Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Investigating Length Bias and Robustness in LVLMs for Multiple-Choice Question Answering
Md. Atabuzzaman, Hani Alomari, Chris Thomas
Large Vision-Language Models (LVLMs) demonstrate strong performance on multiple-choice question answering (MCQA), yet their reliability under biased conditions remains underexplore…
cs.CV2026
Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning
Kazi Sajeed Mehrab, Hani Alomari, Najibul Haque Sarker +4
Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace t…
cs.CV2026
NEST: Narrative Event Structures in Time for Long Video Understanding
Ali Asgarov, Kaushik Narasimhan, Najibul Haque Sarker +6
Recent progress in vision-language models has enabled processing of increasingly long video sequences, but handling extended token streams does not translate to understanding compl…