Research
Trajectory-user linking identifies the likely user behind an anonymous mobility trace, but existing methods often lose fine-grained spatial, temporal, and semantic information or scale poorly.…
This project studies how to make the reasoning produced by medical LLMs more factually reliable, not just their final answers. We construct controlled incorrect rationales with known clinically…
This project studies when error detection and intervention can reliably improve multi-agent LLM systems, where mistakes from one agent may propagate through later interactions and affect the team’s…
Personalized Federated Test-Time Adaptation studies how decentralized models can adapt to changing domains while also remaining robust to severe class imbalance across clients. Existing federated…
Federated Test-Time Adaptation (FTTA) studies how decentralized models can adapt to client-specific distribution shifts at test time using unlabeled local data, without sharing raw data. This project…
Source-Free Federated Test-Time Prompt Tuning (SF-FTTPT) studies how vision-language models can collaboratively adapt prompts at test time when clients have private, heterogeneous data with no access…
Large language models serve speakers of hundreds of languages, yet most of what is known about their inner workings comes from English. Recent interpretability research shows that abstract concepts,…
Modern spoken language systems convert raw audio into compact discrete representations that downstream models generate from and reason over. The central constraint is compression: as few tokens per…
Large language models learn to predict sequences from nothing but text, yet human communication was never just words. Every sentence is accompanied by gesture: the hands, the shoulders, the tilt of a…
This project develops a unified framework for reliable multimodal document understanding in low-resource and multilingual settings It consists of four complementary parts that progressively test…
PACER (Personalized Adaptive Coaching for Engagement and Reflection) is an agentic AI tutoring system for IUB courses in Computer Programming |, Computer Programming II and Data Structure. While LLMs…
LangTutor is an agentic AI tutor that decides what to teach next after each learner response, combining pedagogical methods such as scaffolding, hint-based guidance, retrieval practice, spaced…
35 projects
