Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Xu, Zihan"'
Autor:
Qin, Yulei, Yang, Yuncheng, Guo, Pengcheng, Li, Gang, Shao, Hang, Shi, Yuchen, Xu, Zihan, Gu, Yun, Li, Ke, Sun, Xing
Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and practical. To pi
Externí odkaz:
http://arxiv.org/abs/2408.02085
Text-to-video (T2V) generation models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored. Previous text-to-video benchmarks also neglect this important ability
Externí odkaz:
http://arxiv.org/abs/2407.14505
Autor:
Cui, Xiao, Qin, Yulei, Gao, Yuting, Zhang, Enwei, Xu, Zihan, Wu, Tong, Li, Ke, Sun, Xing, Zhou, Wengang, Li, Houqiang
Knowledge distillation (KD) has been widely adopted to compress large language models (LLMs). Existing KD methods investigate various divergence measures including the Kullback-Leibler (KL), reverse Kullback-Leibler (RKL), and Jensen-Shannon (JS) div
Externí odkaz:
http://arxiv.org/abs/2402.17110
Low Earth Orbit (LEO) satellite networks are rapidly gaining traction today. Although several real-world deployments exist, our preliminary analysis of LEO topology performance with the soon-to-be operational Inter-Satellite Links (ISLs) reveals seve
Externí odkaz:
http://arxiv.org/abs/2402.08988
Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling up-to-date and doma
Externí odkaz:
http://arxiv.org/abs/2311.11691
Autor:
Xu, Zihan, Cho, Youngjun
Mindfulness and relaxation techniques for mental health are increasingly being explored in the human-computer interaction community. Physiological signals and their visualization have often been exploited together in a form of biofeedback with other
Externí odkaz:
http://arxiv.org/abs/2310.14343
In order to appropriately filter multi-modality data sets on a web-scale, it becomes crucial to employ suitable filtering methods to boost performance and reduce training costs. For instance, LAION papers employs the CLIP score filter to select data
Externí odkaz:
http://arxiv.org/abs/2309.13770
Autor:
Gao, Yuting, Liu, Jinfeng, Xu, Zihan, Zhang, Tong Wu Enwei, Liu, Wei, Yang, Jie, Li, Ke, Sun, Xing
During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a challengin
Externí odkaz:
http://arxiv.org/abs/2303.17561
Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence. However, in real
Externí odkaz:
http://arxiv.org/abs/2204.14095
Autor:
Yang, Ruixin, Ma, Shuai, Xu, Zihan, Li, Hang, Liu, Xiaodong, Ling, Xintong, Deng, Xiong, Zhang, Xun, Li, Shiyin
Publikováno v:
IEEE Transactions on Wireless Communications
The bound of the information transmission rate of direct current biased optical orthogonal frequency division multiplexing (DCO-OFDM) for visible light communication (VLC) with finite-alphabet inputs is yet unknown, where the corresponding spectral e
Externí odkaz:
http://arxiv.org/abs/2202.01097