PulseAugur
EN
LIVE 14:41:48

New framework ELEVATE enables local, avatar-based AI tutors

Researchers have introduced ELEVATE, a framework for developing human-centered generative AI virtual tutors. Unlike cloud-based chatbots, ELEVATE utilizes a local-first execution model for privacy and cost-efficiency, allowing deployment on consumer hardware. The system integrates large language models with embodied 3D avatars for multimodal interaction, and includes a teacher-facing governance layer for pedagogical control. A prototype has been implemented and evaluated within a real-world educational curriculum, demonstrating responsive interaction on standard PCs and smartphones. AI

IMPACT This framework could enable more accessible and privacy-preserving AI tutoring solutions for educational institutions.

RANK_REASON The cluster contains an academic paper detailing a new framework for AI tutors. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New framework ELEVATE enables local, avatar-based AI tutors

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Lorenzo Stacchio, Michele Giordano, Daniele Berardini, Primo Zingaretti, Emanuele Frontoni ·

    ELEVATE: Designing Human-Centered GenAI Virtual Tutors for Scalable and Inclusive Education

    arXiv:2606.30662v1 Announce Type: cross Abstract: The advent of Generative Artificial Intelligence (GenAI), and in particular Large Language Models (LLMs), is reshaping educational practice, while intensifying ethical debate about its adoption. To date, the dominant paradigm rema…