Zobrazeno 1 - 10
of 523
pro vyhledávání: '"Zhang, Qingzhao"'
Recent advancements in Large Language Models (LLMs) have significantly increased context window sizes, enabling sophisticated applications but also introducing substantial computational overheads, particularly computing key-value (KV) cache in the pr
Externí odkaz:
http://arxiv.org/abs/2410.03065
Safety is a paramount concern of large language models (LLMs) in their open deployment. To this end, safeguard methods aim to enforce the ethical and responsible use of LLMs through safety alignment or guardrail mechanisms. However, we found that the
Externí odkaz:
http://arxiv.org/abs/2410.02916
Autor:
Jin, Shuowei, Wu, Yongji, Zheng, Haizhong, Zhang, Qingzhao, Lentz, Matthew, Mao, Z. Morley, Prakash, Atul, Qian, Feng, Zhuo, Danyang
Large language models (LLMs) have seen significant adoption for natural language tasks, owing their success to massive numbers of model parameters (e.g., 70B+); however, LLM inference incurs significant computation and memory costs. Recent approaches
Externí odkaz:
http://arxiv.org/abs/2402.12280
Autor:
Wu, Fangzhou, Zhang, Qingzhao, Bajaj, Ati Priya, Bao, Tiffany, Zhang, Ning, Wang, Ruoyu "Fish", Xiao, Chaowei
Large language models (LLMs) have undergone rapid evolution and achieved remarkable results in recent times. OpenAI's ChatGPT, backed by GPT-3.5 or GPT-4, has gained instant popularity due to its strong capability across a wide range of tasks, includ
Externí odkaz:
http://arxiv.org/abs/2312.05275
With the development of data collection techniques, analysis with a survival response and high-dimensional covariates has become routine. Here we consider an interaction model, which includes a set of low-dimensional covariates, a set of high-dimensi
Externí odkaz:
http://arxiv.org/abs/2311.13767
Autor:
Zhang, Qingzhao, Jin, Shuowei, Zhu, Ruiyang, Sun, Jiachen, Zhang, Xumiao, Chen, Qi Alfred, Mao, Z. Morley
Collaborative perception, which greatly enhances the sensing capability of connected and autonomous vehicles (CAVs) by incorporating data from external resources, also brings forth potential security risks. CAVs' driving decisions rely on remote untr
Externí odkaz:
http://arxiv.org/abs/2309.12955
Gene expression-based heterogeneity analysis has been extensively conducted. In recent studies, it has been shown that network-based analysis, which takes a system perspective and accommodates the interconnections among genes, can be more informative
Externí odkaz:
http://arxiv.org/abs/2308.03946
Perception is crucial in the realm of autonomous driving systems, where bird's eye view (BEV)-based architectures have recently reached state-of-the-art performance. The desirability of self-supervised representation learning stems from the expensive
Externí odkaz:
http://arxiv.org/abs/2306.00349
What happens to an autonomous vehicle (AV) if its data are adversarially compromised? Prior security studies have addressed this question through mostly unrealistic threat models, with limited practical relevance, such as white-box adversarial learni
Externí odkaz:
http://arxiv.org/abs/2303.03470
Functional data analysis has been extensively conducted. In this study, we consider a partially functional model, under which some covariates are scalars and have linear effects, while some other variables are functional and have unspecified nonlinea
Externí odkaz:
http://arxiv.org/abs/2301.03705