Lightweight Approach: LLM-Driven Classroom Rehearsal on Apple silicon

Chaoyang University of Technology Institutional Repository > 航空學院 > 航空運務系 > 期刊/會議/專書論文 > Item 310901800/45210

Please use this identifier to cite or link to this item: http://ir.lib.cyut.edu.tw:8080/handle/310901800/45210

Title:	Lightweight Approach: LLM-Driven Classroom Rehearsal on Apple silicon
Authors:	鍾美齡 Liao, Kuo-Chien;Lau, Jirayu;Chung, Meiling;Wu, Chin-Wei;Kuang, Jiong-Rui
Contributors:	航空運務系
Keywords:	AI in education;teaching professional development;simulation-based training;on-device inference;multimodal interaction;YOLO11;virtual student;large language models (LLMs)
Date:	2025-12-17
Abstract:	This study introduces a software system designed to simulate real-time classroom interactions on portable devices, enabling fully on-device artificial intelligence inference. The objective is to leverage the computational capabilities of Apple silicon devices to seamlessly execute large language model (LLM) and computer vision tasks, supporting teacher training and simulation-based learning scenarios. By integrating live OCR (Optical Character Recognition) processing, CoreML-based YOLO (You Only Look Once) object detection, and LLM inference through the Ollama framework, we developed a platform capable of pro-cessing multimodal inputs and delivering instant AI-generated responses in real time. Experimental results confirmed stable performance under con- current AI work-loads, with LLaMA 3.1 (8B parameters) model. Generation speeds scored 17.43 tokens/s with multimodal in-put—slightly lower than the 19.38 tokens/s observed under text-only conditions. Despite the effective performance, limitations re-main, including CoreML optimization complexity for LLM models, possible thermal throttle with the peak GPU utilization, LLM size constraints, the need for fine-tuning to enhance simulation realism, and challenges in cross-platform deployment. While improvements are possible, the results highlight the feasibility of deploying advanced AI-based simulation systems entirely on-device, offering a self-contained, low-latency solution for educational applications.
Relation:	The 14th International Conference on Advanced Materials and Engineering Materials (ICAMEM 2025)
Appears in Collections:	[航空運務系] 期刊/會議/專書論文

Files in This Item:

File	Description	Size	Format
國際研討會摘要初稿-A Lightweight Approach LLM-Driven Classroom Rehearsal on Apple silicon 20251108.pdf	國際研討會摘要初稿-A Lightweight Approach LLM-Driven Classroom Rehearsal on Apple silicon 20251108	70Kb	Adobe PDF	1	View/Open

View Licence

Loading...