News
Papers, awards, talks and milestones, newest first.
2026
Released the project page for IMUdrape: Generating Garment-Mounted Virtual IMU Data from Text through Physics-Based Cloth Simulation, currently under review. IMUdrape simulates the garment a smart-clothing deployment uses and reads virtual IMUs off the fabric. Project page · code (coming soon)
Our paper StitchSense: Smart-Garment Sensing as a Source Domain for Watch-Based Activity Recognition appears in the proceedings of ISWC 2026 (UbiComp/ISWC 2026, Shanghai).
Our paper EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning was accepted to IMWUT. It releases synchronized EEG, ECG, PPG, EDA, IMU, skin-temperature and eye-tracking data with minute-level engagement ratings, plus a benchmark. Project page · code · dataset
Started a Machine Learning Engineer internship at Behavior AI.
2025
Our paper Can We Hide Machines in the Crowd? Quantifying Equivalence in LLM-in-the-loop Annotation Tasks was accepted and presented at SIGIR-AP 2025.
Our paper AgentSense: Virtual Sensor Data Generation Using LLM Agents in Simulated Home Environments was accepted at AAAI 2026. Project page · code
Our paper Towards More Equitable Ulcer Recognition Models: A Dataset of Naturalistic Foot Images from People of Color Living with Diabetes was accepted at the IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).
Our paper Characterising Topic Familiarity and Query Specificity Using Eye-Tracking Data was accepted and presented at SIGIR 2025.
Released a preprint, Scaling Human Activity Recognition: A Comparative Evaluation of Synthetic Data Generation and Augmentation Techniques, which benchmarks synthetic data generation against classical augmentation for HAR.
Our abstract 259-OR: Evaluating Diabetic Foot Ulcer Recognition Algorithms for Patients of Color was published in Diabetes as part of the American Diabetes Association Scientific Sessions.
2024
Our paper Emotion Recognition on the Go: Utilizing Wearable IMUs for Personalized Emotion Recognition was accepted and presented at HASCA within UbiComp/ISWC 2024.
Our paper More Data for People with Disabilities! Comparing Data Collection Efforts for Wheelchair Transportation Mode Detection was published at ISWC and presented at UbiComp/ISWC 2024, where it received a Best Paper Nomination.
Our paper IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition was published in IMWUT. Project page · code
Started my PhD in Computer Science at Georgia Tech.
Received the Provost's Academic Excellence Award as the most outstanding graduating senior in Georgia Tech's College of Computing.
Presented my research on IMUGPT at the ACC Meeting of the Minds conference, as one of five undergraduates selected to represent Georgia Tech.
Awarded the NSF Graduate Research Fellowship (GRFP), which funds three years of my PhD over a five-year period.
Awarded the Georgia Tech President's Fellowship and the Georgia Tech Institute Fellowship to fund my PhD.
2023
Our paper Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition (IMUGPT) was published at ISWC and received the Best Paper Honorable Mention at UbiComp/ISWC 2023. It was also covered in Georgia Tech news.
Our paper On the Utility of Virtual On-body Acceleration Data for Fine-grained Human Activity Recognition was published at ISWC and presented at UbiComp/ISWC 2023.
Our paper On the Benefit of Generative Foundation Models for Human Activity Recognition was accepted and presented at the Generative AI for Pervasive Computing (GenAI4PC) Symposium within UbiComp/ISWC 2023.
Our paper FingerSpeller: Camera-Free Text Entry Using Smart Rings for American Sign Language Fingerspelling Recognition was accepted and presented at ASSETS 2023.
Received a President’s Undergraduate Research Award, with a salary stipend and a travel grant to present at UbiComp/ISWC 2023.
Started a summer internship at Argonne National Laboratory, accelerating graph neural networks for ocean simulation.