Zobrazeno 1 - 10
of 22 437
pro vyhledávání: '"Wang,Han"'
Infrared small target detection (ISTD) is challenging due to complex backgrounds, low signal-to-clutter ratios, and varying target sizes and shapes. Effective detection relies on capturing local contextual information at the appropriate scale. Howeve
Externí odkaz:
http://arxiv.org/abs/2412.17401
As small unmanned aerial vehicles (UAVs) become increasingly prevalent, there is growing concern regarding their impact on public safety and privacy, highlighting the need for advanced tracking and trajectory estimation solutions. In response, this p
Externí odkaz:
http://arxiv.org/abs/2412.12698
Lithium is a typical quantum solid, characterized by cubic structures at ambient pressure. As the pressure increases, it forms more complex structures and undergoes a metal-to-semiconductor transformation, complicating theoretical and experimental an
Externí odkaz:
http://arxiv.org/abs/2412.12451
Autor:
Yin, Tianyi, Wang, Jingwei, Ma, Yunlong, Wang, Han, Wang, Chenze, Zhao, Yukai, Liu, Min, Shen, Weiming, Chen, Yufeng
Encoding time series into tokens and using language models for processing has been shown to substantially augment the models' ability to generalize to unseen tasks. However, existing language models for time series forecasting encounter several obsta
Externí odkaz:
http://arxiv.org/abs/2412.12226
Fractonic many-body systems are characterized by mobility restrictions on single-particle hopping due to the conservation of higher moments (e.g., dipoles, angular momenta, and quadrupoles). This conservation allows the definition of new symmetries a
Externí odkaz:
http://arxiv.org/abs/2412.10280
Autor:
Li, Bingru, Wang, Han
The capacity of LLMs to carry out automated qualitative analysis has been questioned by corpus linguists, and it has been argued that corpus-based discourse analysis incorporating LLMs is hindered by issues of unsatisfying performance, hallucination,
Externí odkaz:
http://arxiv.org/abs/2412.10139
Autor:
Wang, Han, Nie, Yuxiang, Ye, Yongjie, GuanYu, Deng, Wang, Yanjie, Li, Shuai, Yu, Haiyang, Lu, Jinghui, Huang, Can
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image understanding,
Externí odkaz:
http://arxiv.org/abs/2412.09530
As natural disasters become increasingly frequent, the need for efficient and equitable evacuation planning has become more critical. This paper proposes a data-driven, reinforcement learning-based framework to optimize bus-based evacuations with an
Externí odkaz:
http://arxiv.org/abs/2412.05777
The proliferation of Connected Automated Vehicles represents an unprecedented opportunity for improving driving efficiency and alleviating traffic congestion. However, existing research fails to address realistic multi-lane highway scenarios without
Externí odkaz:
http://arxiv.org/abs/2412.02520
Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing, adversarial train
Externí odkaz:
http://arxiv.org/abs/2411.16721