Aadyant Khatri

Aadyant Khatri

Auto-generated profile, based on publicly available information

Aadyant Khatri

Virginia Tech

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2023
Verified
Conference Paper
Open access
PDF file
AAAbdulaziz Alhamadani
Abdulaziz Alhamadani
XZXuchao Zhang
Xuchao Zhang
JHJianfeng He
Jianfeng He
AKAadyant Khatri
Aadyant Khatri
CLChang-Tien Lu
Chang-Tien Lu
Abdulaziz Alhamadani, Xuchao Zhang, Jianfeng He, Aadyant Khatri, Chang-Tien Lu. Proceedings of ArabicNLP 2023. 2023.

22 May 2025 in Journal of Planning Education and Research
Verified
Journal Article
Closed access
FCFanglan Chen
Fanglan Chen
AAAbdulaziz Alhamadani
Abdulaziz Alhamadani
SSShailik Sarkar
Shailik Sarkar
LALulwah AlKulaib
Lulwah AlKulaib
AKAadyant Khatri
Aadyant Khatri
CLChang-Tien Lu
Chang-Tien Lu
This paper establishes a comprehensive ethical framework for urban digital twins (UDTs) to address the limited integration of ethical considerations in their design and implementation. It addresses a critical gap in the literature by providing a structured approach to embed ethics throughout the UDT development lifecycle. The research includes a systematic literature review, an analysis of UDT initiatives, and the development of an ethical framework that integrates co-creation and ethical checks. By embedding ethics at the core of UDT development, this framework provides urban planners and decision-makers with a practical tool to create responsible and sustainable urban ecosystems.

25 January 2025
Verified
Book Chapter
Closed access
PDF file
AKAadyant Khatri
Aadyant Khatri
NENicolas Egierski
Nicolas Egierski
APAshutosh Pochamreddy
Ashutosh Pochamreddy
AAAbdulaziz Alhamadani
Abdulaziz Alhamadani
SSShailik Sarkar
Shailik Sarkar
CLChang-Tien Lu
Chang-Tien Lu

16 February 2025 in arXiv
Verified
Preprint
Open access
PDF file
ANAndrew Neeser
Andrew Neeser
KLKaylen Latimer
Kaylen Latimer
AKAadyant Khatri
Aadyant Khatri
CLChris Latimer
Chris Latimer
NRNaren Ramakrishnan
Naren Ramakrishnan
We present QuOTE (Question-Oriented Text Embeddings), a novel enhancement to retrieval-augmented generation (RAG) systems, aimed at improving document representation for accurate and nuanced retrieval. Unlike traditional RAG pipelines, which rely on embedding raw text chunks, QuOTE augments chunks with hypothetical questions that the chunk can potentially answer, enriching the representation space. This better aligns document embeddings with user query semantics, and helps address issues such as ambiguity and context-dependent relevance. Through extensive experiments across diverse benchmarks, we demonstrate that QuOTE significantly enhances retrieval accuracy, including in multi-hop question-answering tasks. Our findings highlight the versatility of question generation as a fundamental indexing strategy, opening new avenues for integrating question generation into retrieval-based AI pipelines.

24 January 2025
Verified
Book Chapter
Closed access
PDF file
MAMelike Yildiz Aktas
Melike Yildiz Aktas
AKAadyant Khatri
Aadyant Khatri
MAMariam Almutairi
Mariam Almutairi
LALulwah Alkulaib
Lulwah Alkulaib
CLChang-Tien Lu
Chang-Tien Lu

31 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
AAAli Asgarov
Ali Asgarov
USUmid Suleymanov
Umid Suleymanov
AKAadyant Khatri
Aadyant Khatri
Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search strategies, and struggle to effectively combine information from multiple sources. We introduce SIGMA (Search-Augmented On-Demand Knowledge Integration for AGentic Mathematical reAsoning), a unified framework that orchestrates specialized agents to independently reason, perform targeted searches, and synthesize findings through a moderator mechanism. Each agent generates hypothetical passages to optimize retrieval for its analytic perspective, ensuring knowledge integration is both context-sensitive and computation-efficient. When evaluated on challenging benchmarks such as MATH500, AIME, and PhD-level science QA GPQA, SIGMA consistently outperforms both open- and closed-source systems, achieving an absolute performance improvement of 7.4%. Our results demonstrate that multi-agent, on-demand knowledge integration significantly enhances both reasoning accuracy and efficiency, offering a scalable approach for complex, knowledge-intensive problem-solving. We will release the code upon publication.