Johns Hopkins University Computer Science

Watch the keynote by JHU CS alum Carol Reiley here: https://www.youtube.com/watch?v=s9mOgH5VnEU

Design Day 2026 is TOMORROW (Tuesday): 900 Hopkins Engineering students share their projects, demos, and prototypes across campus at our annual showcase! Stream the keynote, delivered by Carol Reiley, ENGR ’07 (MS), CEO of DeepMusic.AI LIVE at noon.

Streaming Link: https://www.youtube.com/user/HopkinsEngineer/live

Visit the official Design Day website for schedule, locations and project previews! https://engineering.jhu.edu/designcenter/designday/

Follow Hopkins Engineering Instagram for project features and student interviews live from the floor all day: https://www.instagram.com/hopkinsengineer/

More about our Keynote Speaker: Carol Reiley, (a.k.a the “Mother of Robots”) is a serial entrepreneur, AI roboticist, and artist. She is currently CEO of AI and arts nonprofit DeepMusic.ai, a World Economic Forum Young Global Leader, and a brand ambassador for Guerlain Cosmetics. She previously founded Drive.ai—which was acquired by Apple—is a children’s book author, and a mentor for young kids in engineering.

Reiley is a pioneer in teleoperated and autonomous robot systems in applications such as surgery, space exploration, disaster rescue, and self-driving cars. She previously worked at Drive.ai, Intuitive Surgical, Lockheed Martin, and General Electric. She co-founded, invested, and was president of Drive.ai, raising over $77 million. She also founded Tinkerbelle Labs for low-cost health care as well as Squishybotz for educational robotics.

She is the author of "Making A Splash," a children’s book on the first growth mindset, which has sold more than 20,000 copies. She was also the first female engineer on the cover of MAKE Magazine and the youngest member on the IEEE Robotics and Engineering Board.

She earned her master’s degree in computer science from the Whiting School of Engineering in 2007 and led a robot outreach event for more than 1000 low-income students in the Baltimore/Washington, D.C., area. She is an advocate for underrepresented groups in technology and speaks out about bias in AI. Her work has been featured in the Wall Street Journal, The New York Times, MIT Tech Review, Vogue, Harper’s Bazaar, and Wired.

Developed by Johns Hopkins University researcher Suchi Saria, an early warning system for sepsis that has reduced deaths by nearly 20% has been approved for use by the U.S. Food and Drug Administration—one of the first AI-based medical tools to get clearance.

FDA approves early warning system for sepsis The AI system detects deadly infections faster than doctors, saving thousands from a condition that claims more than 250,000 lives each year in the U.S.

Check out the 🤖 research our scientists will be presenting next week at ICRA !

In “Pragmatic Embodied Spoken Instruction Following in Human-Robot Collaboration with Theory of Mind,” Xinyi Li, Shivam Aarya, Yizirui Fang, Yifan Yin, Tianmin Shu, and researchers from the Massachusetts Institute of Technology (MIT) and Brown University present a cognitively inspired neurosymbolic 🧠 model to enable robots to pragmatically follow human instructions under diverse speech 💬 conditions: https://arxiv.org/abs/2409.10849

Best Paper Finalist in Robot Learning “Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning” by Anand Bhattad and collaborators from Toyota Technological Institute at Chicago, Waymo, and more studies view-invariant imitation learning by explicitly conditioning policies on camera 🎥 extrinsics: https://arxiv.org/abs/2510.02268

Haoying Zhou, Chang Liu, Yimeng Wu, Junlin Wu, Peter Kazanzides, and Worcester Polytechnic Institute (WPI), University of British Columbia, and Politecnico di Milano researchers propose a multimodal data collection framework with offline and online synchronization to support training and real-time inference in “SurgSync: Time-Synchronized Multi-modal Data Collection Framework and Dataset for Surgical Robotics”: https://arxiv.org/abs/2603.06919

In “Markerless Tracking of Robotic Surgical Instruments With Head Mounted Display for Augmented Reality Applications” Nicholas Greene, Peter Kazanzides, and The Chinese University of Hong Kong 香港中文大學 - CUHK researchers propose a novel markerless tracking method for robotic instruments using a HoloLens 2: https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/htl2.70044

“Shared Haptic Control for Surgical Skill Transfer on a Dual-Console Da Vinci Research Kit” by Xiangyi Le, Nan Jiang, Pucheng Shao, Brendan Burkhart, Peter Kazanzides, and Ugur Tumerdem presents the first implementation of a multilateral controller 🎛️ on the da Vinci Research Kit.

and Zih-Yun “Sarah” Chiu and UC San Diego researchers propose an initial step towards lifelong robot learning for surgical automation in “SurgIRL: Toward Life-Long Learning for Surgical Automation by Incremental Reinforcement Learning”: https://ieeexplore.ieee.org/abstract/document/11223235/

Congratulations to Alan Yuille and his co-authors on their 2026 ICBS Frontiers of Science Award! This annual award from the International Congress for Basic Science recognizes top research in mathematics, physics, and theoretical computer and information sciences.

Yuille team receives 2026 ICBS Frontiers of Science Award The annual award from the International Congress for Basic Science recognizes top research in mathematics, physics, and theoretical computer and information sciences.

“This is part of a broader trend,” says Erik Rye, an incoming computer science professor at Johns Hopkins University. “These centralized systems are a double-edged sword.”

Maryland schools and universities spent Friday morning racing to restore classes, coursework and communications after a nationwide cyberattack knocked the Canvas learning platform offline less than two weeks before many campuses begin final exams.

The disruption began Thursday night after Instructure, the company behind Canvas, took the platform offline following what appeared to be a breach claimed by the hacker group “ShinyHunters.”

Read more: https://bit.ly/4u1lsGT

📸: AP Photo/Mark Schiefelbein

“Reality hijacking” is a risk with the spread of videos online, says JHU CS’ Anton Dahbura. “They’re damaging because it erodes the overall trust we can put in our senses.”

Ending OpenAI's Sora unlikely to slow influx of AI-generated video online, experts say OpenAI is discontinuing Sora, its app that allows users to generate artificial intelligence videos with text prompts.

As moves from promise to performance, one big question keeps percolating: How can the technology be deployed as a force for good? Johns Hopkins University’s Suchi Saria talks about ways to apply AI in the real world while navigating the challenge of building trust when the stakes are high.

AI For Good with Xero CEO Sukhinder Singh Cassidy and Bayesian Health Founder and CEO Suchi Saria As AI moves from promise to performance, one big question keeps percolating: How can the technology be deployed as a force for good? From automating workflows for millions of small businesses and identifying life-threatening conditions that improve patient outcomes, these two innovative leaders talk...

“The dependency of so many educational institutions on Canvas is certainly a systemic risk,” says JHU CS & Johns Hopkins University Information Security Institute’s Anton Dahbura. “Therefore, colleges should require stronger security measures plus resilience plans and alternatives for instruction during outages.”

Massive Canvas data breach hits colleges across California and nation, crippling student work A massive data breach of the Instructure Canvas learning system hit UC, CSU, USC, Stanford and Los Angeles community colleges, among other schools across the nation. A criminal group called ShinyHunters claimed credit for the hack.

"In the old days, usually [it would] take an expert maybe a month to really come up with those complicated attacks. Recently, with the help of AI, [it takes] sometimes maybe one or two days, they can really come up with those complicated attacks," says JHU CS and the Johns Hopkins University Information Security Institute’s Yinzhi Cao.

Maryland students react to Canvas data breach An online learning management system is back online after a cyberattack created chaos for local school districts and colleges in Maryland.

The U.S. Food and Drug Administration has approved Johns Hopkins University researcher Suchi Saria’s AI-powered early warning system, which can detect sepsis faster than doctors—saving thousands from a condition that claims more than 250,000 lives each year in the U.S.

FDA approves early warning system for sepsis The AI system detects deadly infections faster than doctors, saving thousands of lives from a condition that claims more than 250,000 lives each year in the U.S.