Výsledky vyhledávání

Report

Studying Practitioners' Expectations on Clear Code Review Comments

Autor: Li, Zhenhao, Chen, Junkai, Mao, Qiheng, Hu, Xing, Liu, Kui, Xia, Xin

The code review comment (CRC) is pivotal in the process of modern code review. It provides reviewers with the opportunity to identify potential bugs, offer constructive feedback, and suggest improvements. Clear and concise code review comments (CRCs)

Externí odkaz: http://arxiv.org/abs/2410.06515

Zobrazit plný text záznamu

Report

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Autor: Zou, Xin, Wang, Yizhou, Yan, Yibo, Huang, Sirui, Zheng, Kening, Chen, Junkai, Tang, Chang, Hu, Xuming

Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) are susceptible to hallucinations, especially assertively fabricating content not present in the visual inputs. To address the aforementioned challenge, we follow a commo

Externí odkaz: http://arxiv.org/abs/2410.03577

Zobrazit plný text záznamu

Report

Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models

Autor: Zheng, Kening, Chen, Junkai, Yan, Yibo, Zou, Xin, Hu, Xuming

Hallucination issues persistently plagued current multimodal large language models (MLLMs). While existing research primarily focuses on object-level or attribute-level hallucinations, sidelining the more sophisticated relation hallucinations that ne

Externí odkaz: http://arxiv.org/abs/2408.09429

Zobrazit plný text záznamu

Report

NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations

Autor: Chen, Junkai, Li, Zhenhao, Hu, Xing, Xia, Xin

Large language models (LLMs) achieve promising results in code generation based on a given natural language description. They have been integrated into open-source projects and commercial products to facilitate daily coding activities. The natural la

Externí odkaz: http://arxiv.org/abs/2406.19783

Zobrazit plný text záznamu

Report

Reasoning Runtime Behavior of a Program with LLM: How Far Are We?

Autor: Chen, Junkai, Pan, Zhiyuan, Hu, Xing, Li, Zhenhao, Li, Ge, Xia, Xin

Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. To evaluate the capabilities of code LLMs in various aspects, many benchmarks have been proposed (e.g., HumanEval and ClassEval). Code

Externí odkaz: http://arxiv.org/abs/2403.16437

Zobrazit plný text záznamu

Report

FaaSLight: General Application-Level Cold-Start Latency Optimization for Function-as-a-Service in Serverless Computing

Autor: Liu, Xuanzhe, Wen, Jinfeng, Chen, Zhenpeng, Li, Ding, Chen, Junkai, Liu, Yi, Wang, Haoyu, Jin, Xin

Serverless computing is a popular cloud computing paradigm that frees developers from server management. Function-as-a-Service (FaaS) is the most popular implementation of serverless computing, representing applications as event-driven and stateless

Externí odkaz: http://arxiv.org/abs/2207.08175

Zobrazit plný text záznamu