9 papers
Beyond OCR Accuracy: Text-Centric VQA Under Image Degradation with Modular and End-to-End
Ritali Vatsi, Rachapudi Jagadeesh, Shruti Singh Baghel +3
Text-centric Visual Question Answering (VQA) requires reading and reasoning over text embedded in images, a task made substantially harder when images suffer from real-world degrad…
DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
Rahul Mehta, Kavin R, Indrajit Pal +3
Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQAC. DocQAC aims to enhance sea…
Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs
Sandeep Mishra, Devichand Budagam, Anubhab Mandal +3
Real-time multimodal auto-completion is essential for digital assistants, chatbots, design tools, and healthcare consultations, where user inputs rely on shared visual context. We…
Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals
Shruti Singh Baghel, Yash Pratap Singh Rathore, Sushovan Jena +4
Large Vision-Language Models (VLMs) excel at understanding and generating video descriptions but their high memory, computation, and deployment demands hinder practical use particu…
Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics
Kavin R, Pawan Goyal
Standard language models employ unique, monolithic embeddings for each token, potentially limiting their ability to capture the multifaceted nature of word meanings. We investigate…
Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems
Sandeep Mishra, Anubhab Mandal, Bishal Santra +3
Ghosting, the ability to predict a user's intended text input for inline query auto-completion, is an invaluable feature for modern search engines and chat interfaces, greatly enha…
Can MLLMs generate human-like feedback in grading multimodal short answers?
Pritam Sil, Pushpak Bhattacharyya, Pawan Goyal +1
In education, the traditional Automatic Short Answer Grading (ASAG) with feedback problem has focused primarily on evaluating text-only responses. However, real-world assessments o…
ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models
Yaswanth Narsupalli, Abhranil Chandra, Sreevatsa Muppirala +2
Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for eval…
DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit
Jivnesh Sandhan, Yaswanth Narsupalli, Sreevatsa Muppirala +4
Multi-component compounding is a prevalent phenomenon in Sanskrit, and understanding the implicit structure of a compound's components is crucial for deciphering its meaning. Earli…