collaborators

5 papers

cs.CV2026

Physics-Based Benchmarking Metrics for Multimodal Synthetic Images

Kishor Datta Gupta, Marufa Kamal, Md. Mahfuzur Rahman +3

Current state of the art measures like BLEU, CIDEr, VQA score, SigLIP-2 and CLIPScore are often unable to capture semantic or structural accuracy, especially for domain-specific or…

cs.CV2026

VLCE: A Knowledge-Enhanced Framework for Image Description in Disaster Assessment

Md. Mahfuzur Rahman, Kishor Datta Gupta, Marufa Kamal +5

General-purpose vision-language models (VLMs) such as LLaVA and QwenVL produce descriptions of disaster imagery that lack domain-specific vocabulary and actionable detail. We propo…

cs.LG2025

Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules

Kishor Datta Gupta, Mohd Ariful Haque, Marufa Kamal +3

Traditional clustering techniques often rely solely on similarity in the input data, limiting their ability to capture structural or semantic constraints that are critical in many…

cs.AI2025

Continuous Monitoring of Large-Scale Generative AI via Deterministic Knowledge Graph Structures

Kishor Datta Gupta, Mohd Ariful Haque, Hasmot Ali +3

Generative AI (GEN AI) models have revolutionized diverse application domains but present substantial challenges due to reliability concerns, including hallucinations, semantic dri…

cs.SE2025

SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment

Ariful Haque, Sunzida Siddique, Md. Mahfuzur Rahman +5

The integration of Large Language Models (LLMs) such as GitHub Copilot, ChatGPT, Cursor AI, and Codeium AI into software development has revolutionized the coding landscape, offeri…