About

I’m a PhD student at UCLA advised by Prof. Vwani Roychowdhury. My research centers on continual learning, memory, and reasoning in language models and agents: how these systems can learn from experience, adapt to changing tasks and environments, and ground their answers in evidence.

My work spans structured memory and retrieval with Generative Semantic Workspaces, continual learning through external memory with Panini, and deep research with PANINI-DR.

During my internships at AWS, I studied continual learning in enterprise agents, including how to evaluate adaptation when organizational rules change, and explored how non-parametric continual learning methods compare with tabular foundation models for forecasting.

I’ve also spent consecutive summers at NVIDIA contributing to Project G-Assist, an on-device AI assistant. My work spanned the entire stack, from tool-use data acquisition and fine-tuning to retrieval, evaluation, and inference optimization.

I’m also interested in AI for science and healthcare, with work on DNA sequence alignment, clinical information extraction, and clinical decision support. In these settings, I’m particularly interested in uncertainty calibration—making confidence scores reflect how often predictions are correct—and using uncertainty to guide deferral to experts.

Research focus

• Continual learning and memory for language models
• Post-training of language models
• Information retrieval, deep research, and agent reasoning
• Evaluation, verification, and uncertainty calibration
• Efficient models and on-device agents
• AI for science and healthcare

Contact

• Email: {{ with site.Params.email }}[{{ . }}](mailto:{{ . }}){{ end }}
• GitHub: {{ with site.Params.github }}[{{ . }}]({{ . }}){{ end }}
• LinkedIn: {{ with site.Params.linkedin }}[{{ . }}]({{ . }}){{ end }}
• X: {{ with site.Params.x }}[{{ . }}]({{ . }}){{ end }}
• Scholar: {{ with site.Params.scholar }}[{{ . }}]({{ . }}){{ end }}
• CV: {{ with site.Params.cv }}[PDF]({{ . }}){{ end }}