Multimodal Generative AI: From Production Architectures to Multi-Aspect Evaluation Frameworks
Multimodal Generative AI: From Production Architectures to Multi-Aspect Evaluation Frameworks
Muna Majid Sabah1 Sara Khezeli2 Abdolah Chalechale3
1) Msc. Student, Department of Computer Engineering, Razi University, Kermanshah, Iran Email:
2) Msc. Student, Department of Computer Engineering, Razi University, Kermanshah, Iran Email:
3) Associate Professor, Department of Computer Engineering, Razi University, Kermanshah, Iran Email:
IOI Code
:
AAHD-ABKDDE
Publication :
National Conference on Information Technology, Nanotechnology, Artificial Intelligence and Technological Futures Studies(itnaf.ir)
Abstract :
Recent advances in multimodal generative artificial intelligence have transformed the synthesis and evaluation of multimedia content across text, image, video, audio, and 3D modalities. This paper provides a concise, academically rigorous analysis of the core architectures powering this shift; including Generative Adversarial Networks (GANs), Diffusion Models, Autoregressive Transformers, and Multimodal Large Language Models (MLLMs); focusing on personalized education and digital health deployments. We analyze the limitations of standard statistical distance metrics (FID, FVD) and semantic alignment metrics (CLIPScore) in capturing localized visual anomalies, factual contradictions, and target domain utility. To bridge this gap, we propose a position-based selection framework that integrates multimodal judge models with qualitative error auditing, and introduce an operational governance matrix based on clinical risk and ethical alignment scores. Our findings stress that mitigating the proliferation of generative slop and careless speech requires a transition from purely quantitative metrics to multi-dimensional, human-in-the-loop evaluation frameworks that enforce transparency, safety, and regulatory compliance.
Keywords : multimodal generative ai multimodal large language models (mllms) diffusion transformers (dit) intelligent agents multimedia learning algorithmic evaluation