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

645 papers, page 13 of 13

601. NeurIPS 2025ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation
602. NeurIPS 2025SimpleStrat: Diversifying Language Model Generation with Stratification
603. NeurIPS 2025SnapMoGen: Human Motion Generation from Expressive Texts
604. NeurIPS 2025Sparse Image Synthesis via Joint Latent and RoI Flow
605. NeurIPS 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
606. NeurIPS 2025SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
607. NeurIPS 2025Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
608. NeurIPS 2025Steering When Necessary: Flexible Steering Large Language Models with Backtracking
609. NeurIPS 2025Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
610. NeurIPS 2025SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
611. NeurIPS 2025SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
612. NeurIPS 2025Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency
613. NeurIPS 2025Synthetic Series-Symbol Data Generation for Time Series Foundation Models
614. NeurIPS 2025Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
615. NeurIPS 2025TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles
616. NeurIPS 2025Text-to-Code Generation for Modular Building Layouts in Building Information Modeling
617. NeurIPS 2025The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
618. NeurIPS 2025The Curse of Depth in Large Language Models
619. NeurIPS 2025Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
620. NeurIPS 2025Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
621. NeurIPS 2025Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
622. NeurIPS 2025Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
623. NeurIPS 2025Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
624. NeurIPS 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
625. NeurIPS 2025Training Language Models to Generate Quality Code with Program Analysis Feedback
626. NeurIPS 2025Training-Free Constrained Generation With Stable Diffusion Models
627. NeurIPS 2025Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection
628. NeurIPS 2025TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
629. NeurIPS 2025Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
630. NeurIPS 2025Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
631. NeurIPS 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
632. NeurIPS 2025Unified all-atom molecule generation with neural fields
633. NeurIPS 2025Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation
634. NeurIPS 2025Vector Quantization in the Brain: Grid-like Codes in World Models
635. NeurIPS 2025VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
636. NeurIPS 2025VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification
637. NeurIPS 2025VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
638. NeurIPS 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
639. NeurIPS 2025vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models
640. NeurIPS 2025VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
641. NeurIPS 2025ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics Synthesis
642. NeurIPS 2025Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
643. NeurIPS 2025WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
644. NeurIPS 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
645. NeurIPS 2025Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

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.