Hi I'm Yingtian. I am a Third year Ph.D. student at Georgia Tech, advised by Prof. Thomas Plötz. My research connects time-series learning, multimodal sensing and AI agents to understand human dynamics and build AI that evolves with us. My long-term goal is to enable Human–AI Co-evolution, where AI learns from people’s changing contexts, needs, and feedback while helping them achieve their goals.
Our preprint Rondo: Unsupervised Discovery of Recurring Temporal Structure, a framework that discovers reusable units and recurring compositions in unlabeled time series, updating its discoveries as new data arrives, is now available on arXiv!
Our paper TRACE, on contextual activity recognition through multimodal sensing and temporal reasoning, has been accepted to ACM IMWUT!
Our paper EduGage, on multimodal sensing for momentary engagement assessment in self-guided learning, has been accepted to ACM IMWUT!
I attended the ACM AI Leadership Summit 2026 in Atlanta.
We released the preprint of TRACE: Temporal Reasoning over Context and Evidence for Activity Recognition in Smart Homes, a framework that combines ambient and wearable sensing with LLM-based temporal reasoning to understand everyday activities in context.
Rondo discovers reusable local units and recurring compositions in unlabeled time series. By combining representation adaptation with variable-length motif modeling, it captures temporal structure at multiple scales and updates its discoveries as new data arrives.
TRACE combines ambient and wearable sensing with personalized routine information and LLM-based temporal reasoning to understand everyday activities in smart homes. It uses broader context to resolve ambiguous observations and produce more temporally coherent activity predictions.
EduGage combines physiological and behavioral sensing to estimate momentary engagement during self-guided video learning. It provides engagement modeling methods and a synchronized multimodal dataset to support research on fine-grained learner understanding and adaptive learning systems.
LLMartini helps users compare and combine responses from multiple language models in a shared interactive workspace. It aligns related content, highlights differences, and supports user-controlled composition to bring together the complementary strengths of different models.
If you're also interested in Human–AI Co-evolution, ubiquitous computing, or multimodal sensing, I'd love to exchange ideas and explore collaborations. Feel free to get in touch.
Contact me
