URAP

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

Conformal prediction (CP) is a model-agnostic and distribution-free method for quantifying uncertainty in black-box machine learning (ML) models. CP can be used to construct prediction sets/intervals that covers the true labels with a pre-determined probability as long as the training and testing data are exchangeable...

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions to assist in diagnostic and treatment tasks. However, VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. This challenge is particularly pronounced in the medical domain, where we...

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: 12 or more hours     Location: On Campus

Community health workers need to navigate guidelines to make healthcare decisions for patients. The goal of this project is to develop an LLM-based system to assist community health workers retrieve information for the patient hand using multiple international guidelines...

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

Institutional constraints and concerns over patient privacy impedes sharing of clinical data among researchers. High-fidelity synthetic data that mimics the real data distribution without revealing real data for individual patients can help empower and democratize research applying machine learning models to clinical problems. In this project, we will use...

Ronald Fearing - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: 12 or more hours     Location: On Campus

We are looking for students interested in robot design, fabrication, and testing of pouch-based robots, for applications in minimally invasive surgery and beyond. Current surgical tools cannot navigate tortuous anatomical corridors, and as a result, accessing certain locations requires extensive tissue removal, general anesthesia, and a full operating room...

Venkatesan Guruswami - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: to be negotiated     Location: On Campus

Computer-assisted and automated theorem proving has been a longstanding goal of artificial intelligence and has gained increasing importance in recent years. Despite notable advancements, such as AlphaProof from Google DeepMind, which achieves silver-medal standard in solving International Mathematical Olympiad problems, challenges persist in obtaining machine-verifiable theorems and...

Galateia Kazakia - Professor, UC San Francisco, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 9-11 hrs     Location: Off Campus

Our research group focuses on advanced imaging techniques for the study of musculoskeletal structure and function (for details please see: http://www.radiology.ucsf.edu/research/kazakia). For this project, we plan to use two recently developed imaging tools to investigate the structure and composition of bone. State-of-the-art micro computed...

Galateia Kazakia - Professor, UC San Francisco, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 9-11 hrs     Location: Off Campus

Our research group focuses on advanced imaging techniques for the study of musculoskeletal structure and function (for details please see: http://www.radiology.ucsf.edu/research/kazakia). For this project, we will be performing advanced image processing and analysis on high resolution computed tomography (CT) images of the skeleton. These images are being...

Asir Intisar Khan - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: to be negotiated     Location: On Campus

Modern AI and data-intensive technologies demand faster, smaller, and far more energy-efficient electronic devices. However, as today’s electronics continue to shrink, traditional materials, such as metals, are approaching fundamental limits. When metals become thin, their electrical resistivity increases sharply due to electron scattering at their surfaces. This leads...

Asir Intisar Khan - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: to be negotiated     Location: On Campus

Data-centric applications face growing latency and energy challenges due to the separation of logic and memory components in traditional computing architecture. Neuro-inspired computing, modeled on the brain’s energy-efficient neural networks, offers a promising solution by reducing off-chip memory access. However, existing memory technologies struggle to achieve...

Asir Intisar Khan - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: to be negotiated     Location: On Campus

As nanoelectronics evolves, managing heat becomes critical, particularly in high-density 3D chips for AI workloads. Uneven power dissipation leads to localized ‘hot spots’ that compromise device reliability and safety. Current thermal management approaches, such as using high thermal conductivity materials, optimizing through-silicon vias, and passive cooling, often overlook...

Sayeef Salahuddin - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Location: On Campus

A remarkable development in the recent years has been the demonstration that a nanoscale magnet can be switched by a spin-polarized current, without having to apply any external magnetic field. It is a fascinating phenomenon from two different perspectives. Firstly, this effect is purely mediated by quantum mechanics, but...

Sayeef Salahuddin - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     

It is widely believed that the rate of change in current in conventional MOSFETs cannot be decreased below 60 mV/decade. This means that to change every decade of current one must apply at least 60 mV. As a result, the power supply voltage in modern MOSFETs cannot be reduced...

Sayeef Salahuddin - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: to be negotiated     Location: On Campus

Artificial Intelligence is becoming prevalent in many applications. In this research effort we are investigating new ideas of learning and inference. In addition to develop fundamental understanding of the algorithms, we are also designing novel hardware solutions that are specifically suitable for these Learning Machines, going beyond mere implementation of...

Carlo Sequin - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 6-8 hrs     Location: Off Campus

Students will participate in the development of JIPCAD, a design environment that can describe geometrical shapes (e.g., abstract sculptures by famous artists such as Charles Perry, Eva Hild, or Robert Engman) either through a simple procedural language or through an interactive graphical user interface. The typical workflow would start with...

Dawn Song - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

Large Language Model (LLM) agents are increasingly deployed in diverse and critical applications, ranging from customer service to decision support systems. As these agents become more integral to various domains, ensuring their safety and trustworthiness is paramount to prevent misuse, unintended behaviors, and to build user confidence. This project focuses...

Dawn Song - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

As AI models become more complex, understanding their internal decision-making processes becomes increasingly challenging. This project aims to advance the interpretability of AI systems, making their operations transparent and their decisions explainable to users and developers alike. Areas of focus include: - Explainable AI Techniques: Developing methods such as attention...

Dawn Song - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

The intersection of AI and software security presents unique opportunities and challenges. This project focuses on leveraging artificial intelligence to enhance secure code generation and protect software systems from vulnerabilities. Key objectives include: - Secure Code Generation: Developing AI models that can generate code snippets with built-in security best practices...

Dawn Song - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

Artificial Intelligence has the potential to revolutionize the field of mathematics by automating theorem proving and assisting in complex mathematical research. This project explores the application of AI techniques to enhance automated reasoning and support mathematicians in their work. Areas of investigation include: - Automated Theorem Proving: Developing AI models that...

Avideh Zakhor - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: 12 or more hours     Location: On Campus

Over the past few years, we have developed a reinforcement learning based framework for a drone to navigate from one point to another point while avoiding obstacles. In doing so, we do not use the GPS signal as it could be intermittent in many situations. Our approach has been to...

Avideh Zakhor - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: 12 or more hours     Location: On Campus

Over the past few years, we have developed autonomy algorithms to enable a tracked robot to vacuum debris ( peanuts, insulation etc) as it traverses over joists. The current approach is not adaptive in that the hose moves in a predefined sequence of movements. In this project, we will develop an...

Avideh Zakhor - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: 12 or more hours     Location: On Campus

In this project, we will develop methods to enable a Unitree G1 robot to walk, run, and perform whole body tasks such as bending over to pick up boxes. Some of the techniques we will investigate include Reinforcement Learning...

Avideh Zakhor - Professor, Electrical Engineering and Computer Science

Status: Current Term Now Closed     Weekly Hours: 12 or more hours     

We have a number of drones and robots in our lab which are in need of a perception sensors before they can be used. Examples of perception sensors include, RGB cameras, RGB-Depth cameras, Visual-inertial-Odometry units, LiDAR, IMU, etc. In this project, we will be designing mounts for...