Available Research Projects

Machine Learning for Biomedical Imaging & Clinical Prediction
Faculty Members
Dr. Emami (UC Davis Health), Dr. Iman Soltani

Description
This project focuses on applying machine learning and data-driven methods to large-scale biomedical imaging and clinical datasets at the UC Davis Eye Center. The student will contribute to developing and evaluating predictive models to address important questions in human health and disease. Work will involve collaborating closely with clinicians and data scientists in a multidisciplinary research environment.

Expected Outcomes
• Development and evaluation of ML models using imaging and clinical data
• Experience working with real-world health datasets and clinical collaborators
• Contributions to an ongoing long-term research project at the UC Davis Eye Center

Requirements
Applicants should have experience in Python and a strong interest in machine learning. Experience with deep learning frameworks or biostatistical modeling is a plus. This opportunity is intended for second-year MS students.

Opportunities
This position is funded as a Graduate Student Researcher (GSR) for approximately 3 quarters (possibly 4).

How to Apply
If you are interested, please contact Dr. Iman Soltani at [email protected].
Website: https://soltanilab.engineering.ucdavis.edu/
Deep RL for Automated Android UI Exploration
Faculty Members
Xin Liu, Zhe Zhao

Description
This project aims to develop and evaluate deep reinforcement learning (DRL) algorithms for systematic UI exploration in Android apps.The student will adopt and adapt existing DRL-based exploration policies that learn to navigate an app’s UI hierarchy, identify actionable widgets, and trigger transitions that reveal new screens and states. The DRL agent will operate directly on an installed APK, receiving observations from the device (e.g., rendered UI states, view hierarchies) and selecting actions (taps, scrolls, text inputs) to maximize UI coverage.

Expected Outcomes
•A DRL-based exploration framework that increases coverage of unique screens, activities, and UI paths.
•(Optional) Comparative evaluation against LLM-based exploration methods.
•(Optional) A hybrid integration of DRL-based and LLM-based exploration.

This project contributes to a broader effort to build scalable, intelligent testing tools capable of generating high-quality test cases for complex Android apps with minimal human intervention.

Requirements
Applicants should have experience in machine learning, Python, and PyTorch. Prior experience to reinforcement learning and/or Android development is a strong plus. A minimum of 10 hours/week is required. Students may choose to enroll in ECS 199/299.

Opportunities
If the algorithm proves effective, the student will be included as a co-author on an academic paper submission. This project is conducted in collaboration with a Bay Area AI startup. Highly productive students will be considered for part-time internships during the academic year and full-time opportunities during the summer - The company has hired multiple students from UC Davis. Please note that this project does not provide a GSR position.

How to apply
If you are interested, please submit your application here. Please make sure to highlight your RL/Android experience if any. You will be working with Prof. Zhe Zhao, Prof. Xin Liu, and their students.
NeuoInverter
Faculty Member
Ben-Shalom

Description
A neuron's function is defined by its unique expression of ion channels, but these are nearly
impossible to measure directly. Our project solves this inverse problem by creating a
Neuro-Inverter: a deep learning model trained to work backward from a neuron's electrical
"fingerprint" to its underlying molecular recipe. Our model, a powerful Convolutional Neural
Network (CNN) called ONTRA, learned this relationship from a massive dataset of millions of
simulated neurons where the ground truth was known. Our ultimate goal is to apply this
Neuro-Inverter to real-world experimental data from patch-clamp recordings. This will provide a
powerful new tool to accelerate neuroscience research, enabling the rapid classification of
neurons and offering new insights into channel-related diseases (channelopathies) like epilepsy
and autism.

As a research student, you will be responsible for:
•Running large-scale simulations on the current pipeline
•Implementing new simulation models into the data generation pipeline
•Implementing new deep learning architectures

Requirements
•Should be proficient in bash, Python, Pytorch, and deep learning concepts.
•Good coding and debugging skills

How to apply
Please reach out to Professor Roy Ben-Shalom ([email protected]) with your resume highlighting relevant previous experiences.
AI Models for Genetic Module Associated Critical Cell Discovery in Autism and Neurodevelopmental Disorders
Faculty Member
Fereydoun Hormozdiari

Description
Understanding the genetic basis of complex diseases requires not only identifying relevant variants and genes but also pinpointing the specific cell types where these genes exert their effects. This project focuses on discovering these “critical cell types” by leveraging a pathway-centric assumption: that disruptions in sets of functionally related genes within particular cells drive disease. Formally, we aim to identify the subset of variants, genes, and cells (V × G × C) that explains a specific disease, such as neuropsychiatric or neurodevelopmental disorders. The approach is divided into two subproblems: first, mapping variants to functionally related gene sets using case-control genomics and network biology (such as protein-interaction or co-expression networks); second, linking these gene sets to cell types using single-cell or spatial transcriptomics, potentially refining both gene and cell selection iteratively.

To tackle these challenges, we will develop novel AI models to capture complex, non-linear relationships between variants, genes, and cell types. AI-driven approaches can help identify subtle patterns in large-scale genomics and transcriptomics datasets, predict gene activity across cell types, and prioritize critical gene-cell interactions for specific disease subtypes. By integrating AI with biology networks, we aim to build a computational pipeline that not only identifies candidate variants and genes but also predicts the specific cell populations in which they are functionally relevant, thereby providing a more precise understanding of disease mechanisms.

Requirements
• Strong programming skills in Python and/or C/C.
• Solid understanding of data structures, algorithms, and graph-based methods.
• Foundational knowledge of machine learning and AI concepts.
• Familiarity with deep learning frameworks such as TensorFlow or PyTorch.
• Enthusiasm for learning about genetics, genomics, and the molecular mechanisms underlying human diseases.

How to apply
Please email to [email protected] or [email protected] your CV and Transcripts.
VitalCue
Faculty Member
Dipak Ghosal

Description
Modern smartphones capture a myriad of kinetic biometric (movement) based data such as step count, distance, speed, step length, and walking asymmetry as well as behavioral-based data such as number and duration of phone calls made and received, amount of screen time, and number of texts sent and received. All of this biometric data is readily accessible. We know that movement is directly impacted by physical parameters including a person’s weight, musculoskeletal, respiratory, and cardiovascular health. Additionally, both movement and behavior are influenced by mental acuity and their collective deterioration results in frailty. While a single set of biometric measurements is unlikely to be useful to assessing an individual patient, changes in the trend over a larger period of measurement may be very clinically significant.
We propose analyzing the kinetic and behavioral data already captured by smartphones to establish baseline activity levels for patients with chronic medical conditions such as end-stage renal disease requiring either hemodialysis or peritoneal dialysis and end-stage liver disease. We will then test whether deviations from baseline activity identified by machine learning algorithms correspond with clinically significant changes in patients’ health.

Requirements
   - The candidate will use their expertise to make scientific contributions to one or more research studies and will contribute to research and development in the use of kinetic and behavioral data for continuity of care. Under the general direction of the Principal Investigators, the candidate will collaborate with other research personnel as part of a project that seeks to collect, consolidate, and analyze research participant’s kinetic and behavioral data from their smartphones.
  - The candidate will review the academic literature in Machine Learning (ML) and AI techniques for prediction and anomaly detection in multi-modal time series data.
  - The candidate will be actively engaged in preparing data for, and validating, AI models designed for this project and will work with collaborators in the laboratory as well as from other departments at UC Davis.
  - The candidate will draft tables and figures for presentations, and scientific reports, publications and proposals as well as participate in drafting and revising manuscripts as needed.
- The candidate will assist in deploying and maintaining the app that will collect kinetic and behavioral data from the research participants' smartphones.

Basic qualifications (required at time of application)
•    A minimum of Bachelor's degree in Computer Science.
•    Skilled in ML and AI. Knowledge in ML/AI techniques for time series data
•    Fluent in pytorch and other ML/AI tools.
•    Fluent with DevOPs and MLOPs.
•    Familiarity with literature review, data collection, and data consolidation.

Additional qualifications (required at time of start)
•    Evidence of prior ML/AI research and development experience.
•    Evidence of professional competence and activity.
•    Evidence of strong organizational skills and attention to detail.
•    Evidence of excellence in communication skills with proficiency in both written and verbal English.
•    Evidence of ability to work both independently and as part of a team.
•    Familiarity with organizing data for the training and validation of AI modeling.
•    Familiarity with research on time series data.

How to Apply: Please email the following to [email protected]
1.    Subject line of the email must include the text “Application for VitalCue” (without the quotes)
2.    Include CV, transcript of course work, 1-page (max) writeup on prior experience with relevant ML projects
Quantitative Biology computer labs conversion
Faculty Member
Mark Goldman

Description
The undergraduate quantitative biology courses MAT/BIS 27A (Linear algebra with Applications to Biology), MAT/BIS 27B (Differential equations with Applications to Biology), and MAT/BIS 107 (Probability and Stochastic Processes with Applications to Biology) are part of a nation-leading effort to re-design biological science and bioengineering training to tightly integrate computational and mathematical modeling as part of core post-calculus mathematics courses. A set of weekly computational laboratories for the above 3 courses was originally written in MATLAB, but needs to be converted to Python to accommodate the switch of many engineering majors to using Python as the new standard programming language. The project would be to perform this conversion, which will require converting the code in a manner that makes the converted Python code approachable to a student who starts the course with no prior programming experience. Accomplishment of this project will additionally benefit graduate students interested in biotechnology and bioinformatics, as the project team will learn classic problems and modeling approaches in quantitative and computational biology.

Requirements
Prior coursework in linear algebra, differential equations, and probability.

How to Apply: Please contact Prof. Mark Goldman, [email protected]
New Algorithm for Explainable AI
Faculty Member
Xin Liu

Description
The project aims to develop a new post-hoc explainability algorithm for deep learning models, specifically for computer vision applications. The idea revolves around enhancing the existing and widely used method of "Integrated Gradients".

Requirements
Applicants should have expertise in machine learning, deep learning and basic computer vision concepts, and ample experience with Python and Pytorch.

How to Apply: Fill the Google form: https://forms.gle/yv9u1mhFq8XJ5xkc7
Deep Networks to Decode Brain Signals in Listeners with Cochlear Implants
Faculty Member
Lee Miller

Description
The Speech Neuroengineering and Cybernetics Lab (PI: Lee Miller) in collaboration with the Cognitive Neurolinguistics Lab (PI: David Corina) and Dr. Doron Sagiv (Otolaryngology / Head & Neck Surgery) has a research project investigating speech perception in listeners with cochlear implants, including children born deaf as well as very old adults.

Cochlear implants are the most widespread and successful neural prosthesis ever, with over a million users worldwide. They can restore speech perception even in children born deaf. We use EEG to study how children’s brains change and improve as they learn to hear with an implant. One of the greatest challenges for clinicians and researchers, however, is that the implant itself adds electrical noise, thereby obscuring the brain signals. The overall goal of this project is to develop a deep neural network to separate neural signals from cochlear implant noise. This will have a profound effect on design and clinical evaluation the implants. This project will prepare candidates for careers in domains such as medical devices, consumer tech, data science, brain-computer interfaces, and many more.

Requirements
- Candidates will need to be comfortable training and testing deep neural networks (e.g. with Pytorch) and basic signal processing.
- The expected deliverable will be a first-author, peer-reviewed journal publication or conference proceeding, so a demonstrated ability to write well is also required.
- Specific skills may include any of the following (helpful but not required): Time series analysis, machine learning, data augmentation, blind source separation, and working with autoencoders.
How to Apply: If interested, please send an email to [email protected] with subject line “MS Project…” including a brief explanation of why you’re interested in this project, your resume, unofficial transcript, graduation timeline, details on programming abilities, time available (hours/week now, over summer, and through next year), and one example of a report that you have written on your own (for a class or project).
Prediction-Oriented Methods in Handling Missing Data
Faculty Member
Norm Matloff, Emeritus

Description
Many, probably most, real-world datasets contain missing values. A wealth of methods have been developed to deal with this problem, but few if any are prediction-oriented, and not many are suitable for machine learning. Here we will develop novel approaches to this problem.
A software package will be developed, and a paper written that explores the efficiency of the methods. The software will be written in R, with Python interfaces.
Requirements
Some background in linear models and machine learning methods. Previous exposure to R is nice but not required; strong coding skills, including debugging, are a must.

How to Apply: Please contact [email protected].
Python programming for physics modeling
Faculty Member
Emilie Roncali
Description
The Roncali lab in the Department of Biomedical Engineering at UC Davis (https://roncalilab.engineering.ucdavis.edu/) is looking for a highly motivated graduate student (MSc.) with an interest in medical physics and AI programming. Our lab develops physics simulation and AI-based simulations (e.g. GANs), which need to be refactored in Python, specifically for GPU computing.
Requirements
A strong background in computer science and advanced programming skills (Python) are required. The candidate should be familiar with Matlab and C++. The student will work closely with the postdoctoral researchers in the lab to translate their code in Python, implementing good programming practice.

Qualified candidates can apply by sending their CV and a short statement of research interests to Dr. Emilie Roncali ([email protected]).
Scientific software development for DNA nanotechnology
Faculty Member
David Doty

Description
The project will involve:
1. scientific software development, for instance on scadnano (https://github.com/UC-Davis-molecular-computing/scadnano#readme) for structural DNA nanotech design, and nuad (https://github.com/UC-Davis-molecular-computing/nuad#readme) for DNA sequence design.
2. (optional for MS project) Algorithmic and modeling research in support of DNA sequence design.
3. (optional for MS project) Collaborations with partner institutions on wet-lab experiments in nucleic acid strand displacement and self-assembly to tune the modeling and design software.
Requirements
Background in computer science/computer engineering/software engineering (either through a formal degree, or experience with programming)

How to apply:
Contact David Doty at [email protected] and indicate your background with software development.
Analysis and Visualization of Unstructured Climate Data
Faculty Member
Paul Ullrich

Description
Professor Paul Ullrich is leading a team to develop tools for analysis and visualization of climate data, particularly global, unstructured climate datasets defined in spherical geometry. These tools are widely employed throughout the climate science community, including the U.S. Department of Energy, the National Oceanic and Atmospheric Administration, and National Center for Atmospheric Research. Interested students can work with Prof. Ullrich and his team to develop new visualization or analysis capabilities in C++ or Python. Our core software repositories for this project can be found at:
https://github.com/SEATStandards/ncvis
https://github.com/UXARRAY/uxarray

Requirements
- If interested in visualization of climate data, experience with C++
- If interested in analysis of climate data, experience with Python
- Familiarity with Linux operating systems
- Basic familiarity with version control (Git)

How to apply:
If interested, email Prof. Paul Ullrich ([email protected])
Augmented Reality Quadcopter Project
Faculty Member
Nelson Max

Description
Emeritus Professor Nelson Max is looking for more Master’s students to help with a multiplayer augmented reality quadcopter game system. The system includes for each game player a Solo 3DR quadcopter with a mounted ZED2 stereo video camera, a computer with an NVIDIA GTX 1070 GPU, Oculus Rift or Quest VR goggles, Oculus Touch hand held controllers for flying the drone, and wireless communication links. The computers do Simultaneous Localization and Mapping (SLAM) on feature points in the environment, as seen by the video cameras, combined with data from inertial sensors on the quadcopters, to compute their 3D positions.The quadcopter positions are communicated to the master computer, and are used in the game physics calculations. The master computer receives the user flight control signals, and either sends them directly to the quadcopters, or modifies them according to the game physics and to avoid collisions. The games are written in Unity.

The video camera has a wide angle lens so that part of the video image can be displayed on the goggles, appropriate to the user's head position and orientation. The computer graphics augmented reality elements are added in stereo onto the real video background, also accounting for the user head motion. Thus the game players feel as if they were looking through the windows of a real aircraft at the actual environment in which they are flying.

Our initial game was a pong-like paddleball game, with a paddle at each quadcopter, and a virtual ball, which we hope to replace with a third quadcopter. There are game displays showing top down and side views, either on the cockpit dashboard or in a heads-up display on its window, and sound effects when the ball is hit by the paddle, or hits the walls, floor, or ceiling of the game space. Our second game was a maze racing game, where two players start at opposite corners of a 3D two-level maze like track, and attempt to overtake each other.
Aspects of the system development which could lead to Master’s projects are:
- The computer vision system for Simultaneous Location and Mapping (SLAM)
- The control of the quadcopter, including anticipating and preventing collisions
- Integrating the different components into a playable system
- Creating new games using the system

How to apply:
If interested, email Prof. Max at [email protected].
AI-Native Stock Research & Discovery Platform
Faculty Member: Setareh Rafatirad
Description: This project aims to build an AI-native, conversational-first stock research platform for retail investors. The platform will ingest millions of official documents from thousands of publicly listed companies and use advanced AI to help users discover stocks, research companies, and monitor their portfolios - without relying on manual analysis. Core features include:
Conversational AI Assistant: A smart chatbot strictly grounded in official company filings.
AI-Driven Stock Discovery: Automated thematic tagging of companies with full explainability and source document references.
Portfolio Integration: Brokerage account connectivity enabling portfolio-level AI queries, restricted to qualitative research only.
Personalized Dashboard: A customized feed combining AI insights with traditional financial statements and stock charts.
Requirements: Applicants should have experience with Python and familiarity with large language models, NLP, or AI agent frameworks.
How to Apply: If interested, please contact Prof. Setareh Rafatirad at [email protected] and cc: [email protected]. Include your resume, unofficial transcript, a brief explanation of your interest, and your availability (hours/week).
Measuring Safe Autonomy in AI Agents Knowledge Work
Faculty Member: Setareh Rafatirad
Description: This project develops a benchmark to evaluate whether AI agents can operate as accountable, safe, and reliable employees in realistic office settings. Existing agentic benchmarks focus on task completion but overlook critical deployment blockers such as unsafe autonomy, weak governance, and vulnerability to manipulation. This benchmark simulates an inbox-driven workday where agents must handle email, chat, tickets, documents, spreadsheets, and calendar tasks while navigating interruptions and ambiguous requests. There is a good scope for an academic publication in top tier ML Conferences.
Requirements: Applicants should have experience with Python and a strong interest in AI agents, LLM evaluation, or AI safety. Familiarity with agentic frameworks or benchmark design is a plus.
How to Apply: If interested, please contact Prof. Setareh Rafatirad at [email protected] and cc: [email protected]. Include your resume, unofficial transcript, a brief explanation of your interest, and your availability (hours/week).