Ankit Mishra — accepted AI-conference papers

2025

From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding

Settaluri Lakshmi Sravanthi, Ankit Mishra, Debjyoti Mondal, Subhadarshi Panda, Rituraj Singh, Pushpak Bhattacharyya

ACL 2025finding

Accurately grounding visual and textual elements within mobile user interfaces (UIs) remains a significant challenge for Vision-Language Models (VLMs). Visual grounding, a critical task in this domain, involves identifying the most relevant UI element or region based on a natural language query—a pr…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

RG-VQA: Leveraging Retriever-Generator Pipelines for Knowledge Intensive Visual Question Answering

Settaluri Lakshmi Sravanthi, Pulkit Agarwal, Debjyoti Mondal, Rituraj Singh, Subhadarshi Panda, Ankit Mishra +4

EMNLP 2025

In this paper, we propose a method to improve the reasoning capabilities of Visual Question Answering (VQA) systems by integrating Dense Passage Retrievers (DPRs) with Vision Language Models (VLMs). While recent works focus on the application of knowledge graphs and chain-of-thought reasoning, we re

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗