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

630 papers, page 6 of 13

251. NeurIPS 2025Approximately Aligned Decoding
252. NeurIPS 2025AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy
253. NeurIPS 2025ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data
254. NeurIPS 2025AutoPartGen: Autoregressive 3D Part Generation and Discovery
255. NeurIPS 2025BADiff: Bandwidth Adaptive Diffusion Model
256. NeurIPS 2025Benchmarking Large Language Models with Integer Sequence Generation Tasks
257. NeurIPS 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
258. NeurIPS 2025Bi-Directional Communication-Efficient Stochastic FL via Remote Source Generation
259. NeurIPS 2025Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
260. NeurIPS 2025Bidirectional Representations Augmented Autoregressive Biological Sequence Generation: Application in De Novo Peptide Sequencing
261. NeurIPS 2025BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks
262. NeurIPS 2025Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
263. NeurIPS 2025BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation
264. NeurIPS 2025Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation
265. NeurIPS 2025Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
266. NeurIPS 2025Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
267. NeurIPS 2025Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
268. NeurIPS 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code
269. NeurIPS 2025CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
270. NeurIPS 2025CLEVER: A Curated Benchmark for Formally Verified Code Generation
271. NeurIPS 2025CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance
272. NeurIPS 2025CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
273. NeurIPS 2025Color Conditional Generation with Sliced Wasserstein Guidance
274. NeurIPS 2025COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
275. NeurIPS 2025Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
276. NeurIPS 2025Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
277. NeurIPS 2025Constrained Discrete Diffusion
278. NeurIPS 2025Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
279. NeurIPS 2025Contextual Thompson Sampling via Generation of Missing Data
280. NeurIPS 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
281. NeurIPS 2025CoRe: Benchmarking LLMs’ Code Reasoning Capabilities through Static Analysis Tasks
282. NeurIPS 2025CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs
283. NeurIPS 2025CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step
284. NeurIPS 2025CSGO: Content-Style Composition in Text-to-Image Generation
285. NeurIPS 2025Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
286. NeurIPS 2025CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning
287. NeurIPS 2025CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
288. NeurIPS 2025DeltaFormer: Unlock the state space of Transformer
289. NeurIPS 2025Diffusion Beats Autoregressive in Data-Constrained Settings
290. NeurIPS 2025DINGO: Constrained Inference for Diffusion LLMs
291. NeurIPS 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
292. NeurIPS 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
293. NeurIPS 2025Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
294. NeurIPS 2025Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
295. NeurIPS 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
296. NeurIPS 2025DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform
297. NeurIPS 2025Document Summarization with Conformal Importance Guarantees
298. NeurIPS 2025DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel
299. NeurIPS 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoning
300. NeurIPS 2025EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

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.