Zobrazeno 1 - 10
of 10 779
pro vyhledávání: '"Wang, ZhiQiang"'
Autor:
Wang, Yunli, Yang, Zixuan, Zhang, Zhen, Wang, Zhiqiang, Yang, Jian, Wen, Shiyang, Jiang, Peng, Gai, Kun
The scaling law is a notable property of neural network models and has significantly propelled the development of large language models. Scaling laws hold great promise in guiding model design and resource allocation. Recent research increasingly sho
Externí odkaz:
http://arxiv.org/abs/2411.13322
Autor:
Chen, Siqi, Wang, Zhiqiang, Deng, Xianqi, Shen, Yili, Ju, Cheng-Wei, Yi, Jun, Xiong, Lin, Ling, Guo, Alhmoud, Dieaa, Guan, Hui, Lin, Zhou
Rational design of next-generation functional materials relied on quantitative predictions of their electronic structures beyond single building blocks. First-principles quantum mechanical (QM) modeling became infeasible as the size of a material gre
Externí odkaz:
http://arxiv.org/abs/2411.01578
Audio can disclose PII, particularly when combined with related text data. Therefore, it is essential to develop tools to detect privacy leakage in Contrastive Language-Audio Pretraining(CLAP). Existing MIAs need audio as input, risking exposure of v
Externí odkaz:
http://arxiv.org/abs/2410.18371
As Artificial Intelligence (AI) has developed rapidly over the past few decades, the new generation of AI, Large Language Models (LLMs) trained on massive datasets, has achieved ground-breaking performance in many applications. Further progress has b
Externí odkaz:
http://arxiv.org/abs/2410.19848
Autor:
Aiersilan, Aizierjiang, Wang, Zhiqiang
The advent of 5G has driven the demand for high-quality, low-latency live streaming. However, challenges such as managing the increased data volume, ensuring synchronization across multiple streams, and maintaining consistent quality under varying ne
Externí odkaz:
http://arxiv.org/abs/2410.16284
Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer visual/linguistic
Externí odkaz:
http://arxiv.org/abs/2409.13609
LLMs can exhibit age biases, resulting in unequal treatment of individuals across age groups. While much research has addressed racial and gender biases, age bias remains little explored. The scarcity of instruction-tuning and preference datasets for
Externí odkaz:
http://arxiv.org/abs/2409.04340
With the widespread adoption of smartphones, Android malware has become a significant challenge in the field of mobile device security. Current Android malware detection methods often rely on feature engineering to construct dynamic or static feature
Externí odkaz:
http://arxiv.org/abs/2408.16555
All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents
Autor:
Wang, Zhiqiang, Zheng, Hao, Nie, Yunshuang, Xu, Wenjun, Wang, Qingwei, Ye, Hua, Li, Zhe, Zhang, Kaidong, Cheng, Xuewen, Dong, Wanxi, Cai, Chang, Lin, Liang, Zheng, Feng, Liang, Xiaodan
Embodied AI is transforming how AI systems interact with the physical world, yet existing datasets are inadequate for developing versatile, general-purpose agents. These limitations include a lack of standardized formats, insufficient data diversity,
Externí odkaz:
http://arxiv.org/abs/2408.10899
Quench experiments on a unitary Bose gas around a broad Feshbach resonance have led to the discovery of universal dynamics. This universality is manifested in the measured atomic momentum distributions where, asymptotically, a quasi-equilibrated meta
Externí odkaz:
http://arxiv.org/abs/2408.08415