cv

Student Researcher

MIT

Working under Prof. Antonio Torralba on visual generation with multimodal LLMs.

• Co-first author of Doodle Agent: Exploring Freeform Visual Generation with Multimodal LLMs (Accepted to ICCV 2025 AI4VA Workshop), a drawing agent for open-ended visual creation using LLMs and structured prompting.

Student Researcher

MIT

Working under Prof. Leslie Pack Kaelbling on few-shot concept discovery and robotic manipulation using diffusion policies with vision-language conditioning.

• Developed few-shot concept discovery framework, implementing diffusion policy with vision-language conditioning for robotic manipulation.
• Built comprehensive computer vision pipeline integrating ResNet18 encoders, text embedding networks, and classifier-free guidance for diffusion policy, achieving robust policy adaptation from minimal demonstrations.
• Engineered benchmarking system with custom dataset loaders, advanced optimization techniques (AdamW, EMA), and Weights & Biases tracking, evaluating generalization across 12 distinct object-language configurations.

RSI Scholar

Research Science Institute (RSI)

Authored research paper on quantum circuit synthesis under mentorship of Henry Ma (MIT).

• Authored the paper "CNOT-Optimal Circuit Synthesis" under the mentorship of Henry Ma (MIT); Selected as the top 5 paper at RSI out of 100 candidates.

T-Spark Scholar

Tencent

Selected for Tencent's T-Spark program, a highly competitive research initiative for high school students.

• Selected for Tencent's T-Spark program, a highly competitive research initiative for high school students.
• Optimized machine learning models for video recommendation systems, focusing on improving personalization accuracy.

Researcher

MIT PRIMES

Conducted research on NUMA-aware data structures and benchmarking, and studied advanced mathematical topics.

• Conducted research on NUMA-aware data structures and benchmarking under Shangdi Yu and Prof. Julian Shun.
• Studied advanced mathematical topics including coding theory, game theory, topology, and representation theory.
• Presented research findings at the annual MIT PRIMES mini-conference.

Participant

Yau International Mathcamp

Completed advanced coursework in mathematics and presented research findings.

• Completed advanced coursework in linear algebra, algebraic combinatorics, analysis, and topology.
• Selected to present a final project proving Kirchhoff's Matrix-Tree Theorem.

B.S.

Massachusetts Institute of Technology

Mathematics and Computer Science

• Fundamentals of Probability (6.7700)
• Discrete Probability and Stochastic Processes (18.619)
• Deep Learning (6.7960)
• NLP (6.4610)
• Computer Graphics (6.4400)
• Advanced Algorithms (6.5210)
• Machine Learning (6.7900)

High School Diploma

Phillips Academy Andover

High School

William Lowell Putnam Mathematical Competition — Rank 254

Mathematical Association of America

Regeneron Science Talent Search — Top 300 Scholar

Society for Science

MathWorks Math Modeling Challenge — National Champion

MathWorks

Harvard-MIT Mathematics Tournament (HMMT) — 2nd Place, Combinatorics Round

Harvard-MIT Mathematics Tournament

United States of America Mathematical Olympiad (USAMO) — Honorable Mention

Mathematical Association of America

United States of America Computing Olympiad (USACO) — Finalist

USA Computing Olympiad

United States of America Physics Olympiad (USAPhO) — Bronze Medalist

American Association of Physics Teachers

United States of America Junior Mathematical Olympiad (USAJMO) — Top 24

Mathematical Association of America

Doodle Agent: Exploring Freeform Visual Generation with Multimodal LLMs

ICCV 2025 AI4VA Workshop

Co-first author. A drawing agent for open-ended visual creation using LLMs and structured prompting. Accepted to ICCV 2025 AI4VA Workshop.

CNOT-Optimal Circuit Synthesis

Research Science Institute

Authored under the mentorship of Henry Ma (MIT). Selected as the top 5 paper at RSI out of 100 candidates.