4 papers
Do Video-LLMs Actually Watch? Diagnosing Character-Tracking Failures in Long-Form Video
Mohammad Al-Ratrout, Shayla Sharmin, Aditya Raikwar +1
Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across…
Indirect and Direct AI Scaffolding for Computational Problem Posing: A Pilot Experience Report
Shayla Sharmin, Mohammad Fahim Abrar, Mohammad Al-Ratrout +1
Problem posing is a valuable learning activity in computing education, encouraging learners to actively construct, refine, and reflect on problems rather than simply solving them.…
How YouTube Frames ChatGPT Use in Education: An Epistemic Network Analysis with Supporting Multimodal Metadata
Shayla Sharmin, Mohammad Al-Ratrout, Mohammad Fahim Abrar +1
We examine educational YouTube videos through multimodal metadata, such as transcripts, titles, thumbnails, and viewer comments, to investigate how ChatGPT is framed across creator…
AFA: Identity-Aware Memory for Preventing Persona Confusion in Multi-User Dialogue
Mohammad Al-Ratrout, Pavan Uttej Ravva, Shayla Sharmin +3
When multiple people share a single voice assistant, the system conflates their histories: one resident's preferences can leak into another's responses, eroding utility and trust.…