Zobrazeno 1 - 10
of 234
pro vyhledávání: '"Zhu, Dongxiao"'
Autor:
Qiang, Yao, Zhou, Xiangyu, Zade, Saleh Zare, Roshani, Mohammad Amin, Zytko, Douglas, Zhu, Dongxiao
The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where adversaries insert backdoor trigg
Externí odkaz:
http://arxiv.org/abs/2402.13459
Autor:
Zhu, Zhiyu, Chen, Huaming, Zhang, Jiayu, Wang, Xinyi, Jin, Zhibo, Xue, Minhui, Zhu, Dongxiao, Choo, Kim-Kwang Raymond
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome. N
Externí odkaz:
http://arxiv.org/abs/2312.13630
Autor:
Khanduri, Prashant, Li, Chengyin, Sultan, Rafi Ibn, Qiang, Yao, Kliewer, Joerg, Zhu, Dongxiao
Recently, compositional optimization (CO) has gained popularity because of its applications in distributionally robust optimization (DRO) and many other machine learning problems. Large-scale and distributed availability of data demands the developme
Externí odkaz:
http://arxiv.org/abs/2311.12652
Autor:
Sultan, Rafi Ibn, Li, Chengyin, Zhu, Hui, Khanduri, Prashant, Brocanelli, Marco, Zhu, Dongxiao
The Segment Anything Model (SAM) has shown impressive performance when applied to natural image segmentation. However, it struggles with geographical images like aerial and satellite imagery, especially when segmenting mobility infrastructure includi
Externí odkaz:
http://arxiv.org/abs/2311.11319
In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the precondition prompts. Despite its promising performance, ICL suffers from instab
Externí odkaz:
http://arxiv.org/abs/2311.09948
Brain tumor segmentation presents a formidable challenge in the field of Medical Image Segmentation. While deep-learning models have been useful, human expert segmentation remains the most accurate method. The recently released Segment Anything Model
Externí odkaz:
http://arxiv.org/abs/2310.06162
Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it post hoc}
Externí odkaz:
http://arxiv.org/abs/2309.08035
Autor:
Qin, Hong, Kong, Jude, Ding, Wandi, Ahluwalia, Ramneek, Morr, Christo El, Engin, Zeynep, Effoduh, Jake Okechukwu, Hwa, Rebecca, Guo, Serena Jingchuan, Seyyed-Kalantari, Laleh, Muyingo, Sylvia Kiwuwa, Moore, Candace Makeda, Parikh, Ravi, Schwartz, Reva, Zhu, Dongxiao, Wang, Xiaoqian, Zhang, Yiye
Artificial intelligence (AI) can potentially transform global health, but algorithmic bias can exacerbate social inequities and disparity. Trustworthy AI entails the intentional design to ensure equity and mitigate potential biases. To advance trustw
Externí odkaz:
http://arxiv.org/abs/2309.05088
Autor:
Li, Chengyin, Khanduri, Prashant, Qiang, Yao, Sultan, Rafi Ibn, Chetty, Indrin, Zhu, Dongxiao
Segment Anything Model (SAM) is one of the pioneering prompt-based foundation models for image segmentation and has been rapidly adopted for various medical imaging applications. However, in clinical settings, creating effective prompts is notably ch
Externí odkaz:
http://arxiv.org/abs/2308.14936
Vision Transformer (ViT) has recently gained significant attention in solving computer vision (CV) problems due to its capability of extracting informative features and modeling long-range dependencies through the attention mechanism. Whereas recent
Externí odkaz:
http://arxiv.org/abs/2301.13803