Culture & Research Philosophy
Our interdisciplinary team works at the frontier of natural language processing and human-computer interaction and its intersection, guided by curiosity and scientific rigor:
- Experimental: Conduct reproducible experiments that advance fundamental understanding.
- Computational: Leverage algorithms, models, and coding expertise to tackle challenging questions.
Lab Entry
We welcome students from all disciplines with strong curiosity and a passion for rigorous, original research.
Research Topics
- Topic 1: Human–AI Interaction
We study how AI can be designed to augment rather than replace human abilities. Our focus is on enhancing cognition, creativity, and decision-making while supporting well-being and fairness. We also explore the design of AI-enabled applications such as tutors, interviewers, and mental health companions, with attention to human growth and well-being.
- How can AI enhance human cognition, creativity, decision-making, and well-being while reducing biases?
- What AI-enabled applications (e.g., AI tutors, AI interviewers, mental health chatbots, medical VQA) best support human growth and well-being?
- What design principles and psychological theories ensure these systems are effective?
- Topic 2: Natural Language Processing
Our NLP research explores how to make language and speech technologies more efficient, accessible, and powerful. We investigate training frameworks for compact small language models that retain much of the capability of large models, while also advancing speech recognition, diarization, and mixed-language processing to perform robustly in real-world environments.
- How can we create a framework for training small language models that achieve LLM-like power in targeted domains?
- What methods enable compact models to generalize across tasks with limited data?
- How do we advance speech recognition, diarization, voice cloning and mixed-language processing for real-world environments?
- Topic 3: Neural Architectures & Multimodal Models
Beyond applications, we focus on the foundations of building better models. This includes analyzing neural architectures, adding novel components for improved reasoning, and developing multimodal systems that integrate vision, language, and domain knowledge. We are especially interested in high-impact areas such as medical visual question answering (VQA).
- What architectural innovations improve reasoning and generalization in neural networks?
- How can we design multimodal models that effectively combine text, speech, and vision?
- How can we combine graph, attention, or sequential components for better performance?