Zobrazeno 1 - 10
of 9 824
pro vyhledávání: '"SUN, Yuan"'
DNN-based language models perform excellently on various tasks, but even SOTA LLMs are susceptible to textual adversarial attacks. Adversarial texts play crucial roles in multiple subfields of NLP. However, current research has the following issues.
Externí odkaz:
http://arxiv.org/abs/2412.12478
In current multimodal tasks, models typically freeze the encoder and decoder while adapting intermediate layers to task-specific goals, such as region captioning. Region-level visual understanding presents significant challenges for large-scale visio
Externí odkaz:
http://arxiv.org/abs/2412.10348
Autor:
Yang, Wenzhe, Wang, Sheng, Huang, Shixun, Liao, Yuyang, Sun, Yuan, Freire, Juliana, Peng, Zhiyong
There has been increased interest in data search as a means to find relevant datasets or data points in data lakes and repositories. Although approaches have been proposed to support spatial dataset search and data point search, they consider the two
Externí odkaz:
http://arxiv.org/abs/2412.04805
Language models based on deep neural networks are vulnerable to textual adversarial attacks. While rich-resource languages like English are receiving focused attention, Tibetan, a cross-border language, is gradually being studied due to its abundant
Externí odkaz:
http://arxiv.org/abs/2412.02371
The k-means algorithm can simplify large-scale spatial vectors, such as 2D geo-locations and 3D point clouds, to support fast analytics and learning. However, when processing large-scale datasets, existing k-means algorithms have been developed to ac
Externí odkaz:
http://arxiv.org/abs/2412.02244
Autor:
Pargoo, Navid Salami, Ghasemi, Mahshid, Xia, Shuren, Turkcan, Mehmet Kerem, Ehsan, Taqiya, Zang, Chengbo, Sun, Yuan, Ghaderi, Javad, Zussman, Gil, Kostic, Zoran, Ortiz, Jorge
As urban populations grow, cities are becoming more complex, driving the deployment of interconnected sensing systems to realize the vision of smart cities. These systems aim to improve safety, mobility, and quality of life through applications that
Externí odkaz:
http://arxiv.org/abs/2411.19714
Generating and editing dynamic 3D head avatars are crucial tasks in virtual reality and film production. However, existing methods often suffer from facial distortions, inaccurate head movements, and limited fine-grained editing capabilities. To addr
Externí odkaz:
http://arxiv.org/abs/2411.15732
Large language models (LLMs) excel in high-resource languages but face notable challenges in low-resource languages like Mongolian. This paper addresses these challenges by categorizing capabilities into language abilities (syntax and semantics) and
Externí odkaz:
http://arxiv.org/abs/2411.09492
The cold atom qubit platform emerges as an attractive choice for the next stage of quantum computation research, where a special family of synthetic analytical pulses has considerably improved the experimental performance of Controlled-PHASE Rydberg
Externí odkaz:
http://arxiv.org/abs/2411.09882
Autor:
Dong, Wei, Sun, Yuan, Yang, Yiting, Zhang, Xing, Lin, Zhijun, Yan, Qingsen, Zhang, Haokui, Wang, Peng, Yang, Yang, Shen, Hengtao
A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projecti
Externí odkaz:
http://arxiv.org/abs/2410.22952