2 papers
cs.CV2025
Exploring Diagnostic Prompting Approach for Multimodal LLM-based Visual Complexity Assessment: A Case Study of Amazon Search Result Pages
Divendar Murtadak, Yoon Kim, Trilokya Akula
This study investigates whether diagnostic prompting can improve Multimodal Large Language Model (MLLM) reliability for visual complexity assessment of Amazon Search Results Pages…
cs.HC2025
Multimodal LLM Augmented Reasoning for Interpretable Visual Perception Analysis
Shravan Chaudhari, Trilokya Akula, Yoon Kim +1
In this paper, we advance the study of AI-augmented reasoning in the context of Human-Computer Interaction (HCI), psychology and cognitive science, focusing on the critical task of…