MLLM embeddings predict population-level video interaction peaks as cognitive load proxies, generalize across academic fields, and link to interpretable instructional design concepts via theory-coded features.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scalable and Explainable Learner-Video Interaction Prediction using Multimodal Large Language Models
MLLM embeddings predict population-level video interaction peaks as cognitive load proxies, generalize across academic fields, and link to interpretable instructional design concepts via theory-coded features.