相关论文: ProtoBERT-LoRA: Parameter-Efficient Prototypical F…

LoRA has become a universal Parameter-Efficient Fine-Tuning (PEFT) technique that equips Large Language Models (LLMs) to adapt quickly to new tasks. However, when these models are scaled up, even the latest LoRA variants still introduce…

Low-rank adaption (LoRA) is a prominent method that adds a small number of learnable parameters to the frozen pre-trained weights for parameter-efficient fine-tuning. Prompted by the question, ``Can we make its representation enough with…

Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in…

Existing federated learning methods have effectively dealt with decentralized learning in scenarios involving data privacy and non-IID data. However, in real-world situations, each client dynamically learns new classes, requiring the global…

Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated tags, failing to exploit the rich semantic knowledge embedded in clinical…

Electronic health records contain inconsistently structured or free-text data, requiring efficient preprocessing to enable predictive health care models. Although artificial intelligence-driven natural language processing tools show promise…

This study demonstrates that a Multimodal Large Language Model (MLLM) adapted via Low-Rank Adaptation (LoRA) can perform both Automatic Pronunciation Assessment (APA) and Mispronunciation Detection and Diagnosis (MDD) simultaneously.…

Code comment classification is a critical task for automated software documentation and analysis. In the context of the NLBSE'26 Tool Competition, we present LoRA-MME, a Multi-Model Ensemble architecture utilizing Parameter-Efficient…

Recent advancements in text-to-image generative models, particularly latent diffusion models (LDMs), have demonstrated remarkable capabilities in synthesizing high-quality images from textual prompts. However, achieving identity…

Traditional methods for determining assessment item parameters, such as difficulty and discrimination, rely heavily on expensive field testing to collect student performance data for Item Response Theory (IRT) calibration. This study…

Large Language Models (LLMs) frequently reproduce the gender- and sexual-identity prejudices embedded in their training corpora, leading to outputs that marginalize LGBTQIA+ users. Hence, reducing such biases is of great importance. To…

Fine-tuning large-scale pretrained models is prohibitively expensive in terms of computational and memory costs. LoRA, as one of the most popular Parameter-Efficient Fine-Tuning (PEFT) methods, offers a cost-effective alternative by…

Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, reduce adaptation cost by injecting low-rank updates into pretrained weights. However, LoRA's down-projection is randomly initialized and data-agnostic, discarding potentially…

While Large Language Models (LLMs) have revolutionized artificial intelligence, fine-tuning LLMs is extraordinarily computationally expensive, preventing smaller businesses and research teams with limited GPU resources from engaging with…

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of…

Parameter-efficient fine-tuning (PEFT) has become a practical route for adapting large language models to downstream tasks, with LoRA-style methods being particularly attractive because they are inexpensive to train and easy to deploy. Most…

Efficient fine-tuning of pre-trained convolutional neural network (CNN) models using local data is essential for providing high-quality services to users using ubiquitous and resource-limited Internet of Things (IoT) devices. Low-Rank…

An important paradigm of natural language processing consists of large-scale pre-training on general domain data and adaptation to particular tasks or domains. As we pre-train larger models, full fine-tuning, which retrains all model…

Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samples lead to…

Recent studies show that quantum neural networks (QNNs) generalize well in few-shot regimes. To extend this advantage to large-scale tasks, we propose Q-LoRA, a quantum-enhanced fine-tuning scheme that integrates lightweight QNNs into the…