11 papers
TriCLE: Tri-Modal Vision-Language Reasoning for Edge-Deployed Fine-Grained Clustering
Kishor Datta Gupta, Md. Mahfuzur Rahman, Fahad Rahman +4
Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This setting is difficult for stand…
GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Language Models
Mohd Ariful Haque, Fahad Rahman, Kishor Datta Gupta +1
Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all change over time. Static bias be…
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…
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…
Verbatim Data Transcription Failures in LLM Code Generation: A State-Tracking Stress Test
Mohd Ariful Haque, Kishor Datta Gupta, Mohammad Ashiqur Rahman +1
Many real-world software tasks require exact transcription of provided data into code, such as cryptographic constants, protocol test vectors, allowlists, and calibration tables. T…
TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
Mohd Ariful Haque, Fahad Rahman, Kishor Datta Gupta +2
This paper investigates the effectiveness of small language models (SLMs) for agentic tasks (function/tool/API calling) with a focus on running agents on edge devices without relia…