Code Generation papers, 2023–2026

Key findings

• Code Generation went from 210 papers in 2023 to 860 in 2026, roughly 4.1x in three years.
• NeurIPS publishes the most Code Generation work: 630 papers from 2023 to 2026, 29% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 93 in 2026.
• Among the 5 topics under Natural Language, it ranks #1 by 2026 paper count; the fastest grower in the group, Retrieval-Augmented Generation, is up 5.4x versus 4.1x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Code Generation papers

236 papers, page 4 of 5

151. NeurIPS 2026Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
152. NeurIPS 2026OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
153. NeurIPS 2026P-EAGLE: Parallel-Drafting EAGLE with Scalable Training
154. NeurIPS 2026P$^{3}$: Joint Program-and-Proof Planning\\ for Verified Code Generation
155. NeurIPS 2026Panoptic Scene Program Diffusion Transformer
156. NeurIPS 2026Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
157. NeurIPS 2026PBT-Bench: Benchmarking AI Agents on Property-Based Testing
158. NeurIPS 2026Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models
159. NeurIPS 2026Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
160. NeurIPS 2026PhysAgentGym: Free Physical-Law Verifiers for Training Small Code-Reasoning Agents
161. NeurIPS 2026Population-Aligned Persona Generation for LLM-based Social Simulation
162. NeurIPS 2026Prefix Likelihood-Ratio Control: Tail-Stable Training for Long-Horizon Language Generation
163. NeurIPS 2026Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
164. NeurIPS 2026Primal-Dual Flow Matching for Sample-Wise Constrained Generation
165. NeurIPS 2026PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
166. NeurIPS 2026Property-Guided LLM Program Synthesis for Planning
167. NeurIPS 2026PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
168. NeurIPS 2026RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
169. NeurIPS 2026Re-evaluating Confidence Remasking in Masked Diffusion Language Models
170. NeurIPS 2026Recursive Language Models
171. NeurIPS 2026Refactoring Code Through Library Design
172. NeurIPS 2026REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
173. NeurIPS 2026Reinforcement Learning for Code Optimization
174. NeurIPS 2026Reinforcement Learning with Verifiable Physics: Post-training LLMs for PDE Solver Generation
175. NeurIPS 2026Render Structure Uncertainty for HTML Repair in MLLM-based UI-to-Code Generation
176. NeurIPS 2026RepoZero: Can LLMs Generate a Code Repository from Scratch?
177. NeurIPS 2026Representation Fréchet Loss for Visual Generation
178. NeurIPS 2026Rethinking Personalized Generation: Test-time Alignment via Factorized Ranking Models
179. NeurIPS 2026RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments
180. NeurIPS 2026Reward Shaping to Improve Language Model Query Generation
181. NeurIPS 2026RoboExo: Structure-Guided Wrist-to-Exocentric Video Generation for Scalable Robot Learning
182. NeurIPS 2026s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
183. NeurIPS 2026Safe Few-Step Generation via Velocity Editing
184. NeurIPS 2026SAGE: Semantic Ambiguity Guided Capacity Expansion for Retrieval-Augmented Generation
185. NeurIPS 2026SDFlow: Similarity-Driven Flow Matching for Time Series Generation
186. NeurIPS 2026Selected-Tail Reliability in Verifier-Guided Best-of-$N$ Inference
187. NeurIPS 2026SemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences
188. NeurIPS 2026SemISP: Semantic-Consistent Diffusion for Cross-Camera RAW-to-sRGB Generation
189. NeurIPS 2026SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
190. NeurIPS 2026Simple Baselines are Competitive with Code Evolution
191. NeurIPS 2026Simple Test-Time Refinement for Plot-to-Code Generation via Visual-Code Diagnostics
192. NeurIPS 2026SimSD: Simple Speculative Decoding in Diffusion Language Models
193. NeurIPS 2026SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
194. NeurIPS 2026SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation
195. NeurIPS 2026Source-Causal Control of Historical Context in Longitudinal Radiology Report Generation
196. NeurIPS 2026Spatially Feasible 3D Indoor Scene Generation via Interaction-Oriented Human Proxy
197. NeurIPS 2026Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models
198. NeurIPS 2026SPRING: Solver-guided Process Rewards for Novel Logical Reasoning Steps Generation
199. NeurIPS 2026Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
200. NeurIPS 2026StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search

FAQ

How many Code Generation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,161 in total: 210 in 2023, 446 in 2024, 645 in 2025, 860 in 2026.

How many Code Generation papers are at NeurIPS 2026?

NeurIPS 2026 has 236 Code Generation papers, versus 230 the year before.

How many Code Generation papers are at ICLR 2026?

ICLR 2026 has 241 Code Generation papers, versus 164 the year before.

How many Code Generation papers are at ICML 2026?

ICML 2026 has 174 Code Generation papers, versus 79 the year before.

How many Code Generation papers are at CVPR 2026?

CVPR 2026 has 209 Code Generation papers, versus 172 the year before.

Which conference publishes the most Code Generation papers?

NeurIPS, with 630 papers from 2023 to 2026.