On-device language models: A comprehensive review

J Xu, Z Li, W Chen, Q Wang, X Gao, Q Cai… - arxiv preprint arxiv …, 2024 - arxiv.org
The advent of large language models (LLMs) revolutionized natural language processing
applications, and running LLMs on edge devices has become increasingly attractive for …

Multi-layer transformers gradient can be approximated in almost linear time

Y Liang, Z Sha, Z Shi, Z Song, Y Zhou - arxiv preprint arxiv:2408.13233, 2024 - arxiv.org
The computational complexity of the self-attention mechanism in popular transformer
architectures poses significant challenges for training and inference, and becomes the …

[HTML][HTML] Intelligent Cockpits for Connected Vehicles: Taxonomy, Architecture, Interaction Technologies, and Future Directions

F Gao, X Ge, J Li, Y Fan, Y Li, R Zhao - Sensors, 2024 - mdpi.com
Highly integrated information sharing among people, vehicles, roads, and cloud systems,
along with the rapid development of autonomous driving technologies, has spurred the …

An embedded end-to-end voice assistant

L Lazzaroni, F Bellotti, R Berta - Engineering Applications of Artificial …, 2024 - Elsevier
Voice assistants are spreading in various environments, such as houses and cars, bringing
the possibility of controlling heterogeneous Internet of Things devices with simple voice …

Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention

A Orzikulova, H **ao, Z Li, Y Yan, Y Wang… - Proceedings of the CHI …, 2024 - dl.acm.org
Despite a rich history of investigating smartphone overuse intervention techniques, AI-based
just-in-time adaptive intervention (JITAI) methods for overuse reduction are lacking. We …

Comparative analysis of ChatGPT-4 and LLaMA: Performance evaluation on text summarization, data analysis, and question answering

SR Bogireddy, N Dasari - 2024 15th International Conference …, 2024 - ieeexplore.ieee.org
ChatGPT has demonstrated the strong performance of large language models (LLMs) in
natural language tasks since its November 2022 rollout by using vast datasets with trillions …

MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention

R Wu, C Yu, X Pan, Y Liu, N Zhang, Y Fu… - Proceedings of the CHI …, 2024 - dl.acm.org
Problematic smartphone use negatively affects physical and mental health. Despite the wide
range of prior research, existing persuasive techniques are not flexible enough to provide …

ChatIoT: Zero-code Generation of Trigger-action Based IoT Programs

Y Gao, K **ao, F Li, W Xu, J Huang… - Proceedings of the ACM on …, 2024 - dl.acm.org
Trigger-Action Program (TAP) is a simple but powerful format to realize intelligent IoT
applications, especially in home automation scenarios. Existing trace-driven approaches …

Chatbots in knowledge-intensive contexts: Comparing intent and llm-based systems

SK Freire, C Wang, E Niforatos - arxiv preprint arxiv:2402.04955, 2024 - arxiv.org
Cognitive assistants (CA) are chatbots that provide context-aware support to human workers
in knowledge-intensive tasks. Traditionally, cognitive assistants respond in specific ways to …

Unvoiced: Designing an LLM-assisted Unvoiced User Interface using Earables

T Srivastava, P Khanna, S Pan, P Nguyen… - Proceedings of the 22nd …, 2024 - dl.acm.org
We present Unvoiced, a novel unvoiced user interface that leverages jaw motion to enable
users to silently interact with their devices using earables. The core idea is to translate low …