Master's Theses & Technical Reports - 2025
M.S.
Accelerating Randomized Numerical Linear Algebra on a Short-Vector Machine
Jingyi Xu [advisor: Borivoje Nikolic and Sophia Shao]
AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World
Paul Zhiyuan Zhou [advisor: Sergey Levine]
Controlled Preemption: Amplifying Side-Channel Attacks from Userspace
Yongye Zhu [advisor: Christopher Fletcher]
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]
Modeling Diversity Dynamics in Time-Evolving Collaboration Networks
Christopher Archer [advisor: Gireeja Ranade]
Predicting Degradation of Fuel Cell Membrane Electrode Assemblies from Buses
Harsh Srivastav [advisor: Alexandre Bayen]
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 a TMS- and MRI- Compatible Wireless EEG System
Yu-Chi Lin [advisor: Kristofer Pister and Ali Niknejad]
Towards Wideband Linear RF Transmitters for Millimeter-Wave Arrays
Yikuan Chen [advisor: Ali Niknejad]
5th Year M.S.
A Foundational Framework for Joint Speech and 4D Avatar Generation from Syllabic Tokens
Rishi Jain [advisor: Gopala Krishna Anumanchipalli]
A Function Calling Perspective on Scalable Large Language Model Agent Evaluation
Fanjia Yan [advisor: Joseph Gonzalez]
Accented Non-Autoregressive Text to Speech via Articulatory Features
Xavier Yin [advisor: Gopala Krishna Anumanchipalli]
AI-Assisted Dataset Discovery with DATASCOUT
Rachel Lin [advisor: Aditya Parameswaran]
Articulatory Voice-to-Instrument Timbre Transfer in Real-Time with Audio-Conditioned DDSP
David Babazadeh [advisor: Claire Tomlin]
Auxiliary States for Decentralized Optimization in Probabilistic Communication Networks
Noah Adhikari [advisor: Joshua Hug]
Behavioral Alignment and Verifiable Explainability in Autonomous Driving
Ashish Pandian [advisor: Alexandre Bayen]
Benchmarking Extraction of Structured Data from Templatized Documents
Mawil Hasan [advisor: Aditya Parameswaran]
Benchmarking LLMs on Advanced Mathematical Reasoning
Jonathan Yue [advisor: Daniel Klein]
Bimanual Dexterity: 3D Object Reconstruction and Cross-Embodiment Learning for Generalizable Manipulation
Zehan Ma [advisor: Ken Goldberg]
Buyer-Side Recommendation Agents
Andrew Qin [advisor: Kannan Ramchandran]
Chip Placement with Diffusion Models
Vint Lee [advisor: Pieter Abbeel]
Control of a 7-DOF MRI Compatible Robot Arm
Naichen Zhao [advisor: Ronald S. Fearing]
Delay-Locked Loops for Multiphase Clock Generation
Oliver Yu [advisor: Borivoje Nikolic]
Demystifying Decision-Making of Deep RL through Validated Language Explanations
Ashwin Dara [advisor: Alexandre Bayen]
Designing LLM based agents to interact with the embodied world
Dylan Goetting [advisor: Jitendra Malik]
DiT-Serve and DeepCoder: Enabling Video and Code Generation at Scale
Rachel Xin [advisor: Joseph Gonzalez]
Enforcing Least Privilege Cross-Cloud Resource Access for Cloud Orchestrators
Alec Li [advisor: Raluca Ada Popa]
Extending Delayed Fair Sharing: A Generalizable Framework for Multi-Resource Performance Isolation
James DeLoye [advisor: Joseph Gonzalez]
FALCON: Full Stack Evaluation Testbed of Compute Offloaded Extended Reality Systems
Zekai Lin [advisor: Sophia Shao]
FlowFusion: Optimizing Cloud Workflows Through Fusion and Parallelization
Nithin Tatikonda [advisor: Alvin Cheung]
From Recovery to Locomotion: Learning Robust Humanoid Control via Curriculum and Policy Distillation
Stefanie Theodora Karolina Gschwind [advisor: Sergey Levine]
GamesmanROS: A Generalized Game-Playing Robotic System
Nakul Srikanth [advisor: Dan Garcia]
GamesPlane: Augmented Reality Gamesman
Miller Hollinger [advisor: Dan Garcia and Ken Goldberg]
Improving Auto-Formalization to UCLID5 with LLMs and Formal Methods
Anirudh Chaudhary [advisor: Sanjit A. Seshia]
Improving Energy Efficiency of Machine Learning Software with an Instruction-Level Dynamic Energy Model for DNN Accelerators
Jonathan Wang [advisor: Sophia Shao]
Improving LLM Performance in Generating Verilog by Fine Tuning with a Translated Code Dataset
Brendan Roberts [advisor: Sophia Shao]
Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
Anish Kachinthaya [advisor: Trevor Darrell]
Investigations in Optimal Transaction Scheduling
Darren Teh [advisor: Ion Stoica]
Kokkos GPU Implementation of CPU-Based BLAS/LAPACK Operations and RandBLAS Randomization
Rahul Shah [advisor: James Demmel]
Learning to Race Full-Scale Autonomous Racecars
Eric Berndt [advisor: S. Shankar Sastry]
LLM-Powered EDA Log Analysis for Effective Design Debugging
Rohit Kanagal [advisor: Borivoje Nikolic]
Measuring General Intelligence with Generated Games
Vivek Verma [advisor: Daniel Klein]
Monocular Depth Estimation for 3D Scene Completion in Autonomous Racing
Wei Xun Lai [advisor: S. Shankar Sastry]
Multimodal Differential Phase Contrast and Fluorescence Microscopy For Characterizing Protein Aggregation
William Xu [advisor: Laura Waller]
Network Fault Localization for the InterEdge
Matthew Fogel [advisor: Scott Shenker]
On Unsupervised Object-Centric Representation Learning: Advantages and Shortcomings
Yarden Goraly [advisor: Claire Tomlin]
Point Track Prediction Models Enable Imitation from Action-less Datasets
Aryan Jain [advisor: Pieter Abbeel]
Precision Placement of DNA Origami onto Patterned Silicon Wafer Surfaces
Leo Huang [advisor: Grigory Tikhomirov]
Protein Language Model Fitness is a Matter of Preference
Cade Gordon [advisor: Pieter Abbeel]
Reinforcement Learning for Safe LLM Code Generation
Roy Huang [advisor: Joseph Gonzalez]
Reward Modeling for Human Preferences
Evan Frick [advisor: Jiantao Jiao]
Robust Multimodal Perception Stack for High-Speed Autonomous Racecars
Kaushik Singh [advisor: S. Shankar Sastry]
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]
The Development and Management of GradeSuite: A Microservice LMS for Mastery Learning
Connor Bernard [advisor: Dan Garcia]
Toward Pedagogically Effective AI for Introductory Computer Science
Michael Wu [advisor: Prabal Dutta]
Towards Controllable Language Models With Instruction Hierarchies
Jonathan Lu [advisor: David A. Wagner]
Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
Ishan Amin [advisor: Aditi Krishnapriyan]
Training and Analyzing Language Agents in Socially Complex Dialogues
Jessica Lin [advisor: Sergey Levine]
UPSC2M: Benchmarking Adaptive Learning from Two Million MCQ Attempts
Kevin Shi [advisor: Jitendra Malik]
Vision-Guided Outdoor Obstacle Evasion for UAVs via Reinforcement Learning
Shiladitya Dutta [advisor: Avideh Zakhor]
3D Part Scanning, Inspection, and Representation
Tianshuang Qiu [advisor: Ken Goldberg]