Uzair Ahmad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Uzair Ahmad has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Algan Tezel
1 shared publication- Ayaz Aghayev
Brigham and Women’s Hospital
1 shared publication Bekir Sait Ciftler
1 shared publication- Fargana Aghayeva
Department of Radiology, Brigham and Women’s Hospital, Mass General Brigham, Boston, MA 02115, USA
1 shared publication - Farhan Dhanani
Department of Computer Science, National University of Computer and Emerging Sciences, Islamabad, Karachi, Sindh, Pakistan
1 shared publication Hamna Uzair
1 shared publication
Latest Publications
- Open Access
RegVis: An interactive web-based visualization system for linear regression analysis and diagnostics
- Open Access
- 23 June 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3870
Agentic table talk
The article presents a heuristic-driven solution called Agentic Table Talk, which utilizes general-purpose Large Language Models (LLMs) to solve the problem of Table Question Answering (Tabular Q/A). The goal of this task is to answer the user query based on the provided table. Earlier approaches required whole tables to prompt LLMs. As tables can grow infinitely large, directly incorporating entire tables into prompts becomes infeasible due to the finite context window of LLMs, which can only handle a limited number of input tokens. In contrast, some approaches are entirely driven by Retrieval Augmented Generation (RAG) to ground the LLMs with K relevant records where the value of K is predefined and hard coded. The main drawback of such approaches is that they do not yield satisfactory results for Tabular Q/A, where data is structured and cellular. Additionally, the meaning of individual cells is often context-dependent and can vary substantially based on the values of neighboring cells. To address these challenges, this article proposes a novel combination of a lightweight heuristic called RAGular SubGraph Retrieval combined with the ReAct Agentic Framework powered by general-purpose LLMs. In this combination, the proposed heuristic adopts the core principles of traditional RAG while placing greater emphasis on preserving the neighborhood relationships of the selected cells. The ReAct Agent receives the user query along with the filtered tabular data as a subgraph that is assumed to be part of a larger, unknown graph. The output from the heuristic guides the subsequent ReAct Agent with a focused input context that consists of only relevant cells and their neighborhood, based on the given input query. The primary objective of the ReAct Agent is to use explicit reasoning to identify the facts necessary to answer the provided user query. This may involve reasoning over the known subgraph or taking actions (such as re-triggering the heuristic with a slightly modified query or finding the closest K-Adjacent neighbors of a relevant cell) to explore new, unexplored cells based on the structure of the already known regions. Both components work together iteratively to discover relevant facts for generating an authentic answer to the user query based on the provided reference table, until the process successfully locates all the necessary information or sufficient confidence in the query’s un-answerability is achieved. The proposed approach is evaluated using general-purpose LLMs of varying sizes on benchmarked AIT-QA ( https://github.com/IBM/AITQA ) and HiTab ( https://github.com/microsoft/HiTab ) datasets, along with a Synthetic Dataset (SD) ( https://github.com/FarhanDhanani/AgenticTableTalk/tree/main/dataset/synthetic ) featuring large tables. The evaluation examines how heuristic-driven input contexts affect the reasoning abilities of LLMs of varying sizes in managing complex tables and compares these results to existing methodologies. The codebase is publicly available on Git (Agentic Table Talk Approach Available At GIT: https://github.com/FarhanDhanani/AgenticTableTalk ) repository, allowing all experiments to be easily re-executed for reproducing the results.
- 23 June 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3870
Open AccessAgentic table talk
The article presents a heuristic-driven solution called Agentic Table Talk, which utilizes general-purpose Large Language Models (LLMs) to solve the problem of Table Question Answering (Tabular Q/A). The goal of this task is to answer the user query based on the provided table. Earlier approaches required whole tables to prompt LLMs. As tables can grow infinitely large, directly incorporating entire tables into prompts becomes infeasible due to the finite context window of LLMs, which can only handle a limited number of input tokens. In contrast, some approaches are entirely driven by Retrieval Augmented Generation (RAG) to ground the LLMs with K relevant records where the value of K is predefined and hard coded. The main drawback of such approaches is that they do not yield satisfactory results for Tabular Q/A, where data is structured and cellular. Additionally, the meaning of individual cells is often context-dependent and can vary substantially based on the values of neighboring cells. To address these challenges, this article proposes a novel combination of a lightweight heuristic called RAGular SubGraph Retrieval combined with the ReAct Agentic Framework powered by general-purpose LLMs. In this combination, the proposed heuristic adopts the core principles of traditional RAG while placing greater emphasis on preserving the neighborhood relationships of the selected cells. The ReAct Agent receives the user query along with the filtered tabular data as a subgraph that is assumed to be part of a larger, unknown graph. The output from the heuristic guides the subsequent ReAct Agent with a focused input context that consists of only relevant cells and their neighborhood, based on the given input query. The primary objective of the ReAct Agent is to use explicit reasoning to identify the facts necessary to answer the provided user query. This may involve reasoning over the known subgraph or taking actions (such as re-triggering the heuristic with a slightly modified query or finding the closest K-Adjacent neighbors of a relevant cell) to explore new, unexplored cells based on the structure of the already known regions. Both components work together iteratively to discover relevant facts for generating an authentic answer to the user query based on the provided reference table, until the process successfully locates all the necessary information or sufficient confidence in the query’s un-answerability is achieved. The proposed approach is evaluated using general-purpose LLMs of varying sizes on benchmarked AIT-QA ( https://github.com/IBM/AITQA ) and HiTab ( https://github.com/microsoft/HiTab ) datasets, along with a Synthetic Dataset (SD) ( https://github.com/FarhanDhanani/AgenticTableTalk/tree/main/dataset/synthetic ) featuring large tables. The evaluation examines how heuristic-driven input contexts affect the reasoning abilities of LLMs of varying sizes in managing complex tables and compares these results to existing methodologies. The codebase is publicly available on Git (Agentic Table Talk Approach Available At GIT: https://github.com/FarhanDhanani/AgenticTableTalk ) repository, allowing all experiments to be easily re-executed for reproducing the results.
- Open Access
- 1 June 2026
- Published by Elsevier in SSRN Electronic Journal
RegVis: An Interactive Web-Based Visualization System for Linear Regression Analysis and Diagnostics
RegVis is an open-source, browser-based interactive visualization system that makes the mathematical mechanics of linear regression directly perceivable through geometric representation, interactive sampling, and coordinated multi-view exploration. The system implements three novel features absent from existing regression tools: (1) geometric error decomposition that renders Sum of Squared Errors (SSE) and Total Sum of Squares (TSS) as visible translucent squares, making $R^2$ observable as a visual area proportion; (2) interactive confidence interval sampling that empirically demonstrates the frequentist ``$t$\% coverage'' definition by accumulating regression lines from repeated random subsets; and (3) a coordinated three-view architecture (scatterplot, residual plot, Q-Q plot) with sub-100ms synchronized updates triggered by direct click-to-add/remove data manipulation. RegVis is implemented in D3.js and requires no installation.- 1 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRegVis: An Interactive Web-Based Visualization System for Linear Regression Analysis and Diagnostics
RegVis is an open-source, browser-based interactive visualization system that makes the mathematical mechanics of linear regression directly perceivable through geometric representation, interactive sampling, and coordinated multi-view exploration. The system implements three novel features absent from existing regression tools: (1) geometric error decomposition that renders Sum of Squared Errors (SSE) and Total Sum of Squares (TSS) as visible translucent squares, making $R^2$ observable as a visual area proportion; (2) interactive confidence interval sampling that empirically demonstrates the frequentist ``$t$\% coverage'' definition by accumulating regression lines from repeated random subsets; and (3) a coordinated three-view architecture (scatterplot, residual plot, Q-Q plot) with sub-100ms synchronized updates triggered by direct click-to-add/remove data manipulation. RegVis is implemented in D3.js and requires no installation. - Open Access
- 8 April 2026
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 74
An agentic framework for data augmentation in construction defect report classification
- 8 April 2026
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 74
Open AccessAn agentic framework for data augmentation in construction defect report classification
- Open Access
- 15 September 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (18) , 2336
Automated Detection and Segmentation of Ascending Aorta Dilation on a Non-ECG-Gated Chest CT Using Deep Learning
Background/Objectives: Ascending aortic (AA) dilation (diameter ≥ 4.0 cm) is a significant risk factor for aortic dissection, yet it often goes unnoticed in routine chest CT scans performed for other indications. This study aimed to develop and evaluate a deep learning pipeline for automated AA segmentation using non-ECG-gated chest CT scans. Methods: We designed a two-stage pipeline integrating a convolutional neural network (CNN) for focus-slice classification and a U-Net-based segmentation model to extract the aortic region. The model was trained and validated on a dataset of 500 non-ECG-gated chest CT scans, encompassing over 50,000 individual slices. Results: On the held-out test set (10%), the model achieved a Dice similarity coefficient (DSC) score of 99.21%, an Intersection over Union (IoU) of 98.45%, and a focus-slice classification accuracy of 98.18%. Compared with traditional rule-based and prior CNN-based methods, the proposed approach achieved markedly higher overlap metrics while maintaining low computational overhead. Conclusions: A lightweight CNN+U-Net deep learning model can enhance diagnostic accuracy, reduce radiologist workload, and enable opportunistic detection of AA dilation in routine chest CT imaging.
- 15 September 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (18) , 2336
Open AccessAutomated Detection and Segmentation of Ascending Aorta Dilation on a Non-ECG-Gated Chest CT Using Deep Learning
Background/Objectives: Ascending aortic (AA) dilation (diameter ≥ 4.0 cm) is a significant risk factor for aortic dissection, yet it often goes unnoticed in routine chest CT scans performed for other indications. This study aimed to develop and evaluate a deep learning pipeline for automated AA segmentation using non-ECG-gated chest CT scans. Methods: We designed a two-stage pipeline integrating a convolutional neural network (CNN) for focus-slice classification and a U-Net-based segmentation model to extract the aortic region. The model was trained and validated on a dataset of 500 non-ECG-gated chest CT scans, encompassing over 50,000 individual slices. Results: On the held-out test set (10%), the model achieved a Dice similarity coefficient (DSC) score of 99.21%, an Intersection over Union (IoU) of 98.45%, and a focus-slice classification accuracy of 98.18%. Compared with traditional rule-based and prior CNN-based methods, the proposed approach achieved markedly higher overlap metrics while maintaining low computational overhead. Conclusions: A lightweight CNN+U-Net deep learning model can enhance diagnostic accuracy, reduce radiologist workload, and enable opportunistic detection of AA dilation in routine chest CT imaging.