4 citations · 5 across the 6 of their papers we have counts for
7 papers
Evaluating VQA in Vision Language Models using Cooperative Principles
Monika Shah, Sudarshan Balaji, Somdeb Sarkhel +2
We evaluate the performance of Vision Language Models in Visual Question Answering (VQA) when questions violate Grice's maxims. To do this, we use VLMs to generate question modifie…
Analyzing the Sensitivity of Vision Language Models in Visual Question Answering
Monika Shah, Sudarshan Balaji, Somdeb Sarkhel +2
We can think of Visual Question Answering as a (multimodal) conversation between a human and an AI system. Here, we explore the sensitivity of Vision Language Models (VLMs) through…
On Explaining Visual Captioning with Hybrid Markov Logic Networks
Monika Shah, Somdeb Sarkhel, Deepak Venugopal
Deep Neural Networks (DNNs) have made tremendous progress in multimodal tasks such as image captioning. However, explaining/interpreting how these models integrate visual informati…
Disentangling Fine-Tuning from Pre-Training in Visual Captioning with Hybrid Markov Logic
Monika Shah, Somdeb Sarkhel, Deepak Venugopal
Multimodal systems have highly complex processing pipelines and are pretrained over large datasets before being fine-tuned for specific tasks such as visual captioning. However, it…
Verifying Relational Explanations: A Probabilistic Approach
Abisha Thapa Magar, Anup Shakya, Somdeb Sarkhel +1
Explanations on relational data are hard to verify since the explanation structures are more complex (e.g. graphs). To verify interpretable explanations (e.g. explanations of predi…
Mastery Guided Non-parametric Clustering to Scale-up Strategy Prediction
Anup Shakya, Vasile Rus, Deepak Venugopal
Predicting the strategy (sequence of concepts) that a student is likely to use in problem-solving helps Adaptive Instructional Systems (AISs) better adapt themselves to different t…
On the verification of Embeddings using Hybrid Markov Logic
Anup Shakya, Abisha Thapa Magar, Somdeb Sarkhel +1
The standard approach to verify representations learned by Deep Neural Networks is to use them in specific tasks such as classification or regression, and measure their performance…