Zobrazeno 1 - 10
of 586
pro vyhledávání: '"Wang, QiuFeng"'
Vision models excel in image classification but struggle to generalize to unseen data, such as classifying images from unseen domains or discovering novel categories. In this paper, we explore the relationship between logical reasoning and deep learn
Externí odkaz:
http://arxiv.org/abs/2410.04492
Autor:
Huang, Baoru, Vo, Tuan, Kongtongvattana, Chayun, Dagnino, Giulio, Kundrat, Dennis, Chi, Wenqiang, Abdelaziz, Mohamed, Kwok, Trevor, Jianu, Tudor, Do, Tuong, Le, Hieu, Nguyen, Minh, Nguyen, Hoan, Tjiputra, Erman, Tran, Quang, Xie, Jianyang, Meng, Yanda, Bhattarai, Binod, Tan, Zhaorui, Liu, Hongbin, Gan, Hong Seng, Wang, Wei, Yang, Xi, Wang, Qiufeng, Su, Jionglong, Huang, Kaizhu, Stefanidis, Angelos, Guo, Min, Du, Bo, Tao, Rong, Vu, Minh, Zheng, Guoyan, Zheng, Yalin, Vasconcelos, Francisco, Stoyanov, Danail, Elson, Daniel, Baena, Ferdinando Rodriguez y, Nguyen, Anh
Real-time visual feedback from catheterization analysis is crucial for enhancing surgical safety and efficiency during endovascular interventions. However, existing datasets are often limited to specific tasks, small scale, and lack the comprehensive
Externí odkaz:
http://arxiv.org/abs/2408.13126
Autor:
Zhou, Zihao, Liu, Shudong, Ning, Maizhen, Liu, Wei, Wang, Jindong, Wong, Derek F., Huang, Xiaowei, Wang, Qiufeng, Huang, Kaizhu
Exceptional mathematical reasoning ability is one of the key features that demonstrate the power of large language models (LLMs). How to comprehensively define and evaluate the mathematical abilities of LLMs, and even reflect the user experience in r
Externí odkaz:
http://arxiv.org/abs/2407.08733
While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely introduce s
Externí odkaz:
http://arxiv.org/abs/2312.09486
Document dewarping, aiming to eliminate geometric deformation in photographed documents to benefit text recognition, has made great progress in recent years but is still far from being solved. While Cartesian coordinates are typically leveraged by st
Externí odkaz:
http://arxiv.org/abs/2312.07925
Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks. However, the adversarial examples generated by many mainstream word-level adver
Externí odkaz:
http://arxiv.org/abs/2311.11861
Panoramic Narrative Grounding (PNG) is an emerging visual grounding task that aims to segment visual objects in images based on dense narrative captions. The current state-of-the-art methods first refine the representation of phrase by aggregating th
Externí odkaz:
http://arxiv.org/abs/2310.16616
Shanshui, which means mountain and water, is an East Asian traditional brush painting involving natural landscapes. This paper proposes an interactive and generative system based on a Generative Adversarial Network(GAN), which helps users draw Shansh
Externí odkaz:
http://arxiv.org/abs/2310.19803
Autor:
Zhou, Zihao, Wang, Qiufeng, Jin, Mingyu, Yao, Jie, Ye, Jianan, Liu, Wei, Wang, Wei, Huang, Xiaowei, Huang, Kaizhu
With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking prompts in t
Externí odkaz:
http://arxiv.org/abs/2309.01686
Math word problems (MWPs) require analyzing text descriptions and generating mathematical equations to derive solutions. Existing works focus on solving MWPs with two types of solvers: tree-based solver and large language model (LLM) solver. However,
Externí odkaz:
http://arxiv.org/abs/2308.13844