• Research Human–AI interaction, studying how users collaborate with large language models in complex problem-solving tasks such as coding.

• Design and analyze ethnographic studies of AI use, combining qualitative research methods with computational analysis of interaction logs.

• Work with Prof. Emma Wiles to develop insights on how AI systems can be made more equitable and accessible across different user groups.

• Mentor: Prof. Emma Wiles

• Understanding Human-AI Interactions by analyzing interactions between different Users and LLMs for problem-solving tasks like coding.

• Employing ethnographic strategies.

• Using Qualitative Research Methods to make AI equally useful to all.

• Conducted independent and collaborative research in AI, generative modeling, and multimodal learning at Boston University.

• Developed an agentic parental-control web app utilizing LangGraph for intelligent screen monitoring and behavior prediction.

• Led a data-driven analysis of MBTA data, employing XGBoost and Random Forest models to forecast ridership and service reliability.

• Prepared research reports and technical documentation, contributing to the academic and AI community.

• Instructor: Prof. Deepti Ghadiyaram

• Course: CASCS 599 G1 - Advanced Topics in Computer Vision

• Mentor graduate and Ph.D. students on projects in computer vision, generative AI, and multimodal learning.

• Evaluate research papers and experiments focusing on ablation studies.

• Contributed to rubric design, enhancing feedback on technical clarity and research rigor.

• Mentored by Professor Brian Kulis

• Developed long context music generation models using Mamba based state space architectures.

• Compared transformer and Mamba pipelines for melody coherence, stability, and scalability.

• Built an experimental workflow using EnCodec tokenization at 24 kHz and 32 kHz with multi-codebook setups.

• Evaluated model quality with CLAP similarity and FAD and used the results to refine architecture choices.

• Prototyped hybrid designs that combine diffusion stages with Mamba sequence modeling.