5 papers
Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding
Anik De, Abhirama Subramanyam Penamakuri, Rajeev Yadav +6
Reading scene text, that is, text appearing in images, has numerous application areas, including assistive technology, search, and e-commerce. Although scene text recognition in En…
PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis
K Lokesh, Abhirama Subramanyam Penamakuri, Uday Agarwal +4
Traditionally, AI research in medical diagnosis has largely centered on image analysis. While this has led to notable advancements, the absence of patient-reported symptoms continu…
When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs
Abhirama Subramanyam Penamakuri, Navlika Singh, Piyush Arora +1
Large Vision-Language Models (L-VLMs) have demonstrated remarkable performance in various vision and language tasks, including visual question answering (VQA). However, their high…
Mind the (Language) Gap: Towards Probing Numerical and Cross-Lingual Limits of LVLMs
Somraj Gautam, Abhirama Subramanyam Penamakuri, Abhishek Bhandari +1
We introduce MMCRICBENCH-3K, a benchmark for Visual Question Answering (VQA) on cricket scorecards, designed to evaluate large vision-language models (LVLMs) on complex numerical a…
Audiopedia: Audio QA with Knowledge
Abhirama Subramanyam Penamakuri, Kiran Chhatre, Akshat Jain
In this paper, we introduce Audiopedia, a novel task called Audio Question Answering with Knowledge, which requires both audio comprehension and external knowledge reasoning. Unlik…