The 3D point cloud (3DPC) has significantly evolved and benefited from the advances of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between training ...

• Deep transfer learning (DTL) and domain adaptation (DA) enhance 3D point cloud data.
• Taxonomy of DTL methods and knowledge transfer strategies for 3DPC.
• DTL’s applications in 3DPC, i.e., object detection, semantic labeling, and ...

Large language models(LLMs) have shown promising performance for various downstream tasks, especially machine translation. However, LLMs and Specialized Translation Models (STMs) are designed to handle general translation needs, they are not well-...

• Existing universal translation models perform poorly in the e-commerce field.
• Translation models based on LLMs improve translation capabilities more efficiently.
• Resources based on e-commerce texts are conducive to e-commerce ...

The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter-efficient fine-tuning (PEFT) techniques presents significant challenges ...

Large language models (LLMs) have shown exceptional performance in the domain of composite artificial intelligence tasks, offering a preliminary insight into the potential of general artificial intelligence. The fine-tuning process for LLMs ...

Relation classification (RC) is commonly the second step in a relation extraction pipeline, which asserts the relation of two identified entities based on their context. The latest trend for dealing with the task resorts to pre-trained language ...

Modern recommender systems may output considerably different recommendations due to small perturbations in the training data. Changes in the data from a single user will alter the recommendations as well as the recommendations of other users. In ...

In this work, we focus on the cross-domain few-shot classification (CDFSC), which is mostly challenged by the low-data problem as well as extreme domain shift between base and novel target classes. Current methods always employ a lightweight ...

Pre-trained vision-language models, e.g. CLIP, have been increasingly used to address the challenging Open-Vocabulary Segmentation (OVS) task, benefiting from their well-aligned vision-text embedding space. Typical solutions involve either ...

Real-time commentary on football matches is a challenging task that requires precise and coherent descriptions of events as they unfold. Traditional methods often fall short in providing timely and accurate insights into the game. This study aims ...

Video Coding for Machines (VCM) is gaining momentum in applications like autonomous driving, industry manufacturing, and surveillance, where the robustness of machine learning algorithms against coding artifacts is one of the key success factors. ...

Chronic wounds pose significant challenges in medical practice, necessitating effective treatment approaches and reduced burden on healthcare staff. Computer-aided diagnosis (CAD) systems offer promising solutions to enhance treatment outcomes. ...

Previous researches have demonstrated that fine-tuning with legal data can significantly enhance the performance of Large Language Models (LLMs) in legal question-answer (Q&A), affirming that data augmentation is an effective strategy. However, ...

During the development of a speech synthesizer, we often face a lack of training data. This paper describes how the amount of data used to train a speech synthesizer affects the quality of the final synthetic speech. To answer this question, we ...

Image classification, especially unbalanced image classification, holds considerable promise for practical applications. Existing research focuses mainly on enhancing the effectiveness of classifiers through approaches such as data resampling and ...

• Implemented the unbalanced image classification task using reinforcement learning fine-tuning method.
• This method relies on the reward function model to maximize cumulative rewards.
• The fine-tuning process should control the ...

Large pre-trained models based on Vision Transformers (ViTs) contain nearly billions of parameters, demanding substantial computational resources and storage space. This restricts their transferability across different tasks. Recent approaches ...

• Proposed a Lv-Adapter fine-tuning module composed of Linear-layers and Vectors.
• Lv-Adapter can be plug-and-play in transformer-based models.
• When pretrained models are transferred to downstream tasks, Lv-Adapter can improve model ...

Online education systems have gained increasing popularity due to their capability to fully preserve users’ learning data. This advantage enables researchers to assess learners’ mastery through their learning trajectories, thereby facilitating ...

This paper offers a comprehensive comparative study of various pre-trained language models for sentiment analysis in human-computer negotiation dialogues. It examines numerous state-of-the-art PLMs, including GPT-3.5, BERT, and its variants, along ...

Fine-tuning pre-trained models with task-specific data can produce customized models effective for downstream tasks. However, operating large-scale such fine-tuning tasks in real time in the data center faces non-trivial challenges, including ...

Fine-tuning pre-trained large language models (LLMs) helps various downstream tasks, but brings serious privacy leaks when relying on large amounts of data for training. Differentially private stochastic gradient descent (DPSGD) has been designed ...

Deploying deep neural networks (DNNs) on IoT devices is growing due to privacy concerns. However, there is a contradiction between constrained computational capabilities of IoT devices and the large computational requirements of training. To ...$\mathrm{}$