Suchergebnisse - unixcoder

Evaluating uniXcoder Embeddings for Automated Grading: A Study Across Varied Code Perspectives

Autoren: Nakka Narmada Peeta Basa Pati

Quelle: 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT). :1-5

A User Evaluation of UniXcoder Using Statement Completion in a Real-World Setting

Autoren: de Weerdt, Jorit (author)

Index Begriffe: Code Completion, Integrated Development Environment, User Study, bachelor thesis

URL: http://resolver.tudelft.nl/uuid:4c54e567-86a7-4448-9c1b-d85856607b9f
https://github.com/code4me-me/code4me
https://github.com/code4me-me/code4me

An Empirical Analysis on the Performance of UniXcoder

Autoren: van Dam, Tim (author)

Index Begriffe: code completion, type annotations, bachelor thesis

URL: http://resolver.tudelft.nl/uuid:ccf8b865-931c-480b-a5dd-4e4120a20126
https://github.com/timvandam/rp
https://github.com/timvandam/rp

UniXcoder: Unified Cross-Modal Pre-training for Code Representation

Autoren: Guo, Daya Lu, Shuai Duan, Nan et al.

Index Begriffe: Computer Science - Computation and Language, Computer Science - Programming Languages, Computer Science - Software Engineering, text

URL: http://arxiv.org/abs/2203.03850

UniXcoder fine-tuned model

Autoren: Benitez, Julian

Multi-Label Classification of Pure Code.

Autoren: Gao, Bin Qin, Hongwu Ma, Xiuqin

Quelle: International Journal of Software Engineering & Knowledge Engineering; Oct2024, Vol. 34 Issue 10, p1641-1659, 19p

Schlagwörter: PROGRAMMING languages, SOURCE code, CLASSIFICATION, INSTITUTIONAL repositories, ENCODING

Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study

Schlagwörter: InCoder, CodeGPT, UniXcoder, code completion

Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study

Schlagwörter: InCoder, CodeGPT, UniXcoder, code completion

An Empirical Study on the Performance of Large Pre-trained Models for Automatic Line Completion

Schlagwörter: InCoder, UniXcoder, code completion

SYNCode: Synergistic Human–LLM Collaboration for Enhanced Data Annotation in Stack Overflow †.

Autoren: Xia, Meng Maharjan, Shradha Le, Tammy et al.

Quelle: Information; May2025, Vol. 16 Issue 5, p392, 19p

Schlagwörter: LANGUAGE models, SOFTWARE engineering, DEEP learning, TRANSFORMER models, ANNOTATIONS

Mašīnmācīšanās pielietojums programmatūras produktu automatizētās regresijas testēšanas paātrināšanai

Autoren: Cipiševa, Svetlana Arnicāns, Guntis Latvijas Universitāte. Datorikas fakultāte

Weitere Verfasser: Cipiševa, Svetlana Arnicāns, Guntis Latvijas Universitāte. Datorikas fakultāte

Schlagwörter: Rindošanas mašīnmācīšanās, Datorzinātne, Gradient Boosting, Testpiemēra prioritāšu noteikšana, UniXCoder, LambdaMART

Zugangs-URL: https://dspace.lu.lv/dspace/handle/7/66043

An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities.

Autoren: Yang, Zezhou Chen, Sirong Gao, Cuiyun et al.

Quelle: ACM Transactions on Software Engineering & Methodology; Sep2025, Vol. 34 Issue 7, p1-28, 28p

Schlagwörter: CODE generators, DEEP learning, INFORMATION architecture, SEARCH algorithms, MULTISENSOR data fusion, LANGUAGE models, MACHINE learning

One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization.

Autoren: Wang, Deze Chen, Boxing Li, Shanshan et al.

Quelle: ICSE: International Conference on Software Engineering; 2023, p5-16, 12p

Schlagwörter: PROGRAMMING languages, SOURCE code, MULTILINGUALISM, DATA analysis, DATA corruption

Mašīnmācīšanās pielietojums programmatūras produktu automatizētās regresijas testēšanas paātrināšanai ; Application of machine learning to accelerate automated regression testing of software products

Autoren: Cipiševa, Svetlana Arnicāns, Guntis Latvijas Universitāte. Datorikas fakultāte

Weitere Verfasser: Cipiševa, Svetlana Arnicāns, Guntis Latvijas Universitāte. Datorikas fakultāte

Schlagwörter: Datorzinātne, Testpiemēra prioritāšu noteikšana, Rindošanas mašīnmācīšanās, Gradient Boosting, UniXCoder, LambdaMART

Relation: 101361; https://dspace.lu.lv/dspace/handle/7/66043

Verfügbarkeit: https://dspace.lu.lv/dspace/handle/7/66043

Distinguishing LLM-Generated from Human-Written Code by Contrastive Learning.

Autoren: Xu, Xiaodan Ni, Chao Guo, Xinrong et al.

Quelle: ACM Transactions on Software Engineering & Methodology; May2025, Vol. 34 Issue 4, p1-31, 31p

Schlagwörter: CHATGPT, LANGUAGE models, CODE generators, MACHINE learning

Do Current Language Models Support Code Intelligence for R Programming Language?

Autoren: Zhao, Zixiao Fard, Fatemeh

Quelle: ACM Transactions on Software Engineering & Methodology; Nov2025, Vol. 34 Issue 8, p1-39, 39p

Schlagwörter: LANGUAGE models, SOFTWARE engineering, ABSTRACTION (Computer science), PROGRAMMING languages

Multi-View Feature Fusion Model for Software Bug Repair Pattern Prediction.

Autoren: XU Yong CHENG Ming

Quelle: Wuhan University Journal of Natural Sciences; Dec2023, Vol. 28 Issue 6, p493-507, 15p

TCCCD: Triplet-Based Cross-Language Code Clone Detection.

Autoren: Fang, Yong Zhou, Fangzheng Xu, Yijia et al.

Quelle: Applied Sciences (2076-3417); Nov2023, Vol. 13 Issue 21, p12084, 22p

Schlagwörter: PROGRAMMING languages, VECTOR spaces, CARTOGRAPHY software, COMPUTER software development, SOURCE code

CoCoSoDa: Effective Contrastive Learning for Code Search.

Autoren: Shi, Ensheng Wang, Yanlin Gu, Wenchao et al.

Quelle: ICSE: International Conference on Software Engineering; 2023, p2198-2210, 13p

Schlagwörter: QUERY languages (Computer science), PROGRAMMING languages, DATA augmentation, SOFTWARE engineering

Reviews & Products: QUANTITATIVE Analysis (Book)

Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities.

Autoren: Ma, Wei Liu, Shangqing Zhao, Mengjie et al.

Quelle: ACM Transactions on Software Engineering & Methodology; Sep2024, Vol. 33 Issue 7, p1-29, 29p

Schlagwörter: LANGUAGE models, PROGRAMMING languages, FLOWGRAPHS, COMPUTER programming education, SYNTAX (Grammar), DEEP learning