Selected work

Representative Papers

Benchmarking AI for low-resource contexts: Thinking beyond leaderboards

May 27, 2026

This study addresses a critical gap in current AI evaluation methodologies, which often overlook the impact of low-resource deployment conditions—such as noisy inputs, limited hardware capabilities, and unstable network connectivity—on system usability. The work proposes a novel evaluation framework that treats the deployed system as the unit of assessment, integrating task performance with real-world deployment contexts across multiple dimensions. Departing from conventional leaderboard-based approaches, the framework tailors evaluation criteria to specific application categories and introduces a standardized reporting system comprising benchmark cards, deployment profiles, and failure-handling mechanisms. By balancing comparability with contextual sensitivity, this approach provides policymakers and practitioners with clear, actionable insights for informed AI deployment decisions.

0 citationsRead paper

Health Sentinel: An AI Pipeline For Real-time Disease Outbreak Detection

Jun 24, 2025

This study addresses the challenge of real-time monitoring of anomalous health events—such as disease outbreaks—in massive online media streams. We propose a multi-stage automated information extraction framework that integrates rule-based matching, event extraction, deduplication and clustering, and machine learning models to achieve end-to-end conversion of unstructured text into structured epidemic events (including time, location, pathogen, case count, etc.). Our key contribution is a lightweight, interpretable hybrid pipeline robust to high-noise web content, enabling accurate detection and low-false-positive filtering. Deployed since April 2022, the system has processed over 300 million articles, identified 95,000 distinct health events, and validated 3,500+ as potential outbreaks—prompting timely public health interventions. This significantly enhances early-warning timeliness and response efficiency.

0 citationsRead paper

Recent publications

Latest Papers

Benchmarking AI for low-resource contexts: Thinking beyond leaderboards

May 27, 2026

This study addresses a critical gap in current AI evaluation methodologies, which often overlook the impact of low-resource deployment conditions—such as noisy inputs, limited hardware capabilities, and unstable network connectivity—on system usability. The work proposes a novel evaluation framework that treats the deployed system as the unit of assessment, integrating task performance with real-world deployment contexts across multiple dimensions. Departing from conventional leaderboard-based approaches, the framework tailors evaluation criteria to specific application categories and introduces a standardized reporting system comprising benchmark cards, deployment profiles, and failure-handling mechanisms. By balancing comparability with contextual sensitivity, this approach provides policymakers and practitioners with clear, actionable insights for informed AI deployment decisions.

0 citationsRead paper

Health Sentinel: An AI Pipeline For Real-time Disease Outbreak Detection

Jun 24, 2025

This study addresses the challenge of real-time monitoring of anomalous health events—such as disease outbreaks—in massive online media streams. We propose a multi-stage automated information extraction framework that integrates rule-based matching, event extraction, deduplication and clustering, and machine learning models to achieve end-to-end conversion of unstructured text into structured epidemic events (including time, location, pathogen, case count, etc.). Our key contribution is a lightweight, interpretable hybrid pipeline robust to high-noise web content, enabling accurate detection and low-false-positive filtering. Deployed since April 2022, the system has processed over 300 million articles, identified 95,000 distinct health events, and validated 3,500+ as potential outbreaks—prompting timely public health interventions. This significantly enhances early-warning timeliness and response efficiency.

0 citationsRead paper