Zobrazeno 1 - 10
of 2 725
pro vyhledávání: '"Ching, Yun"'
The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various feature extrac
Externí odkaz:
http://arxiv.org/abs/2411.19117
Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this paper, we inv
Externí odkaz:
http://arxiv.org/abs/2411.00348
Autor:
Ko, Ching-Yun, Chen, Pin-Yu, Das, Payel, Mroueh, Youssef, Dan, Soham, Kollias, Georgios, Chaudhury, Subhajit, Pedapati, Tejaswini, Daniel, Luca
Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning the LLM us
Externí odkaz:
http://arxiv.org/abs/2410.03818
Autor:
Hong-Jie Dai, Chien-Chang Chen, Tatheer Hussain Mir, Ting-Yu Wang, Chen-Kai Wang, Ya-Chen Chang, Shu-Jung Yu, Yi-Wen Shen, Cheng-Jiun Huang, Chia-Hsuan Tsai, Ching-Yun Wang, Hsiao-Jou Chen, Pei-Shan Weng, You-Xiang Lin, Sheng-Wei Chen, Ming-Ju Tsai, Shian-Fei Juang, Su-Ying Wu, Wen-Tsung Tsai, Ming-Yii Huang, Chih-Jen Huang, Chih-Jen Yang, Ping-Zun Liu, Chiao-Wen Huang, Chi-Yen Huang, William Yu Chung Wang, Inn-Wen Chong, Yi-Hsin Yang
Publikováno v:
Computational and Structural Biotechnology Journal, Vol 24, Iss , Pp 322-333 (2024)
Data curation for a hospital-based cancer registry heavily relies on the labor-intensive manual abstraction process by cancer registrars to identify cancer-related information from free-text electronic health records. To streamline this process, a na
Externí odkaz:
https://doaj.org/article/b655b90ca42f4ec79453b90abf9ffd50
Autor:
Kao-Jung Chang, Li-Yang Shiau, Shiuan-Chen Lin, Han-Ping Cheong, Ching-Yun Wang, Chun Ma, Yan-Wen Liang, Yi-Ping Yang, Po-Shen Ko, Chih-Hung Hsu, Shih-Hwa Chiou
Publikováno v:
Molecular Medicine, Vol 30, Iss 1, Pp 1-20 (2024)
Abstract N6-methyladenosine (m6A) RNA modification orchestrates cellular epitranscriptome through tuning the homeostasis of transcript stability, translation efficiency, and the transcript affinity toward RNA-binding proteins (RBPs). An aberrant m6A
Externí odkaz:
https://doaj.org/article/b30dd08c10fa428ba34a5d7d33ccc174
Publikováno v:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, pages 9174-9193
Research on text-to-image generation (TTI) still predominantly focuses on the English language due to the lack of annotated image-caption data in other languages; in the long run, this might widen inequitable access to TTI technology. In this work, w
Externí odkaz:
http://arxiv.org/abs/2305.19216
Autor:
Wang, Peiqi, Liu, Yingcheng, Ko, Ching-Yun, Wells, William M., Berkowitz, Seth, Horng, Steven, Golland, Polina
Self-supervised representation learning on image-text data facilitates crucial medical applications, such as image classification, visual grounding, and cross-modal retrieval. One common approach involves contrasting semantically similar (positive) a
Externí odkaz:
http://arxiv.org/abs/2304.13181
Autor:
Yi‐Cheng Pan, Pei‐Yi Chu, Ching‐Chan Lin, Ching‐Yun Hsieh, Wei‐Yu Hsu, Lie‐Fen Shyur, Juan‐Cheng Yang, Wei‐Chao Chang, Yang‐Chang Wu
Publikováno v:
Molecular Oncology, Vol 18, Iss 8, Pp 1866-1884 (2024)
Bladder cancer poses a significant challenge to chemotherapy due to its resistance to cisplatin, especially at advanced stages. Understanding the mechanisms behind cisplatin resistance is crucial for improving cancer therapy. The enzyme glutathione S
Externí odkaz:
https://doaj.org/article/2b592489dea7445fbc623aa501dcb1dd
Autor:
Ching-Yun Wang, Shiuan-Chen Lin, Kao-Jung Chang, Han-Ping Cheong, Sin-Rong Wu, Cheng-Hao Lee, Ming-Wei Chuang, Shih-Hwa Chiou, Chih-Hung Hsu, Po-Shen Ko
Publikováno v:
Heliyon, Vol 10, Iss 21, Pp e39731- (2024)
Acute myeloid leukemia (AML) establishes an immunosuppressive microenvironment that favors leukemic proliferation. The immune-suppressive cytokines altered antigen processing, and presentation collectively assist AML cells in escaping cytotoxic T-cel
Externí odkaz:
https://doaj.org/article/0001cda48d5940b9b687baadbf3fa768
Recent success in fine-tuning large models, that are pretrained on broad data at scale, on downstream tasks has led to a significant paradigm shift in deep learning, from task-centric model design to task-agnostic representation learning and task-spe
Externí odkaz:
http://arxiv.org/abs/2210.02989