Master's Theses & Technical Reports - 2025
M.S.
AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World
Paul Zhiyuan Zhou [advisor: Sergey Levine]
Dense integration of compact topological photonic crystal cavities
Yertay Zhiyenbayev [advisor: Boubacar Kanté]
Designing a DNA-Based “Smart Photoresist” Procedure for Electronics Self-Assembly
Erina Iwasa [advisor: Grigory Tikhomirov]
Incentive-Compatible Vertiport Reservation in Advanced Air Mobility: An Auction-Based Approach
Pan-Yang Su [advisor: S. Shankar Sastry]
Learning to Drive by Imitating Surrounding Vehicles
Yasin Sonmez [advisor: Murat Arcak]
Scaling Reasoning Agents Through Learning and Search
Jiayi Pan [advisor: Alane Suhr]
The Free Termination Property of Queries Over Time
Conor Power [advisor: Joseph M. Hellerstein]
To tile or not to tile, that is the question
Altan Haan [advisor: Max Willsey]
Towards Wideband Linear RF Transmitters for Millimeter-Wave Arrays
Yikuan Chen [advisor: Ali Niknejad]
5th Year M.S.
A Function Calling Perspective on Scalable Large Language Model Agent Evaluation
Fanjia Yan [advisor: Joseph Gonzalez]
Chip Placement with Diffusion Models
Vint Lee [advisor: Pieter Abbeel]
Demystifying Decision-Making of Deep RL through Validated Language Explanations
Ashwin Dara [advisor: Alexandre Bayen]
DiT-Serve and DeepCoder: Enabling Video and Code Generation at Scale
Rachel Xin [advisor: Joseph Gonzalez]
Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
Anish Kachinthaya [advisor: Trevor Darrell]
LLM-Powered EDA Log Analysis for Effective Design Debugging
Rohit Kanagal [advisor: Borivoje Nikolic]
Network Fault Localization for the InterEdge
Matthew Fogel [advisor: Scott Shenker]
Scalable Requirements Elicitation Education Through Simulated Interview Practice with Large Language Models
Nelson Lojo [advisor: Armando Fox]
Scaling Properties of Diffusion Models for Perceptual Tasks
Zeeshan Patel [advisor: Alexei (Alyosha) Efros]
Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
Ishan Amin [advisor: Aditi Krishnapriyan]