8 papers
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…
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…
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…
UrbanInsight: A Distributed Edge Computing Framework with LLM-Powered Data Filtering for Smart City Digital Twins
Kishor Datta Gupta, Md Manjurul Ahsan, Mohd Ariful Haque +2
Cities today generate enormous streams of data from sensors, cameras, and connected infrastructure. While this information offers unprecedented opportunities to improve urban life,…
Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM
Mohd Ariful Haque, Justin Williams, Sunzida Siddique +4
The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions…