Zobrazeno 1 - 10
of 3 434
pro vyhledávání: '"Kuai P"'
Learning a self-supervised Monocular Depth Estimation (MDE) model with great generalization remains significantly challenging. Despite the success of adversarial augmentation in the supervised learning generalization, naively incorporating it into se
Externí odkaz:
http://arxiv.org/abs/2411.02149
Based on the group structure search method of first principles, MnB, MnB2, and MnB6 monolayer two-dimensional systems were designed and their structure, stability, electronic properties, as well as performance as anodes for sodium-ion batteries were
Externí odkaz:
http://arxiv.org/abs/2411.00536
Recently, research based on pre-trained models has demonstrated outstanding performance in violence surveillance tasks. However, most of them were black-box systems which faced challenges regarding explainability during training and inference process
Externí odkaz:
http://arxiv.org/abs/2410.21991
First-Principles Study Lead-Free Halide Double Perovskite Cs2RhAgX6 and Cs2IrAgX6 (X = Cl, Br and I)
In contrast to lead-based perovskites, double perovskites have attracted considerable interest due to their ability to modulate photovoltaic properties and high stability through elemental control. However, most double perovskites are mainly faced wi
Externí odkaz:
http://arxiv.org/abs/2410.22091
Autor:
Chen, Mingkai, Han, Tianhua, Liu, Cheng, Liang, Shengwen, Yu, Kuai, Dai, Lei, Yuan, Ziming, Wang, Ying, Zhang, Lei, Li, Huawei, Li, Xiaowei
Approximate Nearest Neighbor Search (ANNS), which enables efficient semantic similarity search in large datasets, has become a fundamental component of critical applications such as information retrieval and retrieval-augmented generation (RAG). Howe
Externí odkaz:
http://arxiv.org/abs/2410.15621
Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a handcrafted image
Externí odkaz:
http://arxiv.org/abs/2410.04618
Autor:
Liao, Xishun, Liu, Yifan, Kuai, Chenchen, Ma, Haoxuan, He, Yueshuai, Cao, Shangqing, Stanford, Chris, Ma, Jiaqi
Understanding human mobility patterns is crucial for urban planning, transportation management, and public health. This study tackles two primary challenges in the field: the reliance on trajectory data, which often fails to capture the semantic inte
Externí odkaz:
http://arxiv.org/abs/2410.03788
Autor:
Stanford, Chris, Adari, Suman, Liao, Xishun, He, Yueshuai, Jiang, Qinhua, Kuai, Chenchen, Ma, Jiaqi, Tung, Emmanuel, Qian, Yinlong, Zhao, Lingyi, Zhou, Zihao, Rasheed, Zeeshan, Shafique, Khurram
Collecting real-world mobility data is challenging. It is often fraught with privacy concerns, logistical difficulties, and inherent biases. Moreover, accurately annotating anomalies in large-scale data is nearly impossible, as it demands meticulous
Externí odkaz:
http://arxiv.org/abs/2409.03024
Autor:
Kuai, Zhirui, Chen, Zuxu, Wang, Huimu, Li, Mingming, Miao, Dadong, Wang, Binbin, Chen, Xusong, Kuang, Li, Han, Yuxing, Wang, Jiaxing, Tang, Guoyu, Liu, Lin, Wang, Songlin, Zhuo, Jingwei
Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and generalization. Notably, methods like TIGER employing Residual Quantiz
Externí odkaz:
http://arxiv.org/abs/2407.21488
Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while LLMs encode t
Externí odkaz:
http://arxiv.org/abs/2406.14673