AI-Guided Learning: integrated support for the Consume-Understand-Imitate cycle

Design · All designs
Evidence · 3 claims (3 for) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 3 claims rest on one study

Description

The dissertation proposes AI-Guided Learning, an integrated approach in which deep learning systems provide adaptive support at each of three interrelated stages of learning from audio and video: Consume (efficient content consumption), Understand (deep comprehension), and Imitate (skill acquisition). The author states the framework "provides necessary support at each stage as learners progress through three interconnected phases" and stresses that AI functions as a guide that reduces cognitive load while maintaining learner autonomy, rather than automating tasks wholesale. Three subsystems (AIxSpeed, FastPerson, Profy) instantiate the stages.

Design Implications

Context

Requirements

• Deep learning models capable of extracting features from audio, video, and text streams for each stage
• Coordination among subsystems so learners can move cyclically between stages

Constraints

• The author notes the CUI model is an organizing framework proposed in the dissertation rather than an empirically established sequence
• Current limitations include the need for long-term effect validation and extension beyond audio-visual domains

Target Learners

• Self-directed online learners of long-form audio and video content
• Second-language learners practicing pronunciation

Learning Goals

• Efficient consumption of long-form audio-visual content
• Deep comprehension of lecture content
• Skill acquisition through imitation of expert models

Claims

• Aixspeed Adaptive Playback Higher Listenability [+M]
• Fastperson Halves Viewing Time No Quiz Loss [+M]
• Profy Intelligibility Gain Over Elicited Imitation [+M]

Related Designs

Examples

-

Key Sources

• Kazuki Kawamura. (2025). AI-Guided Learning: Research on Knowledge and Skill Acquisition Support Methods Using Deep Learning Audio-Video Processing Techniques. Doctoral dissertation, The University of Tokyo. https://arxiv.org/abs/2608.08990

Page metadata

Field	Value
type	design
id	ai-guided-learning-cui-framework
title	AI-Guided Learning: integrated support for the Consume-Understand-Imitate cycle
description	The dissertation proposes AI-Guided Learning, an integrated approach in which deep learning systems provide adaptive support at each of three interrelated stages of learning from audio and video: Consume (efficient co...
status	review
generated	by process:settle-candidates on 2026-10-10
trust	unverified — no one has confirmed this page's content
sources	1 — kazuki-kawamura-2025

Frontmatter is the page's machine-readable record — see the Schema & Guide.