Results 1 to 10 of about 124,133 (290)

Enhancing queries for code generation with reinforcement learning

Scientific Reports
We present a reinforcement learning framework that enhances natural language queries to improve DeepSeek code generation. A parametric refiner (Qwen with LoRA) is trained via REINFORCE while the generator remains fixed, using a scalar reward that can ...
Dawei Yuan, Guojun Liang, Tingting Li, Suping Liu   +3 more
doaj   +1 more source

Efficient Adaptation: Enhancing Multilingual Models for Low-Resource Language Translation

Mathematics
This study focuses on the neural machine translation task for the TR-EN language pair, which is considered a low-resource language pair. We investigated fine-tuning strategies for pre-trained language models.
Ilhami Sel, Davut Hanbay
doaj   +1 more source

Solo Connection: A Parameter Efficient Fine-Tuning Technique for Transformers

CoRR
Parameter efficient fine tuning (PEFT) is a versatile and extensible approach for adapting a Large Language Model (LLM) for newer tasks. One of the most prominent PEFT approaches, Low Rank Adaptation (LoRA), primarily focuses on adjusting the attention weight matrices within individual decoder blocks of a Generative Pre trained Transformer (GPT2).
Harsh Nilesh Pathak, Randy C. Paffenroth
openaire   +2 more sources

MPVT: An Efficient Multi-Modal Prompt Vision Tracker for Visual Target Tracking

Applied Sciences
Visual target tracking is a fundamental task in computer vision. Combining multi-modal information with tracking leverages complementary information, which improves the precision and robustness of trackers.
Jianyu Xie, Yan Fu, Junlin Zhou, Tianxiang He, Xiaopeng Wang, Yuke Fang, Duanbing Chen   +6 more
doaj   +1 more source

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing

CoRR
Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropic Gaussian noise to the input image and returning the majority votes over the base classifier.
Chengyan Fu, Wenjie Wang 0008
openaire   +2 more sources

QingNangTCM: a parameter-efficient fine-tuning large language model for traditional Chinese medicine

Digital Chinese Medicine
Objective: To develop QingNangTCM, a specialized large language model (LLM) tailored for expert-level traditional Chinese medicine (TCM) question-answering and clinical reasoning, addressing the scarcity of domain-specific corpora and specialized ...
Tong Xuming, Liu Liyan, Yuan Yanhong, Ding Xiaozheng, Jia Huiru, Yang Xu, Im Sio Kei, Wang Mini Han, Xiong Zhang, Wang Yapeng   +9 more
doaj   +1 more source

PeftCD: Leveraging Vision Foundation Models With Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
To tackle the prevalence of spurious changes, the scarcity of annotations, and the difficulty of cross-domain transfer in multitemporal and multisource remote sensing imagery, we propose Parameter-Efficient Fine-Tuning Change Detection (PeftCD), a change
Sijun Dong, Yuxuan Hu, Libo Wang, Geng Chen, Xiaoliang Meng   +4 more
doaj   +1 more source

A new low-rank adaptation method for brain structure and metastasis segmentation via decoupled principal weight direction and magnitude

Scientific Reports
Deep learning techniques have become pivotal in medical image segmentation, but their success often relies on large, manually annotated datasets, which are expensive and labor-intensive to obtain.
Hancan Zhu, Hongxia Yang, Yaqing Wang, Keli Hu, Guanghua He, Jia Zhou, Zhong Li, Alzheimer’s Disease Neuroimaging Initiative   +7 more
doaj   +1 more source

Gated side adapters with memory-efficient fine tuning for RGB-T tracking

ICT Express
Multi-modal tracking fuses different domain features to compensate for each other. Due to the large training complexity of the foundation RGB model, several parameter-efficient fine-tuning (PEFT) methods have been presented for RGB-T tracking.
Dae-Hyeon Park, Mina Baek, Seung-Hwan Bae   +2 more
doaj   +1 more source

Parameter-Efficient Fine-Tuning via General Linear Structural Regularization for High-Rank Adaptation

Information
Parameter-efficient fine-tuning (PEFT) enables large language models to adapt to downstream tasks with low computational cost. As a representative high-rank PEFT method, MoRA (High-Rank Updating for Parameter-Efficient Fine-Tuning) improves update ...
Bo Zhao, Weihua Ou
doaj   +1 more source