Intelligent Learning
& Efficient Processing.

My research in Intelligent Learning and Efficient Processing explores how AI systems can learn, adapt, and process information more efficiently, because making a model bigger is not always the most interesting solution. My work includes neural voice conversion, few-shot speaker adaptation, memory-augmented learning, and reinforcement-learning-based prompt compression for large language models. Across these projects, I’m interested in building AI systems that can do more with less: less data, less computation, less redundancy, and hopefully fewer GPUs begging for mercy. The broader goal is to develop intelligent models that are not only accurate, but also adaptive, efficient, and practical enough to work outside the lab.