1 citations · 1 across the 6 of their papers we have counts for
7 papers
MaRVL-QA: A Benchmark for Mathematical Reasoning over Visual Landscapes
Nilay Pande, Sahiti Yerramilli, Jayant Sravan Tamarapalli +1
A key frontier for Multimodal Large Language Models (MLLMs) is the ability to perform deep mathematical and spatial reasoning directly from images, moving beyond their established…
CountQA: How Well Do MLLMs Count in the Wild?
Jayant Sravan Tamarapalli, Rynaa Grover, Nilay Pande +1
Multimodal Large Language Models (MLLMs) demonstrate remarkable fluency in understanding visual scenes, yet they exhibit a critical lack in a fundamental cognitive skill: object co…
HueManity: Probing Fine-Grained Visual Perception in MLLMs
Rynaa Grover, Jayant Sravan Tamarapalli, Sahiti Yerramilli +1
Recent Multimodal Large Language Models (MLLMs) demonstrate strong high-level visual reasoning on tasks such as visual question answering and image captioning. Yet existing benchma…
GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
Sahiti Yerramilli, Nilay Pande, Rynaa Grover +1
This paper introduces GeoChain, a large-scale benchmark for evaluating step-by-step geographic reasoning in multimodal large language models (MLLMs). Leveraging 1.46 million Mapill…
Attribution Regularization for Multimodal Paradigms
Sahiti Yerramilli, Jayant Sravan Tamarapalli, Jonathan Francis +1
Multimodal machine learning has gained significant attention in recent years due to its potential for integrating information from multiple modalities to enhance learning and decis…
Semantic Augmentation in Images using Language
Sahiti Yerramilli, Jayant Sravan Tamarapalli, Tanmay Girish Kulkarni +2
Deep Learning models are incredibly data-hungry and require very large labeled datasets for supervised learning. As a consequence, these models often suffer from overfitting, limit…
MAEA: Multimodal Attribution for Embodied AI
Vidhi Jain, Jayant Sravan Tamarapalli, Sahiti Yerramilli +1
Understanding multimodal perception for embodied AI is an open question because such inputs may contain highly complementary as well as redundant information for the task. A releva…