Results 121 to 130 of about 227,550 (285)

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

Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence
Foundation models have achieved tremendous success in different domains. However, their huge computation and storage complexity make these models difficult to fine-tune and also less applicable in practice. Recent study shows training in Fourier domain can be an effective fine-tuning method in terms of both model performance and number of training ...
Ding, Xinyu, Chen, Lexuan, Liao, Siyu, Wang, Zhongfeng   +3 more
openaire   +2 more sources

Microporous Microgel Assemblies Facilitating the Recruitment and Osteogenic Differentiation of Progenitor Cells for Bone Regeneration

Advanced Functional Materials, EarlyView.
There is a significant need for biomaterials with well‐defined stability and bioactivity to support tissue regeneration. In this study, we developed a tunable microgel platform that enables the decoupling of stiffness from porosity, thereby promoting bone regeneration.
Silvia Pravato, Haishuo Guan, Bianca M. Carrara, Mira Jacobs, Matteo Monticelli, Lukas Moser, Thomas Moragues, Andrew J. deMello, Tomaso Zambelli, Martin Ehrbar   +9 more
wiley   +1 more source

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

3D‐Printed Sulfur‐Derived Polymers With Controlled Architectures for Lithium‐Sulfur Batteries

Advanced Functional Materials, EarlyView.
Rheology‐guided formulation design for direct ink writing enables the fabrication of 3D sulfur copolymer cathodes with controlled architectures for lithium‐sulfur batteries. The printed electrodes exhibit multiscale porosity and high sulfur utilization, delivering enhanced electrochemical performance compared to conventional cast electrodes.
Bin Ling, Haoran Wang, Pan Yang, Rishav Agrawal, Alex R. Neale, Laurence J. Hardwick, Tom Hasell, Esther García‐Tuñón   +7 more
wiley   +1 more source

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

MOFs and COFs in Electronics: Bridging the Gap between Intrinsic Properties and Measured Performance

Advanced Functional Materials, EarlyView.
Metal‐organic frameworks (MOFs) and covalent organic frameworks (COFs) hold promise for advanced electronics. However, discrepancies in reported electrical conductivities highlight the importance of measurement methodologies. This review explores intrinsic charge transport mechanisms and extrinsic factors influencing performance, and critically ...
Jonas F. Pöhls, R. Thomas Weitz
wiley   +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

Expanding Chemical Space of Nucleic Acid Nanoparticles for Tunable Antiviral‐Like Immunomodulatory Responses and Potent Adjuvant Activity

Advanced Functional Materials, EarlyView.
We introduce a nucleic acid nanoparticle (NANP) platform designed to be rrecognized by the human innate immune system in a regulated manner. By changing chemical composition while maintaining constant architectural parameters, we identify key determinants of immunorecognition enabling the rational design of NANPs with tunable immune activation profiles
Martin Panigaj, Hannah S. Newton, Jian Wang, Laxmi Pandey, Yelixza I. Avilla, Phong Nguyen, Morgan Chandler, Justin Halman, Yasmine Radwan, Stephanie Smith, Elijah Edmondson, Simone Difilippantonio, Chelsea Sanders, Bao Tran, Yongmei Zhao, Shaojun Xie, Edward Cedrone, Barry W. Neun, Meni Wanunu, Nikolay V. Dokholyan, Marina A. Dobrovolskaia, Kirill A. Afonin   +21 more
wiley   +1 more source

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