Culture & Research Philosophy
Our interdisciplinary team works at the frontier of natural language processing and human-computer interaction, 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
We focus on thought-provoking, high-impact questions in AI and HCI.
Topic 1: Small Language Models (SLM)- How small can a language model get before its reasoning and generative capabilities collapse?
- Can we distill complex knowledge into compact models without losing robustness or generalization?
- How can SLMs adapt to new domains or languages with minimal data?
Topic 2: Multilingual & Mixed-Language Speech Recognition- How do humans switch effortlessly between languages, and can machines emulate this ability?
- Can we create robust recognition systems for low-resource languages and mixed-language conversations?
- What are the limits of speaker diarization in noisy, real-world environments?
Topic 3: Voice Cloning & Talking Avatars- Is it possible to replicate a person’s voice with only seconds of audio without artifacts?
- How do we make talking avatars convey emotion and personality convincingly?
- What are the ethical boundaries in creating hyper-realistic synthetic voices and avatars?
Topic 4: LLMs that Truly Understand Humans- Can a machine model human beliefs, values, and biases without replicating harmful stereotypes?
- How can LLMs reason about human emotion and culture in context-sensitive ways?
- Is it possible to quantify and evaluate “understanding” in a machine?