Image denoising (DN), demosaicing (DM) and super-resolution (SR) are the key tasks of the low-level vision. Joint demosaicing, denoising and Super-resolution (JDDSR) can effectively improve the image quality. However,...
详细信息
Addressing the challenge of easy inverse kinematics solution but difficult forward kinematics solution for Delta parallel robots, a kinematic model for the Delta robot was established. By improving the fitness functio...
详细信息
Compared to Full-Model Fine-Tuning (FMFT), Parameter Efficient Fine-Tuning (PEFT) has demonstrated superior performance and lower computational overhead in several code understanding tasks, such as code summarization ...
详细信息
ISBN:
(纸本)9798350330663
Compared to Full-Model Fine-Tuning (FMFT), Parameter Efficient Fine-Tuning (PEFT) has demonstrated superior performance and lower computational overhead in several code understanding tasks, such as code summarization and code search. This advantage can be attributed to PEFT's ability to alleviate the catastrophic forgetting issue of Pre-trained Language Models (PLMs) by updating only a small number of parameters. As a result, PEFT effectively harnesses the pre-trained general-purpose knowledge for downstream tasks. However, existing studies primarily involve static code comprehension, aligning with the pre-training paradigm of recent PLMs and facilitating knowledge transfer, but they do not account for dynamic code changes. Thus, it remains unclear whether PEFT outperforms FMFT in task-specific adaptation for code-change-related tasks. To address this question, we examine two prevalent PEFT methods, namely Adapter Tuning (AT) and Low-Rank Adaptation (LoRA), and compare their performance with FMFT on five popular PLMs. Specifically, we evaluate their performance on two widely-studied code-change-related tasks: Just-In-Time Defect Prediction (JIT-DP) and Commit Message Generation (CMG). The results demonstrate that both AT and LoRA achieve state-of-the-art (SOTA) results in JIT-DP and exhibit comparable performances in CMG when compared to FMFT and other SOTA approaches. Furthermore, AT and LoRA exhibit superiority in cross-lingual and low-resource scenarios. We also conduct three probing tasks to explain the efficacy of PEFT techniques on JIT-DP and CMG tasks from both static and dynamic perspectives. The study indicates that PEFT, particularly through the use of AT and LoRA, offers promising advantages in code-change-related tasks, surpassing FMFT in certain aspects. This research contributes to a deeper understanding of the capabilities of PEFT in leveraging pre-trained PLMs for dynamic code changes. The replication package is available at https://***/ishuol
As a place for receiving electric energy transmitted by the power grid and secondary distribution of electric energy in the power system, the substation includes primary equipment for transforming voltage and current ...
详细信息
Currently, Super-resolution image reconstruction (SRIR or SR) is a research hotspot in the field of computer vision and image processing. With the development of deep learning, The technology of super-resolution image...
详细信息
With the rapid development of the mobile Internet, people's demand for transportation methods is also increasing. At the same time, road congestion is becoming more and more serious due to the wide availability an...
详细信息
In recent years, the exploration of multi-agent collaborative games using deep reinforcement learning has emerged as a prominent and active area within artificial intelligence research. This paper contributes to this ...
详细信息
Blockchains have been widely adopted to track critical data in complicated applications recently, thus it is necessary to provide efficient infrastructure to analyze large-scale chain data. However, the current blockc...
详细信息
In this paper, a new hybrid artificial intelligent A∗ search method for scheduling flexible manufacturing systems (FMSs) based on timed Petri nets (PNs) is proposed. First, it uses place-timed Petri nets to model FMSs...
详细信息
The present research gives extensive attitude towards using Gen AI for foretelling election results and also analyze the behavior of the voter while voting. By capitalizing various data sources from preceeding electio...
详细信息
暂无评论