Research

Research Overview

Our research centers on Edge AI, aiming to build personalized, trustworthy, and efficient AI that meets the needs of diverse users and real-world environments. We develop learning and inference algorithms that enable AI services across edge devices and collaborative computing systems, addressing challenges arising from heterogeneous data, evolving user needs, safety requirements, and limited resources. Our research spans large language and multimodal models, image/video understanding and generation, and embodied AI, including vision-language-action models.

Our Approach

Our research brings together neural representation interpretability, mathematical foundations, and AI systems. We investigate how neural networks represent and process information, and how their internal representations influence model behavior and generalization. By connecting theoretical analysis with empirical investigation, we use these insights to develop principled learning and inference algorithms for personalized, trustworthy, and efficient AI.

1. Personalized AI 

AI systems must adapt to diverse users, downstream tasks, and continually changing environments. We study how models can learn collaboratively from distributed and heterogeneous data without requiring users or institutions to share their private data. We also investigate how foundation models can adapt to individual needs and acquire new knowledge while retaining previously learned capabilities. Our research focuses on collaborative/federated learning, continual learning, and foundation model adaptation, enabling AI to evolve with users and their environments.

2. Trustworthy AI

AI systems should remain safe and reliable as they are trained, adapted, and deployed. We investigate how to preserve safety during fine-tuning and compression, align predictive confidence with actual correctness, and selectively remove unwanted knowledge. Our research spans LLM safety, confidence calibration, and machine unlearning, with an emphasis on maintaining trustworthiness as models and data evolve.

3. Efficient AI

Making capable AI widely accessible requires efficient use of data, computation, memory, and communication. We develop algorithms and systems that reduce the cost of training and inference while preserving model capabilities, with particular attention to the constraints of edge devices. Our research includes parameter-efficient fine-tuning, model compression/quantization, and collaborative/adaptive inference.