformers for Image Generation
146. CVPR 2026Pointer-CAD Unifying B-Rep and Command Sequences via Pointer-based Edges
147. CVPR 2026PoseMaster A Unified 3D Native Framework for Stylized Pose Generation
148. CVPR 2026PrITTI Primitive-based Generation of Controllable and Editable 3D Semantic Urban
149. CVPR 2026Progressive Neural Architecture Generation
150. CVPR 2026Property-Informed Diffusion-Based Text-to-Microstructure 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。