Changxiao Cai

Changxiao Cai

By |

Changxiao Cai’s research interests lie broadly in the intersection of statistics, optimization, and machine learning. He is interested in developing provably scalable methods for information extraction from high-dimensional data, with an aim to achieve the optimal interplay between statistical accuracy and computational efficiency.

jjpark

Jeong Joon Park

By |

3D reconstruction and generative models. I use neural and physical 3D representations to generate realistic 3D objects and scenes. The current focus is large-scale, dynamic, and interactable 3D scene generations. These generative models will be greatly useful for content creators, like games or movies, or for autonomous agent training in virtual environments. For my research, I frequently use and adopt generative modeling techniques such as auto-decoders, GANs, or Diffusion Models.

In my project “DeepSDF,” I suggested a new representation for a 3D generative model that made a breakthrough in the field. The question I answered is: “what should the 3D model be generating? Points, meshes, or voxels?” In DeepSDF paper, I proposed that we should generate a “function,” that takes input as a 3D coordinate and outputs a field value corresponding to that coordinate, where the “function” is represented as a neural network. This neural coordinate-based representation is memory-efficient, differentiable, and expressive, and is at the core of huge progress our community has made for 3D generative modeling and reconstruction.

3D faces with apperance and geometry generated by our AI model

Two contributions I would like to make. First, I would like to enable AI generation of large-scale, dynamic, and interactable 3D world, which will benefit entertainment, autonomous agent training (robotics and self-driving) and various other scientific fields such as 3D medical imaging. Second, I would like to devise a new and more efficient neural network architecture that mimics our brains better. The current AI models are highly inefficient in terms of how they learn from data (requires a huge number of labels), difficult to train continuously and with verbal/visual instructions. I would like to develop a new architecture and learning methods that address these current limitations.

Liyue Shen

By |

My research interest is in Biomedical AI, which lies in the interdisciplinary areas of machine learning, computer vision, signal and image processing, medical image analysis, biomedical imaging, and data science. I am particularly interested in developing efficient and reliable AI/ML-driven computational methods for biomedical imaging and informatics to tackle real-world biomedicine and healthcare problems, including but not limited to, personalized cancer treatment, and precision medicine.

In the field of AI/ML, we focus on developing reliable, generalizable, data-efficient machine learning and deep learning algorithms by exploiting prior knowledge from the physical world, such as: Prior-integrated learning for data-efficient ML Uncertainty awareness for trustworthy ML. In the field of Biomedicine, we focus on developing efficient computational methods for biomedical imaging and biomedical data analysis to advance precision medicine and personalized treatment, such as: Multi-modal data analysis for decision making Clinical trial translation for real-world deployment.

In the field of AI/ML, we focus on developing reliable, generalizable, data-efficient machine learning and deep learning algorithms by exploiting prior knowledge from the physical world, such as: Prior-integrated learning for data-efficient ML Uncertainty awareness for trustworthy ML. In the field of Biomedicine, we focus on developing efficient computational methods for biomedical imaging and biomedical data analysis to advance precision medicine and personalized treatment, such as: Multi-modal data analysis for decision making Clinical trial translation for real-world deployment.

What are some of your most interesting projects?

Our goal is to develop efficient and reliable AI/ML-driven computational methods for biomedical imaging and informatics to tackle real-world biomedicine and healthcare problems. We hope the technology advancement in AI and ML can help us to better understand human health in different levels. Specifically, we develop Biomedical AI in different parts, including:
– AI in Biomedical Imaging: develop novel machine learning algorithms to advance biomedical imaging techniques for obtaining computational images with improved quality. Specifically, relevant topics include but not limited to: Implicit neural representation learning; Diffusion model / Score-based generative model; Physics-aware / Geometry-informed deep learning.
– AI in Biomedical Image Processing and Bioinformatics: develop robust and efficient machine learning algorithms to extract useful information from multimodal biomedical data for assisting decision making and precision medicine. Specifically, relevant topics include but not limited to: Multimodal representation learning; Robust learning with missing data / noisy labeling; Data-efficient learning such as self- / un- / semi-supervised learning with limited data / labels.

How did you end up where you are today?

I am an assistant professor in the ECE Division of the Electrical Engineering and Computer Science department of the College of Engineering, University of Michigan – Ann Arbor. Before this, I received my Ph.D. degree from the Department of Electrical Engineering, Stanford University. I obtained her Bachelor’s degree in Electronic Engineering from Tsinghua University in 2016. I is the recipient of Stanford Bio-X Bowes Graduate Student Fellowship (2019-2022), and was selected as the Rising Star in EECS by MIT and the Rising Star in Data Science by The University of Chicago in 2021.

Stella Yu

Stella Yu

By |

My research lies at the intersection of computer vision, human vision, and machine learning. Visual perception presents not just a fascinating computational problem, but more importantly an intelligent solution for large-scale data mining and pattern recognition applications.
My research has thus three themes.
1. Actionable Representation Learning Driven by Natural Data. I attribute our fast effortless vision to actionable representation learning driven by natural data, where mid-level visual pieces can be reassembled and adapted for seeing the new.
2. Efficient Structure-Aware Machine Learning Models. I view a computational model as dual to the data it takes in; since visual data are full of structures, models reflective of such structures can achieve maximum efficiency.
3. Application to Science, Medicine, and Engineering. I am interested in applying computer vision and machine learning to capture and exceed human expertise, enabling automatic data-driven discoveries in science, medicine, and engineering.

Nishil Talati

Nishil Talati

By |

I am a research faculty at the Computer Science and Engineering department at University of Michigan. I work with a group of talented PhD students on computer architecture, compiler techniques, and software engineering. My group focuses on developing novel software and hardware solutions to optimize large-scale data intensive worklods (e.g., graph traversals).

I earned my PhD degree in CSE from University of Michigan, Ann Arbor, USA, master’s degree in EE from Technion – Israel Institute of Technology, Haifa, Israel, and an undergraduate degree in EEE from BITS Pilani, Goa Campus, Goa, India.

Aditi Verma

Aditi Verma

By |

I am interested in how nuclear technologies specifically and complex technologies broadly—and their institutional infrastructures—can be designed in more creative, and participatory ways that are epistemically inclusive of both lay and expert perspectives. To this end, my work focuses on developing a more fundamental understanding of the early stages of the design process to improve design practice and pedagogy, and also improve the tools with which designers of complex systems work. I am particularly interested in developing novel approaches for gathering both qualitative and quantitative data generated throughout the design processes of complex systems and using this data to improve design outcomes. In my work, I focus on three main research questions:

  1. How can a fundamental understanding of design be used to improve design practice, design tools, and engineering pedagogy?
  2. How can design processes be made more open and participatory such that epistemic plurality and inclusivity are achieved as part of the design process?
  3. How can insights from design research be applied to the designs of policies and institutions for the governance — both innovation and regulation — of nuclear technologies?

The picture depicts the Sociotechnical Readiness Level which is a framework which critiques and reimagines the traditional Technology Readiness Level Framework. As part of the new SRL framework, we are developing new metrics and indicators to measure both social and technical aspects of a technology's readiness throughout its design and development processImage: The Sociotechnical Readiness Level, which is a framework which critiques and reimagines the traditional Technology Readiness Level Framework. As part of the new SRL framework, we are developing new metrics and indicators to measure both social and technical aspects of a technology’s readiness throughout its design and development process.

What are some of your most interesting projects?

Two new projects I am most excited about are (1) developing a sociotechnical readiness level framework for the assessment of novel technologies and (2) diagnosing the causes of cost overruns in the early stages of technology design.
In the first project, we are critiquing and reimagining the traditional Technology Readiness Level framework to capture both societal and engineering aspects of a technology’s readiness and integrate them into a single framework. As part of this work, we will develop metrics and indicators for assessing a technology’s readiness across the nine levels of sociotechnical readiness.
In the second project, we are studying how decisions made in the early stages of design impact overall system cost. This work is especially crucial in a nuclear energy context because recent nuclear plant construction projects have been severely impacted by cost overruns as well as project delays. It is vitally important to diagnose the causes of these cost overruns and address them in the early stages of the design if nuclear reactors are to play a significant role in our low-carbon energy systems.

How did you end up where you are today?

I was drawn to the field of nuclear engineering because of the enormous potential nuclear technologies have for solving one of the grandest challenges of our time: access to reliable, clean, and abundant energy.

What is the most significant scientific contribution you would like to make?

I hope to develop a deeper and more fundamental understanding of the design processes of complex systems that leads to more creative, robust, societally, and environmentally beneficial design outcomes.

What makes you excited about your data science and AI research?

There is an enormous opportunity to use data science and AI to study the early stages of the design processes of complex systems and develop new tools to stimulate a broader exploration of the design space and to ensure better design outcomes.

What are 1-3 interesting facts about yourself?

I love learning new languages. Depending on how you count, I speak (with varying levels of ability) six (or seven).

Todd Allen

Todd Allen

By |

My research is focussed on nuclear energy systems and public policy. My research has included data analysis to predict equipment failures and materials degradation.

Siddhartha Srivastava

Siddhartha Srivastava

By |

My research broadly revolves around extending, specializing, and developing novel ML/AI methods for computational mechanics. My primary focus is data-driven physics-based modeling that utilizes approaches like Variational System Identification and PDE-constrained optimization. I apply these methods for inferring PDE models for complex physical phenomena, for instance, foldings during brain growth, deformation mechanics in soft matter (human tissue and ligaments), and migration and proliferation in biological cells. I also develop graph-based approaches for Machine Learning and NISQ (Noisy Intermediate Scale Quantum) computing. These methods are rooted in classical physics and mathematical analysis but simultaneously developed in concert with real-life experimental data.

Liang Zhao

Liang Zhao

By |

I am working on analyzing the solar wind plasma measurements obtained by multiple space missions. Especially, I am interested in the solar wind heavy ion elemental abundance and charge states measured by SWICS on Ulysses and ACE and HIS onboard Solar Orbiter mission. Applications of machine learning and artificial intelligence algorithms on solar wind plasma classification and heliophysics parameter prediction are a brand new research area that we have been working on.

Additional Information

What are some of your most interesting projects?

How did you end up where you are today?

What is the most significant scientific contribution you would like to make?

What makes you excited about your data science and AI research?

What are 1-3 interesting facts about yourself?

Max Li

Max Li

By |

Max’s research interests lies in the design, management, and optimization of large-scale infrastructure systems, focusing on the air transportation system and emerging aerial mobility systems. He is interested in the application of methods applicable to networked systems, especially with resource constraints (e.g., airspace and airport capacity), diverse stakeholders (e.g., passenger-centric, airline-centric), and complex dynamics (e.g., changing temporal behaviors). Max has worked on a variety of data-driven problems related to analyzing flight delays across airport networks, strategic/tactical air traffic management and delay assignments, privacy and routing in drone-based applications, and uncertainty-aware traffic management. He is interested in methods such as graph signal processing and signal processing over non-Euclidean domains, data-driven optimization, mixed-integer/integer/combinatorial programs, resilient network design, and stochastic optimization. Broadly, Max hopes to contribute to a safe, resilient, and efficient air transportation system (inclusive of intra- and inter-city modalities) within the context of a passenger’s (or cargo’s) door-to-door journey.

A flight delay assignment mechanism that does not rely on knowing the exact value of an airline's private per-flight valuation of flight delays. The mechanism requires the system capacities/demand per round, and computes an initial solution. This solution is adjusted by a Coordinating Airline using privatized information from Participating Airlines. The resultant solution is proposed, and any negative public delays incurred is recorded to a ledger. The role of Coordianting/Participating Airlines then rotate depending on the current ledger balance.

Image: A flight delay assignment mechanism that does not rely on knowing the exact value of an airline’s private per-flight valuation of flight delays. The mechanism requires the system capacities/demand per round, and computes an initial solution. This solution is adjusted by a Coordinating Airline using privatized information from Participating Airlines. The resultant solution is proposed, and any negative public delays incurred is recorded to a ledger. The role of Coordinating/Participating Airlines then rotate depending on the current ledger balance.

What is the most significant scientific contribution you would like to make?

Working with air traffic controllers and traffic flow managers to deploy/prototype a congestion management solution/model!

What makes you excited about your data science and AI research?

The potential positive impact on the air transportation system, and helping to make it more efficient and equitable in terms of access.