1 code implementation • 7 Nov 2024 • Rongjie Yi, Xiang Li, Weikai Xie, Zhenyan Lu, Chenghua Wang, Ao Zhou, Shangguang Wang, Xiwen Zhang, Mengwei Xu
The interest in developing small language models (SLM) for on-device deployment is fast growing.
1 code implementation • 24 Sep 2024 • Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu
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 and cloud environments.
no code implementations • 9 Sep 2024 • Dongqi Cai, Shangguang Wang, Chen Peng, Zeling Zhang, Mengwei Xu
Human memory is inherently prone to forgetting.
no code implementations • 8 Sep 2024 • Wangsong Yin, Rongjie Yi, Daliang Xu, Gang Huang, Mengwei Xu, Xuanzhe Liu
To address this issue, we introduce ELMS, an on-device LLM service designed to provide elasticity in both the model and prompt dimensions of an LLMaaS.
no code implementations • 21 Aug 2024 • Hanzi Mei, Dongqi Cai, Ao Zhou, Shangguang Wang, Mengwei Xu
Meanwhile, FedMoE progressively adjusts the submodels to optimal through global expert recommendation.
1 code implementation • 8 Jul 2024 • Daliang Xu, Hao Zhang, Liming Yang, Ruiqi Liu, Gang Huang, Mengwei Xu, Xuanzhe Liu
On-device large language models (LLMs) are catalyzing novel mobile applications such as UI task automation and personalized email auto-reply, without giving away users' private data.
1 code implementation • 28 Jun 2024 • Haiyang Shen, Yue Li, Desong Meng, Dongqi Cai, Sheng Qi, Li Zhang, Mengwei Xu, Yun Ma
\textsc{ShortcutsBench} includes a wealth of real APIs from Apple Inc.'s operating systems, refined user queries from shortcuts, human-annotated high-quality action sequences from shortcut developers, and accurate parameter filling values about primitive parameter types, enum parameter types, outputs from previous actions, and parameters that need to request necessary information from the system or user.
no code implementations • 18 May 2024 • Pai Zeng, Zhenyu Ning, Jieru Zhao, Weihao Cui, Mengwei Xu, Liwei Guo, Xusheng Chen, Yizhou Shan
We survey the large language model (LLM) serving area to understand the intricate dynamics between cost-efficiency and accuracy, which is magnified by the growing need for longer contextual understanding when deploying models at a massive scale.
1 code implementation • 12 Apr 2024 • Li Zhang, Shihe Wang, Xianqing Jia, Zhihan Zheng, Yunhe Yan, Longxi Gao, Yuanchun Li, Mengwei Xu
LlamaTouch comprises three key techniques: (1) On-device task execution that enables mobile agents to interact with realistic mobile environments for task execution.
no code implementations • 1 Mar 2024 • Zeling Zhang, Dongqi Cai, Yiran Zhang, Mengwei Xu, Shangguang Wang, Ao Zhou
Communication overhead is a significant bottleneck in federated learning (FL), which has been exaggerated with the increasing size of AI models.
no code implementations • 23 Feb 2024 • Zejun Zhang, Li Zhang, Xin Yuan, Anlan Zhang, Mengwei Xu, Feng Qian
Following OpenAI's introduction of GPTs, a surge in GPT apps has led to the launch of dedicated LLM app stores.
1 code implementation • 16 Jan 2024 • Mengwei Xu, Wangsong Yin, Dongqi Cai, Rongjie Yi, Daliang Xu, QiPeng Wang, Bingyang Wu, Yihao Zhao, Chen Yang, Shihe Wang, Qiyang Zhang, Zhenyan Lu, Li Zhang, Shangguang Wang, Yuanchun Li, Yunxin Liu, Xin Jin, Xuanzhe Liu
Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment.
2 code implementations • 10 Jan 2024 • Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, Yunxin Liu
Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.
no code implementations • 8 Sep 2023 • Daliang Xu, Wangsong Yin, Xin Jin, Ying Zhang, Shiyun Wei, Mengwei Xu, Xuanzhe Liu
Currently, the execution of these generative tasks heavily depends on Large Language Models (LLMs).
1 code implementation • 28 Aug 2023 • Jinliang Yuan, Chen Yang, Dongqi Cai, Shihe Wang, Xin Yuan, Zeling Zhang, Xiang Li, Dingge Zhang, Hanzi Mei, Xianqing Jia, Shangguang Wang, Mengwei Xu
Concurrently, each app contributes a concise, offline fine-tuned "adapter" tailored to distinct downstream tasks.
no code implementations • 28 Aug 2023 • Rongjie Yi, Liwei Guo, Shiyun Wei, Ao Zhou, Shangguang Wang, Mengwei Xu
Large Language Models (LLMs) such as GPTs and LLaMa have ushered in a revolution in machine intelligence, owing to their exceptional capabilities in a wide range of machine learning tasks.
1 code implementation • 26 Aug 2023 • Mengwei Xu, Dongqi Cai, Yaozong Wu, Xiang Li, Shangguang Wang
Federated Learning (FL), a method to preserve user data privacy, is often employed in fine-tuning LLMs to downstream mobile tasks, an approach known as FedLLM.
1 code implementation • 2 May 2023 • Simon Kolker, Louise Dennis, Ramon Fraga Pereira, Mengwei Xu
We propose the use of the hypothetical retrospection argumentation procedure, developed by Sven Ove Hansson to improve existing approaches to machine ethical reasoning by accounting for probability and uncertainty from a position of Philosophy that resonates with humans.
1 code implementation • 12 Dec 2022 • Dongqi Cai, Shangguang Wang, Yaozong Wu, Felix Xiaozhu Lin, Mengwei Xu
Such an inadequacy of data labels is known as a few-shot scenario; it becomes the key blocker for mobile NLP applications.
no code implementations • 1 Dec 2022 • Dongqi Cai, Yaozong Wu, Haitao Yuan, Shangguang Wang, Felix Xiaozhu Lin, Mengwei Xu
To address these challenges, we first introduce a data generator for federated few-shot learning tasks, which encompasses the quantity and skewness of scarce labeled data in a realistic setting.
1 code implementation • 15 Jun 2022 • Rongjie Yi, Ting Cao, Ao Zhou, Xiao Ma, Shangguang Wang, Mengwei Xu
DNNs are ubiquitous on edge devices nowadays.
1 code implementation • 20 May 2022 • Dongqi Cai, Yaozong Wu, Shangguang Wang, Felix Xiaozhu Lin, Mengwei Xu
A key challenge is to properly configure the depth and width of adapters, to which the training speed and efficiency is highly sensitive.
1 code implementation • 14 Feb 2022 • Qiyang Zhang, Xiang Li, Xiangying Che, Xiao Ma, Ao Zhou, Mengwei Xu, Shangguang Wang, Yun Ma, Xuanzhe Liu
Deploying deep learning (DL) on mobile devices has been a notable trend in recent years.
no code implementations • 5 Dec 2021 • Yun Li, Chen Zhang, Shihao Han, Li Lyna Zhang, Baoqun Yin, Yunxin Liu, Mengwei Xu
Human brains are known to be capable of speeding up visual recognition of repeatedly presented objects through faster memory encoding and accessing procedures on activated neurons.
no code implementations • 22 Oct 2020 • Jinliang Yuan, Mengwei Xu, Xiao Ma, Ao Zhou, Xuanzhe Liu, Shangguang Wang
Our proposed FL can accelerate the learning process and reduce the monetary cost with frequent local aggregation in the same LAN and infrequent global aggregation on a cloud across WAN.
no code implementations • 12 Jun 2020 • Chengxu Yang, Qipeng Wang, Mengwei Xu, Zhenpeng Chen, Kaigui Bian, Yunxin Liu, Xuanzhe Liu
Based on the data and the platform, we conduct extensive experiments to compare the performance of state-of-the-art FL algorithms under heterogeneity-aware and heterogeneity-unaware settings.
no code implementations • 15 Feb 2020 • Jinliang Yuan, Mengwei Xu, Yuxin Zhao, Kaigui Bian, Gang Huang, Xuanzhe Liu, Shangguang Wang
To preserve user privacy while enabling mobile intelligence, techniques have been proposed to train deep neural networks on decentralized data.
no code implementations • 2 Sep 2019 • Mengwei Xu, Xiwen Zhang, Yunxin Liu, Gang Huang, Xuanzhe Liu, Felix Xiaozhu Lin
Elf is a runtime for an energy-constrained camera to continuously summarize video scenes as approximate object counts.
Databases
no code implementations • 28 Apr 2019 • Mengwei Xu, Tiantu Xu, Yunxin Liu, Felix Xiaozhu Lin
For efficiency, we advocate for these cameras to be zero streaming: capturing videos to local storage and communicating with the cloud only when analytics is requested.
1 code implementation • 8 Nov 2018 • Mengwei Xu, Jiawei Liu, Yuanqiang Liu, Felix Xiaozhu Lin, Yunxin Liu, Xuanzhe Liu
We are in the dawn of deep learning explosion for smartphones.
1 code implementation • 1 Dec 2017 • Mengwei Xu, Mengze Zhu, Yunxin Liu, Felix Xiaozhu Lin, Xuanzhe Liu
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision.
no code implementations • 1 Dec 2017 • Mengwei Xu, Feng Qian, Mengze Zhu, Feifan Huang, Saumay Pushp, Xuanzhe Liu
Due to their on-body and ubiquitous nature, wearables can generate a wide range of unique sensor data creating countless opportunities for deep learning tasks.