Zobrazeno 1 - 10
of 2 137
pro vyhledávání: '"Liu Shengzhong"'
Autor:
Kimura, Tomoyoshi, Li, Jinyang, Wang, Tianshi, Kara, Denizhan, Chen, Yizhuo, Hu, Yigong, Wang, Ruijie, Wigness, Maggie, Liu, Shengzhong, Srivastava, Mani, Diggavi, Suhas, Abdelzaher, Tarek
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a class of) IoT applications. A case study is presented featuring a vehicle
Externí odkaz:
http://arxiv.org/abs/2404.02461
Autor:
Wang, Tianshi, Li, Jinyang, Wang, Ruijie, Kara, Denizhan, Liu, Shengzhong, Wertheimer, Davis, Viros-i-Martin, Antoni, Ganti, Raghu, Srivatsa, Mudhakar, Abdelzaher, Tarek
This paper introduces SudokuSens, a generative framework for automated generation of training data in machine-learning-based Internet-of-Things (IoT) applications, such that the generated synthetic data mimic experimental configurations not encounter
Externí odkaz:
http://arxiv.org/abs/2402.02275
Autor:
Liu, Shengzhong, Kimura, Tomoyoshi, Liu, Dongxin, Wang, Ruijie, Li, Jinyang, Diggavi, Suhas, Srivastava, Mani, Abdelzaher, Tarek
This paper proposes a novel contrastive learning framework, called FOCAL, for extracting comprehensive features from multimodal time-series sensing signals through self-supervised training. Existing multimodal contrastive frameworks mostly rely on th
Externí odkaz:
http://arxiv.org/abs/2310.20071
Autor:
Guo, Hongpeng, Tian, Beitong, Yang, Zhe, Chen, Bo, Zhou, Qian, Liu, Shengzhong, Nahrstedt, Klara, Danilov, Claudiu
Deep learning video analytic systems process live video feeds from multiple cameras with computer vision models deployed on edge or cloud. To optimize utility for these systems, which usually corresponds to query accuracy, efficient bandwidth managem
Externí odkaz:
http://arxiv.org/abs/2306.15129
Autor:
Wang, Ruijie, Li, Baoyu, Lu, Yichen, Sun, Dachun, Li, Jinning, Yan, Yuchen, Liu, Shengzhong, Tong, Hanghang, Abdelzaher, Tarek F.
This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \textit{false negative issue} (i.e., potential true facts being excluded) and \textit{false positive issue} (i.e., unreliable or outdated facts being
Externí odkaz:
http://arxiv.org/abs/2306.07512
Autor:
Liu, Shengzhong1 (AUTHOR) sl29@illinois.edu, Yao, Shuochao2 (AUTHOR) shuochao@gmu.edu, Fu, Xinzhe3 (AUTHOR) xinzhe@mit.edu, Tabish, Rohan1 (AUTHOR) rtabish@illinois.edu, Yu, Simon1 (AUTHOR) jundayu2@illinois.edu, Bansal, Ayoosh1 (AUTHOR) ayooshb2@illinois.edu, Yun, Heechul4 (AUTHOR) heechul.yun@ku.edu, Sha, Lui1 (AUTHOR) lrs@illinois.edu, Abdelzaher, Tarek1 (AUTHOR) zaher@illinois.edu
Publikováno v:
Communications of the ACM. Feb2024, Vol. 67 Issue 2, p110-117. 8p.
Autor:
Wang, Ruijie, Li, Zheng, Sun, Dachun, Liu, Shengzhong, Li, Jinning, Yin, Bing, Abdelzaher, Tarek
In this paper, we investigate a realistic but underexplored problem, called few-shot temporal knowledge graph reasoning, that aims to predict future facts for newly emerging entities based on extremely limited observations in evolving graphs. It offe
Externí odkaz:
http://arxiv.org/abs/2210.08654
Autor:
Qin, Ru, Wu, Yin, Ding, Zicheng, Li, Pengcheng, Zhuang, Zhihua, Li, Ruipeng, Huang, Wenliang, Gao, Zhaomin, Hua, Jiayi, Liu, Shengzhong Frank, Han, Yanchun, Zhao, Kui
Publikováno v:
In Polymer 15 November 2024 313
Autor:
Zhang, Junqi a, Gao, Fei a, ⁎, Wang, Zhiteng a, Li, Yanyang a, Lang, Lei a, Zhou, Tianxiang a, Li, Rui a, Yang, Fei a, Tian, Qingwen a, ⁎, Liu, Shengzhong (Frank) a, b, c, ⁎⁎
Publikováno v:
In Nano Energy March 2025 135
Autor:
Chen, Jiyang, Yu, Simon, Tabish, Rohan, Bansal, Ayoosh, Liu, Shengzhong, Abdelzaher, Tarek, Sha, Lui
Object detection in state-of-the-art Autonomous Vehicles (AV) framework relies heavily on deep neural networks. Typically, these networks perform object detection uniformly on the entire camera LiDAR frames. However, this uniformity jeopardizes the s
Externí odkaz:
http://arxiv.org/abs/2111.09799