Zobrazeno 1 - 10
of 807
pro vyhledávání: '"Liu, Fangming"'
Autor:
Lu, Yaxi, Yang, Shenzhi, Qian, Cheng, Chen, Guirong, Luo, Qinyu, Wu, Yesai, Wang, Huadong, Cong, Xin, Zhang, Zhong, Lin, Yankai, Liu, Weiwen, Wang, Yasheng, Liu, Zhiyuan, Liu, Fangming, Sun, Maosong
Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper
Externí odkaz:
http://arxiv.org/abs/2410.12361
Autor:
Wang, Junming, Sun, Zekai, Guan, Xiuxian, Shen, Tianxiang, Huang, Dong, Zhang, Zongyuan, Duan, Tianyang, Liu, Fangming, Cui, Heming
Existing AGR navigation systems have advanced in lightly occluded scenarios (e.g., buildings) by employing 3D semantic scene completion networks for voxel occupancy prediction and constructing Euclidean Signed Distance Field (ESDF) maps for collision
Externí odkaz:
http://arxiv.org/abs/2410.05079
Autor:
Lu, Zhenyan, Li, Xiang, Cai, Dongqi, Yi, Rongjie, Liu, Fangming, Zhang, Xiwen, Lane, Nicholas D., Xu, Mengwei
Small language models (SLMs), despite their widespread adoption in modern smart devices, have received significantly less academic attention compared to their large language model (LLM) counterparts, which are predominantly deployed in data centers a
Externí odkaz:
http://arxiv.org/abs/2409.15790
Autor:
Wang, Junming, Huang, Dong, Guan, Xiuxian, Sun, Zekai, Shen, Tianxiang, Liu, Fangming, Cui, Heming
Air-ground robots (AGRs) are widely used in surveillance and disaster response due to their exceptional mobility and versatility (i.e., flying and driving). Current AGR navigation systems perform well in static occlusion-prone environments (e.g., ind
Externí odkaz:
http://arxiv.org/abs/2408.10618
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
Autor:
Sun, Zekai, Guan, Xiuxian, Wang, Junming, Song, Haoze, Qing, Yuhao, Shen, Tianxiang, Huang, Dong, Liu, Fangming, Cui, Heming
The rapid advancements in machine learning techniques have led to significant achievements in various real-world robotic tasks. These tasks heavily rely on fast and energy-efficient inference of deep neural network (DNN) models when deployed on robot
Externí odkaz:
http://arxiv.org/abs/2405.19257
Deep Neural Network (DNN) inference on serverless functions is gaining prominence due to its potential for substantial budget savings. Existing works on serverless DNN inference solely optimize batching requests from one application with a single Ser
Externí odkaz:
http://arxiv.org/abs/2405.05633
Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm called edge model caching.
Externí odkaz:
http://arxiv.org/abs/2405.03990
Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm called edge model caching.
Externí odkaz:
http://arxiv.org/abs/2404.14204
Graft: Efficient Inference Serving for Hybrid Deep Learning with SLO Guarantees via DNN Re-alignment
Deep neural networks (DNNs) have been widely adopted for various mobile inference tasks, yet their ever-increasing computational demands are hindering their deployment on resource-constrained mobile devices. Hybrid deep learning partitions a DNN into
Externí odkaz:
http://arxiv.org/abs/2312.10636