Artificial Intelligence

Topics of accepted ECE NeurIPS papers include diffusion models, large language models, multi-armed bandit models, and more.

Smarter use of processor speeds saves energy without compromising training speed and performance.

The post Up to 30% of the power used to train AI is wasted. Here’s how to fix it. appeared first on Michigan Engineering News.

Advanced microscopy techniques and AI models will help design complex nanoparticles for specific biological targets with less trial and error.

The post Precision health and advanced communications: €9M ($10M) for bio-inspired nanoparticles on demand appeared first on Michigan Engineering News.

‘There’s an intellectual milieu and an enthusiasm that’s palpable.’

The post U.S. presidential advisory council visited U-M for transportation & mobility research appeared first on Michigan Engineering News.

New batteryless and wireless sensor tested in pigs.

The post Cancer management: Stent sensor can warn of blockages in the bile duct appeared first on Michigan Engineering News.

Some sick Black patients are likely labeled as “healthy” in AI datasets due to inequitable medical testing.

The post Accounting for bias in medical data helps prevent AI from amplifying racial disparity appeared first on Michigan Engineering News.

Accepted papers for the ICML conference span topics including deep representation learning, language model fine-tuning, generative modeling, and more.

Doctoral student Can Yaras wants to reduce the carbon footprint of AI.

Doctoral student Matthew Raymond wants to facilitate the development of new and groundbreaking nanomedicines.

The DoD funds efforts to incorporate AI agents into game theory and develop microelectronics that can withstand a hot day on Venus or carry quantum information.

The post $15M for game theory with AI agents, quantum semiconductors for microelectronics and photonics  appeared first on Michigan Engineering News.

Capturing nanoscale ‘packages’ that cancer cells send out, twisting gold nanoparticles use light to distinguish healthy patients from lung cancer patients.

The post Faster, more sensitive lung cancer detection from a blood draw appeared first on Michigan Engineering News.

New approach could offer those with food allergies another option besides avoidance.

The post Tick-borne red meat allergy prevented in mice through new nanoparticle treatment appeared first on Michigan Engineering News.

Taking advantage of the transformer neural networks that power large language models, engineers can get recipes for materials with the optical properties they need.

The post OptoGPT for improving solar cells, smart windows, telescopes and more appeared first on Michigan Engineering News.

Headworn tech from U-M startup could protect agricultural and industrial workers from airborne pathogens.

The post An invisible mask? Wearable air curtain, treated to kill viruses, blocks 99.8% of aerosols appeared first on Michigan Engineering News.

Timekeeping in the brain is done with neurons that relax at different rates after receiving a signal; now memristors—hardware analogues of neurons—can do that too.

The post AI chips could get a sense of time appeared first on Michigan Engineering News.

Most human oocytes never get a chance to mature into eggs—a new study sheds light on why.

The post Spatial atlas of the human ovary with cell-level resolution will bolster reproductive research appeared first on Michigan Engineering News.

Most human oocytes never get a chance to mature into eggs—a new study sheds light on why.

The post First atlas of the human ovary with cell-level resolution is a step toward artificial ovary appeared first on Michigan Engineering News.

Award-winning research led by Prof. Qing Qu discovered an intriguing phenomenon that diffusion models consistently produce nearly identical content starting from the same noise input, regardless of model architectures or training procedures.

Current technologies already in use could help prevent crashes and deaths linked to impaired driving.

The post Auto industry deadlines loom for impaired-driver detection tech, U-M offers a low-cost solution appeared first on Michigan Engineering News.

The first organized stem cell culture model that resembles all three sections of the embryonic brain and spinal cord could shed light on developmental brain diseases.

The post Human stem cells coaxed to mimic the very early central nervous system appeared first on Michigan Engineering News.

When using only data collected before patients with sepsis received treatments or medical tests, the model’s accuracy was no better than a coin toss.

The post Widely used AI tool for early sepsis detection may be cribbing doctors’ suspicions appeared first on Michigan Engineering News.

Dawn Tilbury is recognized for advances in manufacturing network control and human-robot interaction, as well as engineering leadership.

The post Leader in robotics at U-M and beyond elected to National Academy of Engineering appeared first on Michigan Engineering News.

University of Michigan researchers examine if molecular compounds in exhaled breath could lead to improved diagnosis and tracking of acute respiratory distress syndrome (ARDS).

The post U-M team receives NIH grant for collaborative research to speed ARDS diagnosis appeared first on Michigan Engineering News.

By trapping and concentrating tiny numbers of cancer cells from blood samples, the device can identify whether a treatment is working at the four-week mark.

The post Is lung cancer treatment working? This chip can tell from a blood draw appeared first on Michigan Engineering News.

Prof. Lei Ying leads a new MURI that is focused on the interplay between online and offline networks and how they could impact disruptive behavior and events.

Regulators pinned their hopes on clinicians being able to spot flaws in explanations of an AI model’s logic, but a study suggests this isn’t a safe approach.

The post Clinicians could be fooled by biased AI, despite explanations appeared first on Michigan Engineering News.

How do chatbots based on the transformer architecture decide what to pay attention to in a conversation? They’ve made their own machine learning algorithms to tell them.

The post Understanding attention in large language models appeared first on Michigan Engineering News.

AI model that pairs text, images performs poorly on lower-income or non-Western images, potentially increasing inequality in digital technology representation.

The post Biases in large image-text AI model favor wealthier, Western perspectives appeared first on Michigan Engineering News.

Even with lead service line replacement, the city’s water has issues that require public education.

The post Building Flint’s trust in its drinking water appeared first on Michigan Engineering News.

Taking inspiration from the word-predicting large language models, a U-M team is kickstarting an atom-predicting model with 200,000 node hours on Argonne’s Polaris.

The post Building a chemical ‘GPT’ to help design a key battery component appeared first on Michigan Engineering News.

A “new physiological flow” modeled in the body could aid in treatment of lung infections and pulmonary edema.

The post Century-old question on fluid in lungs answered appeared first on Michigan Engineering News.

And that tracks with the way our motor circuits work—we’re not that complicated.

The post Simple neural networks outperform the state-of-the-art for controlling robotic prosthetics  appeared first on Michigan Engineering News.

Technique pioneered at the University of Michigan could improve outcomes for cancer and neurological conditions.

The post How sound waves trigger immune responses to cancer in mice appeared first on Michigan Engineering News.

Research suggests volatile organic compounds in breath could mark distinction between COVID-19, variants and non-COVID illnesses.

The post Study finds exhaled breath could enhance detection, diagnosis of COVID-19 and variants appeared first on Michigan Engineering News.

Technique developed at the University of Michigan provides a non-invasive alternative to surgery, chemotherapy and radiation treatments for cancer.

The post Tumor-destroying soundwaves receive FDA approval for liver treatment in humans appeared first on Michigan Engineering News.

When a person’s cognitive function is highly variable, they’re likely to be more infectious and have more symptoms after exposure to a respiratory virus.

The post A brain game may predict your risk of infection appeared first on Michigan Engineering News.

A new industry partnership seeks to enable on-demand local manufacturing of next-generation N95s with innovative designs and materials.

The post U-M researchers helping to develop a machine for on-demand N95 mask manufacturing appeared first on Michigan Engineering News.

The unique program awards $875k in flexible funding.

The post Bioengineer and M.D. receives Packard Fellowship to study cellular memory appeared first on Michigan Engineering News.

The ability to accurately detect where X-rays land and in what dose could reduce the collateral damage from radiation therapy.

The post Tracking radiation treatment in real time promises safer, more effective cancer therapy  appeared first on Michigan Engineering News.

The challenge is a means of pushing forward with their research into development of next-generation embodied AI agents.

A delegation from LG AI Research visited campus to review LG-funded projects in process and discuss future collaborations.

The award recognizes the outstanding contributions of a young scientist in the field of theoretical computer science.

Lee designs implantable and wearable electronics to help restore movement to those who have lost limbs or have been paralyzed.

Look at some of the ways ECE and other University of Michigan researchers are using computer vision for real-world applications.

Being able to decide not only whether a micron-scale particle twists but also how much could open new avenues for machine vision and more.

The post For the first time, controlling the degree of twist in nanostructure particles appeared first on Michigan Engineering News.

Real-time data collected at the two-lane roundabout will be used to efficiently test the safety of autonomous vehicles.

The post World’s first realistic simulated driving environment based on ‘crash-prone’ Michigan intersection appeared first on Michigan Engineering News.

Automation uncovers combinations of amino acids that feed two bacterial species and could tell us much more about the 90% of bacteria that humans have hardly studied.

The post AI could run a million microbial experiments per year appeared first on Michigan Engineering News.

A new tool in the fight against superbugs goes beyond protein folding simulations like AlphaFold, potentially revealing antibiotic candidates.

The post Nanobiotics: AI for discovering where and how nanoparticles bind with proteins appeared first on Michigan Engineering News.

Machine learning points out why antibodies fail to stay on target, binding to molecules that aren’t markers of disease—and suggests better designs.

The post AI tool helps optimize antibody medicines appeared first on Michigan Engineering News.

U-M professor of computer science and engineering identifies new concerns that recent AI advances pose for financial markets.

The post Senate testimony: AI risks to the financial sector appeared first on Michigan Engineering News.

As the auto industry expands beyond transportation, university collaborations are more important than ever.

The post Toyota Research Institute and Michigan Engineering discuss importance of long-standing partnership appeared first on Michigan Engineering News.

Using a simple and convenient touchscreen interface, the algorithm learns the assistance preferences of the wearer.

The post Choosing exoskeleton settings like a Pandora radio station appeared first on Michigan Engineering News.

The world needs better tools to protect people during floods. A new machine learning method could help.

The post Outsmarting floodwaters appeared first on Michigan Engineering News.

The semiconductor-compatible technology is a million times faster than existing electronics and could give us access to an entire new world of quantum phenomena.

The latest DoD funding announcements bolster Michigan Engineering’s efforts to support revitalization of the U.S. semiconductor sector.

‘In undergrad, you sometimes feel like you’re just passing classes. But what we’re doing here is science.’

The post Semiconductor workforce program increases access to hands-on training appeared first on Michigan Engineering News.

Prof. Eid is looking to design the future of smart cities and infrastructures using ultra-low power wireless sensing and communications technologies.

Prof. Eid is looking to design the future of smart cities and infrastructures using ultra-low power wireless sensing and communications technologies.

A new fabrication process greatly improves the reliability of highly-efficient semi-transparent solar cells, which can be applied to windows to generate solar power.

Mack Kira, co-director of the Quantum Research Institute with Steven Cundiff, is ready to take Michigan’s quantum activities to the next level.

U-Michigan joins industry, state, education partners to develop talent and technology.

While hunger for an artificial intelligence that can think like a human remains unsated, AI continues to appear in our lives in smaller ways.

Quantum information science and engineering is one of the hottest fields in engineering – and ECE wants to make it accessible to everyone.

Deep learning models that power giants like TikTok and Amazon, as well as tools like ChatGPT, could save energy without new hardware or infrastructure.

The post Optimization could cut the carbon footprint of AI training by up to 75% appeared first on Michigan Engineering News.

The results of monitoring for diseases beyond COVID-19 are now publicly available for Ann Arbor, Flint, Jackson, Tecumseh and Ypsilanti.

The post Wastewater dashboard adds monkeypox, flu and more for five southeast Michigan communities appeared first on Michigan Engineering News.

New virtual testing environment breaks the ‘curse of rarity’ for autonomous vehicle emergency decision-making.

The post Simulated terrible drivers cut the time and cost of AV testing by a factor of one thousand appeared first on Michigan Engineering News.

Yoo is making memory devices more flexible and tunable, making them irresistible for modern AI applications.

Aditya is creating high-resolution, accessible, scalable, and portable imaging radars that are 200x cheaper and 100x smaller than what is currently available.

Prof. Zetian Mi’s team proved the viability of a reconfigurable, ScAlN/AlGaN/GaN ferroelectric HEMT transistor that is critical for next-generation communication and computing systems

The tool is expected to advance the study of exciton dynamics, which could help identify new research directions for clean energy and information technology.

Xiao has been working on several projects in Prof. Zetian’s Mi’s group, including micro LED technology and renewable energy.

Navid’s research is focused on artificial photosynthesis and optoelectronics using III-Nitride based semiconductor materials.

Next-gen computing material gets down to the right size for modern manufacturing.

The post Nanoscale ferroelectric semiconductor could power AI and post-Moore’s Law computing on a phone appeared first on Michigan Engineering News.

Led by Prof. Becky Peterson, the research focuses on a category of materials important for low power logic operations, high pixel density screens, touch screens, and haptic displays.

The post Scalable method to manufacture thin film transistors achieves ultra-clean interface for high performance, low-voltage device operation appeared first on Michigan Engineering News.

Dr. Mehdi Saligane, a leader in the open-source chip design community, was among the first researchers to fabricate a successful chip as part of Google’s multi-project wafer program.

The post Open-source hardware: a growing movement to democratize IC design appeared first on Michigan Engineering News.

Thatchaphol Saranurak and collaborators were recognized at SODA ’23 for their work that broke an approximation barrier in dynamic graph matching.

U-M CSE PhD candidate Sarah Jabbour discusses how collaboration is centered in her experience as a graduate student.

The Michigan AI Lab is focused on building a community of diverse viewpoints in an effort to reduce the bias we see in the exploding world of artificial intelligence.

U-M CSE PhD candidate Sarah Jabbour discusses how collaboration is centered in her experience as a graduate student.

The SCISCCO system could better monitor brain and organ metabolism, helping to diagnose concussions, monitor cerebral metabolism in traumatic brain injury patients, and gauge the response of organs to treatments in an operating or emergency room scenario.

The post New non-invasive optical imaging approach for monitoring brain health could improve outcomes for traumatic brain injury patients appeared first on Michigan Engineering News.

Euisik Yoon’s team, led by Sungjin Oh, developed a low-power neural recording front-end circuit to interface with state-of-the-art neural probes.

The post Best paper for a low-power ADC circuit for brain-machine interface applications appeared first on Michigan Engineering News.

A team led by P.C. Ku and Qing Qu has developed a miniature, paper-thin spectrometer measuring 0.16mm2 that can also withstand harsh environments.

The post Miniature and durable spectrometer for wearable applications appeared first on Michigan Engineering News.

Known affectionately as “The Sh*tty Project,” Codling, an ECE PhD student, monitors the vibrations in pig pens to track the health of the piglets and predict when they’re in danger.

$10M will fund training for 60 postdoctoral fellows as part of international cohort.

Mechanical engineers at the University of Michigan are tackling mysteries of bone density loss in space and on Earth.

The post Gravity’s impact on bone cells—experiments heading to the International Space Station appeared first on Michigan Engineering News.

Three Michigan Engineering faculty help to elevate communities and systems through a people-first approach to teaching.

The post Expert take: Engineering for the success of humanity appeared first on Michigan Engineering News.

Jason Mars, CEO of Ann Arbor startup Clinc, was named #2 in Bank Innovations’s “10 Most innovative CEOs in Banking 2017” list. Clinc is leading the pack for development of intelligent banking assistant software.

Even though we interact with different web services in different ways, there are clues in the data that can indicate trends and identify a unique profile.

The researchers identified movement between industry, academia, and government work, tracked the growth of important organizations, and built predictive models for career transitions and employer retention.

Jie Song devised a method to combine summarized datasets that group information by incompatible units.

Foofah is a tool that can help to minimize the effort and required background knowledge needed to clean up data.

Researchers have implemented a new way to diagnose software failures with a high degree of accuracy and efficiency.

Researchers used hierarchical trees to provide a better idea of how concepts are represented and related in a collection of text.

This conversational in-vehicle digital assistant can respond to drivers’ questions and commands in natural language

Kasikci presents a method to improve a program’s ability to use data in a straightforward, efficient way

Graphs that are customized, stored locally, and able to change over time can enable faster and more accurate searching and digital assistants

Chowdhury’s lab multiplied the number of jobs a GPU cluster can finish in a set amount of time

The goal of the work was to identify seven things about who the subject was talking to just by analyzing text messages.

Perez’s research focuses on analyzing speech patterns of patients with Huntington Disease.

Danai Koutra earned the award for her proposal to innovate the way we use networks to understand the world and speed up our technology.

Erie provided database repairs that were previously performed exclusively by human programmers.

Using real-time fMRI readings, researchers linked spatial reasoning with CS problem solving.

As a fungal infection ravages bat populations, the new game hopes to promote public awareness of ongoing research to combat the issue.

Tang’s project will redesign data center systems to support large-scale use of hardware accelerators to meet future computational demand.

The team’s new tool will combine of software and data to make gathering structured data dramatically easier.

Researchers plan to establish a framework for a national institute that would enable research using sensitive data, while preventing misuse and misinterpretation.

Researchers designed three new systems to speed up code at several key bottlenecks.

Comparing graphs the team’s tool is up to an order of magnitude faster than competitive baselines.

This round of funding strongly encourages pioneering work with the potential for major expansion.

A team at Michigan proposed an approach to generating realistic and high-fidelity stock market data to enable broader study of financial markets.

Researchers have demonstrated the ability to “unlearn” sensitive identifying data from audio used to train machine learning models.

Most programs in use today have to be completely rewritten at a very low level to reap the benefits of hardware acceleration. This system demonstrates how to make that translation automatic.

Goel designs algorithms that can automatically demonstrate the correctness of hardware systems.

Subarno Banerjee uses program analysis to improve software systems’ safety and security.

The student’s project targets critical moments where the next instruction in a program is only available in a slower type of memory.

The team will build high-quality datasets to enable automatic quality checking and fraud detection of the new coronavirus data.

Researchers are working with the city on two key initiatives to address food availability for elderly and low-income populations.

“My research has the potential to democratize programming and make it possible for millions of people around the globe to automate otherwise tedious tasks using programming.”

The system targets software that runs using concurrent execution, a widespread method for boosting performance, and proves whether a program will output what it’s supposed to.

A new secure code is needed to protect private information from the power of quantum computing.

His work is in complexity theory of distributed computing.

The award recognizes early career faculty who show great promise in developing future computing technologies.

The new technique automatically constructs policies for applications that keep them from compromising other programs.

How automated guarantees that our most complex programs are secure and trustworthy can save us time, money, and anxiety.

The Michigan Game Studios database, developed by lecturer Austin Yarger, helps organize the state’s rapidly growing scene.

Through his work, Tim hopes to dramatically accelerate genomic sequencing analysis, enabling the use of handheld genomic sequencers to produce actionable diagnostic data within minutes.

The thesis completely solves a longstanding open problem in the theory of distributed computing.

Prof. Greg Bodwin has devised a solution to an important open question in graph theory that offers promising new options for repairing and constructing resilient networks.

Baris Kasikci plans to improve software fuzzers by learning how deployed software is most commonly run by users.

Probabilities with a negative sign have been of great use in quantum physics.

100+ researchers from across the University of Michigan and from industry gathered on North Campus for the third U-M Workshop on Data Mining.

The paper proposes an interactive natural language interface for relational databases, which enables novice users to construct complex queries.

The software enables users to ask questions about the hosts and networks that compose the Internet and get an immediate reply.

Prof. Mozafari is passionate about building large-scale data-intensive systems that are more scalable, more robust, and more predictable.

He has built software systems for information extraction, database integration, and feature engineering and applied these to problems in the social sciences.

The paper explores how automated speech recognition and crowd-sourced human correction and generation of transcripts can be traded off to improve accuracy and latency.

CSE students and faculty will collaborate as a part of a larger team to help respond to the crisis.

Secrets lurk in the dark web, the 95 percent of the internet that most of us can’t see. One U-M professor is bringing some of those secrets to light, making the digital and the real world a little safer.

The team will use fMRI to identify some of the underlying processes that occur when a code reviewer weighs in on a piece of software and its author.

The system can add more flexibility to task management apps to help learning users make informed decisions about their time.

K-5 teachers and students throughout Michigan are building thriving learning communities online by using free deeply-digital, standards-aligned curricula and platform developed by the U-M Center for Digital Curricula.

The monitoring system will collect data from surface and penetrating sensors, then wirelessly relay the information to an inspector on site or miles away.

The 5-week course will provide the technical background and public policy foundation that today’s citizens need to understand the electronic voting debate.

Serial entrepreneur Dug Song (CS BS 1997) and recent alum Jon Oberheide (CSE PhD 2011) founded security firm Duo Security in early 2010 and have rapidly grown their company to serve over 500 customers in 40+ countries around the world.

The project proposes to produce a parallel heterogeneous 3D near-threshold computing system with unprecedented energy efficiency.

The paper addresses how to manage multiple sources so that the user can maximize the information gained from each acoustic source.

HiJack is a hardware/software platform that utilizes the headset jack on a smartphone as a universal power/data interface.

A really big chip is ready to take on really big challenges.

Virta Laboratories was co-founded in part by Prof. Kevin Fu and former CSE postdoctoral researcher Denis Foo Kune.

The researchers are finding a solution to implement state-of-the-art vision systems in wearable devices where there is little heat dissipation

Prof. H.V. Jagadish sheds light on current issues regarding data privacy and technology.

New software developed by CSE engineers and inspired, in part, by a Batman movie, could give any smartphone the capacity to sense force or pressure on its screen or body.

U-M team will serve as model for nimble and innovative system-on-chip design.

The symposium highlighted new developments in computer architecture, and included a session on how the center’s research can contribute to limiting the impact of pandemics.

The approaches to energy adaptation he proposed are now commonplace, and the applications he analyzed (web browsers, voice recognition, video players, and maps) are still ubiquitous.

Recent breakthrough developments in technologies for real-time genome sequencing, analysis, and diagnosis are poised to deliver a new standard of personalized care.

The award recognizes Prof. Wenisch’s contributions to memory persistency and energy-efficient systems.

His work in the area of real-time computing has spanned decades and has had impact in a broad range of applications.

The papers provide data-driven solutions to hospital infection and the use of machine learning in healthcare.

The result will be new measurement methods to determine how moods are shaped by both the behavior of an individual and daily interactions over time

“What I’m doing is trying to come up with ideas to let the agent continue learning different skills across its life.”

New algorithm can help robots go from structured environments like factories to complex, unstructured places like our homes.

The new event series aims to create an educational environment for the public.

Baveja’s paper tackled the difficult problem of giving artificial intelligence a way to understand and represent knowledge collected over time.

The goal of Lasecki’s proposal is to create methods for making AI systems more robust and flexible.

May Mobility intends to gradually acclimate the public to the experience of autonomous driving.

The authors provide an overview of common challenges to implementing ML in a health-care setting, and describe the necessity of breaking down the silos in ML.

Up to this point, no attacks had been discovered targeting a car’s LiDAR system—but a major new finding from researchers at the University of Michigan has demonstrated what that might look like.

The goal of the symposium is to facilitate conversations between AI practitioners from Michigan and beyond.

Wurman and his cofounders were recognized for their invention of the Kiva system, a revolutionary warehouse order fulfillment system that uses mobile robots and control software to bring inventory shelves to workers.

The students and faculty submitted projects spanning several key application areas for AI.

Her work uses machine learning to measure mood, emotion, and other aspects of human behavior for purposes of providing early or real-time interventions for people in managing their health.

Five multidisciplinary research teams are working on projects to assist with the coronavirus outbreak and to help find solutions to pressing problems.

Mower Provost talks about getting awards, doing industry research, understanding human behavior – and Star Wars.

The project, which received a best paper award, demonstrated that a certain bias in humans who train intelligent agents significantly reduced the effectiveness of the training.

The virtual interviewer uses therapeutic writing techniques to help users cope with difficult situations.

The model is a practical method for robots to look for target items in complex, realistic environments.

Kasikci will sift through the byproducts of hundreds of millions of common program executions to determine how this data can automate some key steps in bug finding and fixing.

The Rising Star Award is based on an individual’s whole body of work in the first five years after the PhD.

The project enables neural networks to model how people are positioned based on only partial views of their bodies, like perspective shots in instructional videos or vlogs.

PhD student Emily Sheetz is working to design more dexterous robots to work alongside humans in space.

This distinction recognizes young researchers with exceptional promise who are having an impact on the world.

His work on reinforcement learning is aimed at accelerating the training of RL agents.

Twelve students and faculty co-authored papers spanning several key application areas for AI.

His work is in the area of coordinating systems of autonomous agents that operate in uncertain, dynamic environments.

Wang hopes that, by summarizing longer documents, she can make a new class of information more accessible to a variety of audiences.

The fellowship will advance her work in inferring relational world knowledge in machines with explicit and implicit representations.

Zhizhuo is interested in computer vision and its ability to make breakthroughs in interdisciplinary fields such as ecology and climatology.

Through his work in NLP and computational social science, Sky hopes to understand complex social interactions and contribute towards the democratization of technology.

Through her work in augmented reality, Jaylin hopes to improve the accessibility of emerging technologies for people with disabilities and expand access to computing.

A new method enables robot arms to build a tower of champagne glasses.

A new algorithm gives autonomous agents the ability to take in batches of multiple instructions at once while responding dynamically to changes in their surroundings.

New model PixelSynth creates an interactive experience given just a single image.

Prof. Chai has been recognized for significant contributions to grounded natural language processing and the interaction between language processing and robotics.

His goal is to build AI systems that can recognize and understand a 3D and interactive world from a single image.

The LG AI Research Center, and its partnership with U-M, represents a commitment by LG to become a leader in developing advanced AI technologies.

The meetup was intended to foster connections between researchers across campus with an interest in the development and application of NLP.

The two will collaborate on building new programming techniques that are accessible to non-experts and non-programmers.

Team SEAGULL, led by doctoral student Yichi Zhang and advised by Prof. Joyce Chai, strives to develop embodied AI agents capable of attending to users’ needs, following natural language instructions, collaborating, and continuously improving through interaction.

The projects are a part of LG’s mission to advance AI such as Deep Reinforcement Learning, 3D Scene Understanding, and Reasoning with a Large-scale Language Model and Bias & Fairness related to AI ethics.

When decisions about your healthcare are informed by AI, bias in machine learning can have dire consequences. Ph.D. student Trenton Chang researches how inequities in healthcare delivery impact machine learning and AI.

All of the research being presented focuses on getting the absolute best performance from the tiniest circuits, sensors, and electronic devices.

This research is expected to have a fundamental and long term impact on a diverse set of applications ranging from energy conservation to health care.

The M3 is a fully autonomous computing system that acts as a smart sensing system.

Research led by Prof. Zetian Mi has been honored with the 2020 Editor-in-Chief Choice Award from “Photonics Research.”

The post High Efficiency Ultraviolet Light Emitting Diodes to sterilize pathogens, including COVID-19 appeared first on Michigan Engineering News.

Liu’s most recent research involves online learning, modeling of large-scale internet measurement data, and incentive mechanisms for security games.

DARPA is trying to build a system that can turn large data sets into models that can make predictions, and U-M is in on the project.

Mingyan Liu, recipient of the 2018 Distinguished Innovator of the Year award, gave a talk about her startup company and participated on a panel discussing data science commercialiation.

Hero and Lindquist took a few minutes to talk about the impact of machine learning on Signal Processing and Control Systems, and what they plan to do about it

Kim takes an interdisciplinary approach to tackle challenges in heterogeneous classes of energy-efficient and versatile communication systems.

His research develops computational methods for learning succinct representations from high-dimensional data.

Prof. Al Hero was interviewed and gave a presentation about his research using machine learning to improve our understanding of the human gut

The digital beamforming chip offers significant advantages over current analog beamforming solutions.

Rather than installing new “2D” semiconductors in devices to see what they can do, this new method puts them through their paces with lasers and light detectors.

Komma, a PhD student, is working to develop robust low powered localization technology for Artificial Intelligence enabled Internet of Things in locations where GPS is limited or blocked.

The research could improve efficiency in systems such as electric vehicles, grid systems, mass transit, and industrial automation

Michael Flynn and his group are applying their groundbreaking work in beamforming to the challenge of low-power on-chip speech recognition.

In a project he calls the “Marauder’s Map,” Prof. Zhang uses machine learning-based data models, physics models, and heuristic models to turn physical structures into sensing devices.

When the pandemic shut down in-person instruction, this six-member team created and delivered individual lab kits to 1,200 students around the world so hands-on lab experience could continue.

From the internships that inspired her interest in signal & image processing and machine learning to late night study sessions at the Duderstadt to her background in classical dance, Master’s student Rucha Apte shares her journey with us.

The ability to precisely tune electrical polarization switching through molecular beam epitaxy is a gamechanger

The study yields new insights into the survival of a native snail important to Tahitian culture and ecology and to biologists studying evolution, while proving the viability of similar studies of very small animals including insects

The ECE startup builds neuromorphic computer chips uniquely suitable for AI applications

The post Michigan startup MemryX, Inc. promises faster, cheaper AI processing appeared first on Michigan Engineering News.

Prof. Elaheh Ahmadi is working to design a new kind of semiconductor that can provide high power at high frequencies

Ahmadi’s research is focused on using GaN and Ga2O3 materials to provide higher output power per unit area at higher frequencies.

Prof. Jay Guo and his team discovered a scalable way to settle down and precisely arrange micro- and nano-sized particles according to size

The post Egg-carton-style patterning keeps charged nanoparticles in place and suitable for a wide range of applications appeared first on Michigan Engineering News.

Mi’s research is impacting the future of alternative energy, as well as improved methods for water purification and air disinfection.

Yoon’s research has contributed to a better understanding of the brain, as well as improved detection and treatment of cancer.

Hofmann’s control technology has been implemented in commercial vehicles, and he works tirelessly to enhance opportunities for underrepresented students.

A recent breakthrough in ferroelectric III-V semiconductors at the University of Michigan has been followed by several advancements and new funding to bring the technology closer to market.

A longstanding collaboration between engineers and neuroscientists leads to new insights into how neurons work in the hippocampus.

A charge-neutral information carrier could cut energy waste from computing, now that it can potentially be transported within chips.

Jian’s research is focused on improving the efficiency of high-power electronics, which is important for energy security and sustainability.

Mohanty’s research is focused on advancing high electron mobility transistors for next generation wireless technologies.

Jian works to improve the efficiency of high-power electronics for better energy security and sustainability.

Atif’s coding framework addresses quantum information network coding problems and has helped uncover new insights into the world of quantum information.

The book was co-authored by ECE Master’s student Wesley Joo-Chen Thio and Professor Emeritus Julien Sprott of U Wisconsin.

Prof. Zetian Mi leads a team that created highly-efficient red micro LEDs suitable for augmented and virtual reality.

Patel and Michielssen developed the Wigner-Smith time delay matrix for electromagnetics.

Bentley presented her research as an NDSEG Fellow. She is working to make smaller, more affordable high accuracy navigation-grade gyroscopes.

As a member of the X-lites program, ZEUS joins an international community of extreme light labs working together to advance laser science for the benefit of society

The ZEUS laser at the University of Michigan has begun its commissioning experiments

The CHIPS and Science Act of 2022 promises to revitalize the U.S. semiconductor industry. Dennis Sylvester offers his perspective on what it means for ECE.

The post CHIPS and Science Act: Implications and opportunities appeared first on Michigan Engineering News.

Flynn is one of the world’s premier scholars of analog and mixed-signal integrated circuits and systems, analog-to-digital conversion (ADC), and other interface circuits.

Armin’s research is focused on the development of a sub-millimeter-wave radar system for the next generation of navigation and imaging sensors.

The University hosted the 2016 Robotics: Science and Systems Conference, which allowed attendees to hear about the latest in robotics through talks, presentations, workshops, and tutorials.

Prof. Ozay’s award-winning work will be used in future space missions

Centralizing available data in the intelligent systems community through a COmputer Vision Exchange for Data, Annotations and Tools, called COVE.

Office of Naval Research has awarded Dmitry Berenson, an assistant professor of Electrical Engineering and Computer Science, $1.1 million to help advance emergency response capabilities for robots.

New walking robot based on birds

As a member of the DDOTS to PICS MURI, Revzen will advance modeling and control of dynamic systems.

How to build fast and cheap robots

A biologist turned roboticist takes a closer look at dog gaits to help design better movements for four-legged robots.

Putting our arm movements into code.

Prof. Shai Revzen’s lab in ECE has developed an inexpensive technique to rapidly fabricate a variety of useful robots.

Prof. Jessy Grizzle has long said that his work in robotics could one day be used to help the disabled. Now he and his group, alongside French company Wandercraft, are working to make that claim a reality in the form of walking exoskeletons.

Research will focus on how autonomous vehicles adapt to wide-ranging changes.

Berenson works to improve the ability of autonomous robots to handle soft, deformable objects.

Five college teams test robotic suits that could enhance humans’ abilities.

PhD student Jean Young Song offers an improved solution to the problem of image segmentation.

The most exciting use of AI for me focuses around a better collective use of our available resources, says Corso.

Prof. Robert Dick and advisee Ekdeep Singh Lubana developed a new technique that significantly improves the efficiency of machine vision applications

Researchers built the first visual SLAM processor on a single chip that provides highly accurate, low-power, and real-time results.

Second Prize overall went to doctoral student Xiuzhang Cai for his radar target classification research applicable to autonomous vehicles.

The team was awarded a Best New Application Paper Award by the IEEE Robotics and Automation Society for their work developing reliable control systems for Lane Keeping and Adaptive Cruise Control.

CE undergrad Amulya Parmar designed a machine learning algorithm to curb fake news as part of the Tavtech Fellowship program.

Cassie Blue, the bipedal robot, takes advantage of the 2019 polar vortex to set a record-breaking walk.

The Center for Entrepreneurship profiles a team of EECS students, who are working to develop the next generation of delivery vehicles.

University of Michigan researchers have been awarded an NSF grant to design an open source framework for robotic prosthetic legs that function more naturally and offer a wider range of capabilities.

Prof. Mingyan Liu is a key member of a project to mitigate bias in Artificial Intelligence and Machine Learning systems for long-term equitable outcomes.

Transparent optical sensor arrays combine with a specialized neural network in new University of Michigan prototype

With the help of 1.6 million GaN nanopillars per sensor, the University of Michigan team was able to provide human-level sensitivity with directionality on a compact, easily manufactured system

Seiler’s contributions to Matlab’s Robust Control Toolbox and to the control of vehicle platoons have resulted in major industrial applications.

Prof. Peter Seiler co-authored the paper that focuses on reachability analysis for a variety of systems, including aircraft control and autonomous vehicles.

Prof. Emeritus Daniel Atkins III chaired and Prof. Al Hero served on a National Academies committee that published a new report describing the impact of artificial intelligence and automated research workflow technologies in propelling research and scientific discovery.

Having excelled in careers at Microsoft, Amazon, and now Meta, the alum and renowned video game engineer co-founded The Motor City Alliance to make Detroit a powerhouse for FIRST Robotics teams

‘You shouldn’t need a Ph.D. to design new computing systems.’

DARPA’s initiative to reinvigorate the microelectronics industry draws deeply on Michigan Engineering expertise.

How changing the rules of computing could lighten Big Data’s impact on the internet.

PhD student Trevor Odelberg is looking to enable long range, highly reliable, and low-power cellular IoT devices that one day can run entirely on harvested energy, reducing battery waste and empowering devices to last for decades.

The post Batteryless next-generation cellular devices could empower a more sustainable future appeared first on Michigan Engineering News.

The frame in which a human marks out the boundaries of an object makes a huge difference in how well AI software can identify that object through the rest of the video.

Graphical online simulation could spur more targeted COVID-19 protection measures.

Could human-robot collaboration revitalize an outmoded business model and attract new workers?

The post Remodeling the construction industry appeared first on Michigan Engineering News.

The new $2.5 million endowment to support a professorship is the second U-M sponsorship from Toyota

The post Toyota funds professorship in AI at U-Michigan appeared first on Michigan Engineering News.

With new courses at the UG and graduate level, ECE is delivering state-of-the-art instruction in machine learning for students in ECE, and across the University

A major defense project pivots to explore how to encourage COVID-safe behavior effectively.

As COVID-19 looks more like a disease of the immune system, a Michigan engineer is working with doctors to look at how immune responses differ between mild and severe cases.

The post Engineering immunity: Profiling COVID-19 immune responses and developing a vaccine appeared first on Engineering Research News.

The web tools will help state officials identify potential hotspots as they reopen Michigan to business.

When white blood cells don’t know when to stop, an injection of rod-shaped particles may draw them away from a site of excessive inflammation.

The post How rod-shaped particles might distract an out-of-control immune response appeared first on Engineering Research News.

Public policy and engineering team up to improve food access.

The post Hunger and COVID: Fighting pandemic-related food insecurity in Detroit appeared first on Michigan Engineering News.

Medical giant Johnson & Johnson and federal HHS select U-M design with “minimal impact on daily life.”

The post Personal cold plasma “air curtain” design for COVID-19 protection moves forward appeared first on Michigan Engineering News.

Research in mice shows efficacy for multiple sclerosis.

The post Treating autoimmune disorders with an inhaler, rather than an IV appeared first on Michigan Engineering News.

Measuring RNA from SARS-COV-2 allows for more accurate testing than similar methods.

The post More responsive COVID-19 wastewater test developed appeared first on Michigan Engineering News.

First-of-its-kind study examined multiple pathogens, as well as filtration and fit.

The post N95 mask disinfection: New evidence on how hospitals can effectively recycle key PPE appeared first on Michigan Engineering News.

The method could one day be used to develop nanobodies against other viruses and disease targets as well.

The post New protein engineering method could accelerate the discovery of COVID-19 therapeutics appeared first on Michigan Engineering News.

“Wastewater-based epidemiology has shown to be a valuable tool to inform public health officials of case levels and infection trends in a community.”

The post Michigan researchers get $5.3M to expand COVID-19 wastewater monitoring appeared first on Michigan Engineering News.

Material and size designed to give electrodes a chance to operate in the body for years.

The post Carbon fiber brain-implant electrodes show promise in animal study appeared first on Michigan Engineering News.

A conventional approach to HIV vaccination does not induce immune responses in everyone equally, and a new computer model shows why.

The post Predicting how well a vaccine will work for you appeared first on Michigan Engineering News.

In preparation for climate adaptation in water-stressed areas, researchers will assess how well existing treatment systems prepare water for reuse.

The post Wastewater to drinking water: EPA grants $1.2M to U-M for virus removal study appeared first on Michigan Engineering News.

The model can be used as a tool to inform decision-makers and individuals on relative risks and advantages associated with a layered defense.

The post Michigan Engineering group creates model for layering COVID-19 defenses appeared first on Michigan Engineering News.

The multidisciplinary research team ​​will synergize efforts across the University.

The post New $13.8M center at U-M will study infectious disease, pandemic preparedness appeared first on Michigan Engineering News.

Twisted semiconductor nanostructures convert red light into the twisted blue light in tiny volumes, which may help develop chiral drugs.

The post New photonic effect could speed drug development appeared first on Michigan Engineering News.

Computer modeling links a person’s genes to whether producing more antibodies will help them fight off the disease.

The post How well do boosters work? Depends on your genes appeared first on Michigan Engineering News.

Terahertz light creates twisting vibrations in biomolecules such as proteins, confirming whether their compositions and structures are safe and effective.

The post Twisted vibrations enable quality control for chiral drugs and supplements appeared first on Michigan Engineering News.

Studies in mice show how the two of the body’s natural injury responders conflict following traumatic muscle injuries.

The post Recovery from muscle loss injuries hindered by immune cell conflicts appeared first on Michigan Engineering News.

Michigan Engineering researchers will help reveal pathways for virus detection and transmission

The post Interdisciplinary study seeks to mitigate transmission of respiratory viral diseases such as flu and COVID-19 in children appeared first on Michigan Engineering News.

Technique pioneered at the University of Michigan could improve outcomes for cancer and neurological conditions.

The post Tumors partially destroyed with sound don’t come back, in rats appeared first on Michigan Engineering News.

Nano-engineered drugs that stop harmful bacteria and viruses could be on the horizon.

The post Nanobiotics: model predicts how nanoparticles interact with proteins appeared first on Michigan Engineering News.

A protein that crosses the blood-brain barrier carries a drug that kills tumor cells and another that activates the immune system.

The post $2.38M to test nano-engineered brain cancer treatment in mice appeared first on Michigan Engineering News.

Work for the Michigan Department of Environment, Great Lakes and Energy will develop a policy roadmap to safe, low cost water services.

The post University of Michigan partners on multi-institution planning effort for state’s water future appeared first on Michigan Engineering News.

Polyurethane locks in the antimicrobial power of tea tree and cinnamon oils. The new technology could start making public spaces safer within a year.

The post Durable coating kills the COVID virus and other germs in minutes appeared first on Michigan Engineering News.

Cancer cells delete DNA when they go to the dark side, so a team of doctors and engineers targeted the “backup plans” running critical cell functions.

The post Shutting down backup genes leads to cancer remission, in mice appeared first on Michigan Engineering News.

An electrode array implanted in the brain predicts finger motions in near real time.

The post Individual finger control for advanced prostheses demonstrated in primates appeared first on Michigan Engineering News.

A new machine learning platform detects and quantifies radiation-induced defects instantaneously and could be extended to interpret other microscopy data.

The post Augmented reality for testing nuclear components appeared first on Michigan Engineering News.

University of Michigan to explore inventive uses for the technology, including material science, biology and medicine

The post Update: Augmented reality engineering startup lands $1.1M SBIR grant appeared first on Michigan Engineering News.

For now, Grizzle and his graduate students are only attempting the easiest routes, between the grassy two- to three-foot moguls, over smaller undulations that he calls “merely very difficult.”

Cassie is the first offering from new startup Agility Robotics, and is loosely modeled on the cassowary, a flightless bird similar to an ostrich.

Data gleaned from cameras and sensors increases predictive accuracy.

The post Teaching self-driving cars to predict pedestrian movement appeared first on Michigan Engineering News.

U-M researchers examined how a person’s perception of safety in an autonomous vehicle was influenced by its “personality” traits.

The post What humans want, in an automated car appeared first on Michigan Engineering News.

Charting a path to powered exoskeletons: A Q&A with Leia Stirling

The post Stronger, faster, further appeared first on Michigan Engineering News.

U-M startup says robotic food deliveries have quadrupled.

The post Delivery robots help Ann Arbor restaurants weather COVID appeared first on Michigan Engineering News.

An open-source perception and movement system, to be developed with NSF funding, could enable robots that partner with humans in fires and disaster areas.

The post $1M for open-source first-responder robots appeared first on Michigan Engineering News.

Tested without needing hospitals to share data, the method for developing the model could speed further improvements in medical prediction tools.

The post Open-source patient model tops industry standard appeared first on Michigan Engineering News.

Sheth is the co-founder of Inspiritus Health and has developed a simple to use, non-invasive medical device that keeps patients’ muscles engaged when they are on a ventilator to prevent muscle atrophy.

The adaptive immune system serves as a template for defending neural nets from confusion-sowing attacks

Quantum materials emit light as though it were only a positive pulse, rather than a positive-negative oscillation.

The post Emulating impossible “unipolar” laser pulses paves the way for processing quantum information appeared first on Michigan Engineering News.

Producing synthesis gas, a precursor of a variety of fuels and chemicals, no longer requires natural gas, coal or biomass.

The new computer model accurately predicts the behavior of millions of microbial communities from hundreds of experiments, an advance toward precision medicine.

Virtual assortment of user devices provides a realistic training environment for distributed machine learning, protects privacy by learning where data lives.

The post Open source platform enables research on privacy-preserving machine learning appeared first on Michigan Engineering News.

Highlights include The New York Times and National Geographic.

The post In the news: Michigan Engineering experts July 18-22 appeared first on Michigan Engineering News.

Highlights include CNN and Popular Science.

The post In the news: Michigan Engineering experts July 25-29 appeared first on Michigan Engineering News.

The hectoSTAR probe, with 128 stimulating micro-LEDs and 256 recording electrodes integrated in the same neural probe, was designed for some stellar brain mapping projects

The post Next generation neural probe leads to expanded understanding of the brain appeared first on Michigan Engineering News.

New technique could enable processing speeds a million to a billion times faster than today’s computers and spur progress in many-body physics.

The post Seeing electron movement at fastest speed ever could help unlock next-level quantum computing appeared first on Michigan Engineering News.

Prof. Zetian Mi’s team are the first to achieve high-performance, highly stable green micro-LEDs with dimensions less than 1 micrometer on silicon, which can support ultrahigh-resolution full-color displays and other applications.

The post Breakthrough in green micro-LEDs for augmented/mixed reality devices appeared first on Michigan Engineering News.

Housing Computer Science and Engineering together with the School of Information will drive advances in information and computing through a convergence of disciplines.

The post U-M celebrates Leinweber Computer Science and Information Building construction appeared first on Michigan Engineering News.

The cohort of 36 new tenured and tenure-track faculty includes 11 faculty hired at the rank of professor or associate professor.

The post Senior hires stand out in an impressive year for faculty hiring appeared first on Michigan Engineering News.