Johns Hopkins University Computer Science

As part of Johns Hopkins University’s continued investment in data science and AI, the Department of Computer Science is pleased to welcome six new tenure-track faculty to its ranks this academic year!

Their research spans embodied and multimodal AI, algorithms and machine learning, and network security and privacy.

Learn more about our new assistant professors here: https://www.cs.jhu.edu/news/johns-hopkins-computer-science-welcomes-six-new-tenure-track-faculty/

Congratulations to our faculty on winning 2026 Johns Hopkins University Discovery Awards! Learn more about their proposed projects below:

CS faculty receive 2026 Johns Hopkins Discovery Awards Winning projects—chosen from 324 proposals—will accelerate the research of 132 individuals from across the university.

Congratulations to Johns Hopkins University computer scientists Ziyang Li and Yinzhi Cao on their team’s selection as a Genesis Mission Awardee by the U.S. Department of Energy.

Their $750,000 award will support the transformation of high-performance computing software development from an expert craft that requires years of specialized knowledge into a structured, reproducible, AI-assisted scientific workflow.

Learn more about how the team will advance innovation and strengthen America’s scientific leadership here: https://www.cs.jhu.edu/news/hopkins-led-team-selected-for-inaugural-department-of-energy-genesis-mission-award/

Hear from our researchers on how the Johns Hopkins University is harnessing the power of AI to develop new drugs, diagnostic tools, and administrative services:

Johns Hopkins already leads the medical world. On AI, it won’t be easy. Johns Hopkins is investing heavily in AI research and medicine, including training a robot to help in the operating room.

150 Years of Innovation: Suchi Saria is improving outcomes for sepsis patients with an AI-powered tool that helps doctors diagnose the deadly condition nearly two hours earlier than traditional methods.

Read the full article in the Whiting School of Engineering at Johns Hopkins University magazine: https://engineering.jhu.edu/magazine/history-made/150-years-of-innovation-2026/

Congratulations to Zongwei Zhou on receiving the 2026 Best Paper Award from IEEE Transactions on Medical Imaging! 🏆 The award recognizes his work on UNet++, now the most cited paper in the journal’s recent history and a standard tool in medical image analysis.

Zongwei Zhou receives IEEE Transactions on Medical Imaging Best Paper Award The award recognizes his work on UNet++, now the most cited paper in the journal’s recent history and a standard tool in medical image analysis.

In the Whiting School of Engineering at Johns Hopkins University magazine: “Design is not just about aesthetics,” says CS major Michael Baum, Engr ’27. “It is fundamentally about communication. Small decisions can determine whether someone immediately grasps the main idea or misses it entirely.”

Discerning Data - Johns Hopkins Engineering Magazine Storytelling with Data demonstrates the importance of ethically collecting and interpreting data.

Congratulations to our students on their Summer Provost’s Undergraduate Research Awards! ☀️ Learn about the projects they’re researching this summer here: https://www.cs.jhu.edu/news/five-cs-students-receive-summer-provosts-undergraduate-research-awards

📢 Attention undergrads! 📢 Join us next week for our second Faculty Research Panel of the summer to learn about research opportunities available to you and connect with faculty outside of the classroom! ☀️ Learn more here: https://www.cs.jhu.edu/event/computer-science-faculty-research-panel-8/

Congratulations to the Johns Hopkins University Computational Cognition, Vision, and Learning group on its acceptances to the American Association of Physicists in Medicine (AAPM) / Canadian Organization of Medical Physicists Annual Meeting and Exhibition ! Learn about the abstracts the team will be presenting next week in Vancouver 🇨🇦:

- ORAL PRESENTATIONS -

In “AI-Assisted Pancreatic Target Delineation on CT: Multicenter Validation and Contouring QA,” Wenxuan Li, Pedro R. A. S. Bassi, Xinze Zhou, Qi Chen, Kai Ding, Heng Li, Alan Yuille, Zongwei Zhou, and collaborators from UCSF develop and validate an AI system that supports radiotherapy-relevant pancreatic target 🎯 delineation: https://aapm.confex.com/aapm/2026am/meetingapp.cgi/Paper/25623

“Physics-Informed Synthetic Tumor Modeling In CT for Training and Stress-Testing Target Delineation AI” by Qi Chen, Wenxuan Li, Kai Ding, Heng Li, Alan Yuille, and Zongwei Zhou tests whether a “time-machine” ⌛ tumor synthesis pipeline can generate realistic small PDAC targets 🎯: https://aapm.confex.com/aapm/2026am/meetingapp.cgi/Paper/25952

Tianyu Lin, Junqi Liu, Kai Ding, Heng Li, Alan Yuille, and Zongwei Zhou test whether commonly used pixel-wise CT reconstruction metrics reflect the preservation of clinically relevant anatomy 🩻 for radiotherapy imaging in “Task-Based Evaluation of Sparse-View CT Reconstruction Metrics for Radiotherapy Imaging”: https://aapm.confex.com/aapm/2026am/meetingapp.cgi/Paper/26147

- SNAP ORAL PRESENTATIONS -

In “A Multicenter Pancreatic Target Segmentation Dataset for Radiotherapy and Imaging AI Benchmarking” Wenxuan Li, Xinze Zhou, Qi Chen, Pedro R. A. S. Bassi, Kai Ding, Heng Li, Alan Yuille, Zongwei Zhou, and collaborators from UCSF and NVIDIA provide a large, diverse, and quality-controlled abdominal CT dataset: https://aapm.confex.com/aapm/2026am/meetingapp.cgi/Paper/26254

“Weakly Supervised Radiotherapy Segmentation from CT Reports: Reducing Voxel-Wise Labeling for Target Tumors and Organs-at-Risk” by Pedro R. A. S. Bassi, Wenxuan Li, Xinze Zhou, Kai Ding, Heng Li, Alan Yuille, Zongwei Zhou, and UCSF colleagues reduces reliance on voxel-wise tumor masks by training CT segmentation models directly from radiology and pathology reports 📝: https://aapm.confex.com/aapm/2026am/meetingapp.cgi/Paper/26305

Pedro R. A. S. Bassi, Wenxuan Li, Alan Yuille, Zongwei Zhou, and Yucheng Tang establish a large-scale, independent benchmark for evaluating auto-contouring AI in “Benchmarking Auto-Contouring AI for Radiotherapy: Robustness, Calibration, and Failure Modes”: https://aapm.confex.com/aapm/2026am/meetingapp.cgi/Paper/27362

and in “Cancerverse: Multicenter CT Segmentation of 16 Cancers for Radiotherapy Targets and OARs,” Zongwei Zhou, Wenxuan Li, and Alan Yuille provide a large, multicenter, longitudinal CT dataset with voxel-wise tumor annotations across multiple cancer sites: https://aapm.confex.com/aapm/2026am/meetingapp.cgi/Paper/27460