Zobrazeno 1 - 10
of 2 800
pro vyhledávání: '"ZHANG, YICHI"'
Autor:
Chen, Sihan, Qian, Zhuangzhuang, Siu, Wingchun, Hu, Xingcan, Li, Jiaqi, Li, Shawn, Qin, Yuehan, Yang, Tiankai, Xiao, Zhuo, Ye, Wanghao, Zhang, Yichi, Dong, Yushun, Zhao, Yue
Outlier detection (OD), also known as anomaly detection, is a critical machine learning (ML) task with applications in fraud detection, network intrusion detection, clickstream analysis, recommendation systems, and social network moderation. Among op
Externí odkaz:
http://arxiv.org/abs/2412.12154
A longstanding problem of deep learning models is their vulnerability to adversarial examples, which are often generated by applying imperceptible perturbations to natural examples. Adversarial examples exhibit cross-model transferability, enabling t
Externí odkaz:
http://arxiv.org/abs/2411.16782
Autor:
Zhao, Haozhe, Si, Shuzheng, Chen, Liang, Zhang, Yichi, Sun, Maosong, Zhang, Mingjia, Chang, Baobao
Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on images an
Externí odkaz:
http://arxiv.org/abs/2411.14279
Autor:
Guo, Lingbing, Bo, Zhongpu, Chen, Zhuo, Zhang, Yichi, Chen, Jiaoyan, Lan, Yarong, Sun, Mengshu, Zhang, Zhiqiang, Luo, Yangyifei, Li, Qian, Zhang, Qiang, Zhang, Wen, Chen, Huajun
Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal halluc
Externí odkaz:
http://arxiv.org/abs/2410.07526
Background: Liver cancer ranks as the fifth most common malignant tumor and the second most fatal in our country. Early diagnosis is crucial, necessitating that physicians identify liver cancer in patients at the earliest possible stage. However, the
Externí odkaz:
http://arxiv.org/abs/2410.18090
How can we automatically select an out-of-distribution (OOD) detection model for various underlying tasks? This is crucial for maintaining the reliability of open-world applications by identifying data distribution shifts, particularly in critical do
Externí odkaz:
http://arxiv.org/abs/2410.03074
Autor:
Chen, Liang, Tan, Sinan, Cai, Zefan, Xie, Weichu, Zhao, Haozhe, Zhang, Yichi, Lin, Junyang, Bai, Jinze, Liu, Tianyu, Chang, Baobao
This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts more codes
Externí odkaz:
http://arxiv.org/abs/2410.01912
This paper presents a unified framework for bond-associated peridynamic material correspondence models that were proposed to inherently address the issue of material instability or existence of zero-energy modes in the conventional correspondence for
Externí odkaz:
http://arxiv.org/abs/2410.00934
The discontinuous operations inherent in quantization and sparsification introduce obstacles to backpropagation. This is particularly challenging when training deep neural networks in ultra-low precision and sparse regimes. We propose a novel, robust
Externí odkaz:
http://arxiv.org/abs/2409.09245
Autor:
Zhang, Yichi, Sitharam, Meera
Volume calculation of configurational spaces acts as a vital part in configurational entropy calculation, which contributes towards calculating free energy landscape for molecular systems. In this article, we present our sampling-based volume computa
Externí odkaz:
http://arxiv.org/abs/2408.16946