Zobrazeno 1 - 10
of 4 553
pro vyhledávání: '"Zhang,Xinyi"'
AI-generated content (AIGC), such as advertisement copy, product descriptions, and social media posts, is becoming ubiquitous in business practices. However, the value of AI-generated metadata, such as titles, remains unclear on user-generated conten
Externí odkaz:
http://arxiv.org/abs/2412.18337
Autor:
Shi, Wenhang, Chen, Yiren, Bian, Shuqing, Zhang, Xinyi, Zhao, Zhe, Hu, Pengfei, Lu, Wei, Du, Xiaoyong
Knowledge stored in large language models requires timely updates to reflect the dynamic nature of real-world information. To update the knowledge, most knowledge editing methods focus on the low layers, since recent probes into the knowledge recall
Externí odkaz:
http://arxiv.org/abs/2412.17872
While remarkable success has been achieved through diffusion-based 3D generative models for shapes, 4D generative modeling remains challenging due to the complexity of object deformations over time. We propose DNF, a new 4D representation for uncondi
Externí odkaz:
http://arxiv.org/abs/2412.05161
Autor:
Wang, Chenyu, Gupta, Sharut, Zhang, Xinyi, Tonekaboni, Sana, Jegelka, Stefanie, Jaakkola, Tommi, Uhler, Caroline
Multimodal representation learning seeks to relate and decompose information inherent in multiple modalities. By disentangling modality-specific information from information that is shared across modalities, we can improve interpretability and robust
Externí odkaz:
http://arxiv.org/abs/2410.23996
Autor:
Zhang, Xinyi, Günther, Manuel
Face recognition in the wild has gained a lot of focus in the last few years, and many face recognition models are designed to verify faces in medium-quality images. Especially due to the availability of large training datasets with similar condition
Externí odkaz:
http://arxiv.org/abs/2410.01498
Autor:
Cui, Qinpeng, Liu, Yixuan, Zhang, Xinyi, Bao, Qiqi, Liao, Qingmin, Wang, Li, Lu, Tian, Liu, Zicheng, Wang, Zhongdao, Barsoum, Emad
Diffusion-based image super-resolution (SR) models have attracted substantial interest due to their powerful image restoration capabilities. However, prevailing diffusion models often struggle to strike an optimal balance between efficiency and perfo
Externí odkaz:
http://arxiv.org/abs/2409.17778
Autor:
Zhang, Xinyi, Zhao, Hanyu, Xiao, Wencong, Jia, Xianyan, Xu, Fei, Li, Yong, Lin, Wei, Liu, Fangming
The era of large deep learning models has given rise to advanced training strategies such as 3D parallelism and the ZeRO series. These strategies enable various (re-)configurable execution plans for a training job, which exhibit remarkably different
Externí odkaz:
http://arxiv.org/abs/2408.08586
OpenFlow switches are fundamental components of software defined networking, where the key operation is to look up flow tables to determine which flow an incoming packet belongs to. This needs to address the same multi-field rule-matching problem as
Externí odkaz:
http://arxiv.org/abs/2408.04390
Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve
Externí odkaz:
http://arxiv.org/abs/2408.02922
Autor:
Li, Yiyan, Li, Haoyang, Pu, Zhao, Zhang, Jing, Zhang, Xinyi, Ji, Tao, Sun, Luming, Li, Cuiping, Chen, Hong
Knob tuning plays a crucial role in optimizing databases by adjusting knobs to enhance database performance. However, traditional tuning methods often follow a Try-Collect-Adjust approach, proving inefficient and database-specific. Moreover, these me
Externí odkaz:
http://arxiv.org/abs/2408.02213