{"total":35,"rows":[{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361,"area":null},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63,"area":null},{"id":"2207.11280","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","created":"2022-07-22","cited_by_count":48,"area":null},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32,"area":null},{"id":"2204.09653","title":"On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages","created":"2022-04-05","cited_by_count":30,"area":null},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2402.01935","title":"Code Representation Learning At Scale","created":"2024-02-02","cited_by_count":26,"area":null},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2205.11739","title":"Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2110.03868","title":"Towards Learning (Dis)-Similarity of Source Code from Program Contrasts","created":"2021-10-08","cited_by_count":17,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2205.02029","title":"CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training","created":"2022-05-04","cited_by_count":15,"area":null},{"id":"2208.08100","title":"CommitBART: A Large Pre-trained Model for GitHub Commits","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2208.08643","title":"Learning Program Representations with a Tree-Structured Transformer","created":"2022-08-18","cited_by_count":6,"area":null},{"id":"2304.11072","title":"An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph","created":"2023-04-17","cited_by_count":5,"area":null},{"id":"2312.00413","title":"Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2503.05507","title":"Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2205.01293","title":"A Survey of Deep Learning Models for Structural Code Understanding","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2208.05596","title":"Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines","created":"2022-08-11","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2401.10716","title":"Structured Code Representations Enable Data-Efficient Adaptation of Code Language Models","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2406.12326","title":"Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2503.22776","title":"Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2605.28557","title":"Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2303.01645","title":"APIContext2Com: Code Comment Generation by Incorporating Pre-Defined API Documentation","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2304.13350","title":"Neuro-symbolic Zero-Shot Code Cloning with Cross-Language Intermediate Representation","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2503.23231","title":"CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2402.05783","title":"Text-to-Code Generation with Modality-relative Pre-training","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2406.11437","title":"Analysing the Behaviour of Tree-Based Neural Networks in Regression Tasks","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2407.18945","title":"CogNarr Ecosystem: Facilitating Group Cognition at Scale","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2505.14759","title":"LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2508.02729","title":"Interpreting Performance Profiles with Deep Learning","created":"2025-08-01","cited_by_count":0,"area":null}],"next_cursor":null}