Graphic Designer

UI professor repairs damaged ancient manuscripts with AI. Paul Dilley received a $500,000 grant from Schmidt Sciences to develop AI tools that can reconstruct missing sections of ancient manuscripts. April 12, 2026 Paul Dilley, a University of Iowa assistant professor in the classics department, earned a $500,000 grant to use AI to restore ancient manuscripts, A University of Iowa-led research team is aiming to use AI to restore lost sections of ancient manuscripts, with support from a $500,000 grant from Schmidt Sciences, a philanthropic organization that funds unconventional scientific research. Paul Dilley, the Erling B. "Jack" Holtsmark Associate Professor in the UI's Classics department and the departmental executive officer of the UI Department of Religious Studies, will train AI models for the next three years to suggest hidden characters in ancient texts. Dilley said many ancient texts are uncovered by happenstance, such as the Herculaneum papyri, a collection of thousands of ancient Roman scrolls carbonized by the A.D. 79 eruption of Mount Vesuvius. "Often these texts aren't very well preserved," he said. "You need to take steps to make them legible again. Sometimes, those steps are difficult, as in the case of the Herculaneum papyri." Many ancient texts are filled with ink that has faded to the point where the naked eye can no longer discern it. "The first step in recovering these texts is usually some kind of enhanced imaging technique to try to make the ink appear more legible," Dilley said. "Multispectral imaging can make the traces of ink that are still left on the page really jump out." Dilley said he and his team will use multispectral imaging as a first step to identify ancient manuscripts, then bring AI to bridge any gaps. Honghai Zhang, a senior research scientist at the Iowa Institute for Biomedical Imaging - a multidisciplinary research initiative at UI that brings together different departments for medical imaging - used a similar form of multispectral imaging in a study analyzing medieval manuscripts. Zhang was part of a team that used medical CT scans, which use X-rays to take detailed images of the body, to look inside the books without opening them. "To extract hidden information from a damaged manuscript, parchment, or scroll, it's a huge effort," he said. "It involves the collaboration of people from different research fields." Zhang said the chemical buildup of the ink in a manuscript will play a large role in determining which scanner will best decipher the text. While Zhang's team used CT scans, others are using infrared-based scans, a process that takes several hours. "Imaging has been evolving and advancing for many years. Day in and day out, we're dealing with higher and higher resolutions," he said. "AI is also evolving, but using the combination of those two for ancient manuscripts is something new, which is interesting and challenging." Dilley said even as multispectral imaging continues to advance, there is a limit to what it can decipher. "If the manuscript has already been damaged, imaging obviously doesn't help you see the missing parts," he said. "That's where AI comes in." Dilley said editors will train the AI to perform a process called infilling, or suggesting restorations for letter fragments. Generative AI will also be used to infer and suggest new text for lacunas, or portions of manuscripts where all text is missing. For his current study, Dilley said the AI will be trained to perform infilling and restore lacuna for Greek, Latin, and Celtic languages. "The plan is to publish the models open access and to make it extendable to other languages," he said. "The basic pipeline should be extendable to other languages." Robert Cargill, the Roger A. Hornsby associate professor in the classics, said he and Dilley were hired at UI as part of a Digital Humanities Initiative in 2011, an emerging field that had just begun digitizing ancient texts and putting them in online libraries. Cargill said Dilley's new experimentation with AI is a similar instance of having the foresight to use emerging technology for studying the humanities. "There is some research that can be done without technology, and technology simply helps speed up the process," he said. "But there is other research, like the kind that Paul is doing, that just cannot be done without the help of technology and AI." Cargill said opening something like an ancient charred scroll would be impossible; simply, as it would crumble from frailty. With an AI algorithm that scans every layer and compares lines to a database of known letters in the ancient language, Cargill said such work is possible. "This is real research that 50 years ago we would have just called magic," he said. Cargill said Dilley's research, being conducted at Iowa, will help UI students learn about the emerging role of AI in the humanities, giving them a leg up in the job market. "The only other people doing it are nations. Israel is doing this with the Dead Sea Scrolls, but that's an entire government," he said. "Countries that have massive budgets are doing this, and Professor Dilley is able to do it here at the University of Iowa with this grant." Dilley said as his team looks to integrate AI into the humanities, it is important to give scholars space to have the final say on what lost sections of ancient manuscripts could have been. "It's definitely not meant to replace traditional human language learning and engagement, but it can be a way to make potential breakthroughs in otherwise very difficult sections of a damaged manuscript," he said. "It's meant to be a great help, but not the final say." Support the daily iowan. The independent, student-run newsroom at the DI covers the University of Iowa and local community to keep you informed. Your support helps provide the necessary resources and training to continue our mission.

Schmidt Sciences awards over $3m to study AI's impact on jobs. (C) Schmidt Sciences As part of its AI at Work program, Schmidt Sciences has awarded over $3 million to 19 real-world studies conducted by international labor economists about how AI is transforming jobs around the world, the organization announced today. The awardees will each receive up to $200,000 to study how emerging AI technology is affecting worker productivity, wages, employment and careers, with the goal of uncovering where AI can provide the greatest value to labor markets and the global economy, and where AI's impact will be felt most acutely. Schmidt Sciences is supporting both work underway and commissioning new studies. Over the next two years, awardees will conduct randomized controlled trials and similar field studies in job sites ranging from banks to factories to laboratories to the gig economy. The 19 researchers leading these efforts, selected from more than 300 applicants, represent a variety of career levels, from PhD candidates to professors, and hail from 16 institutions in eight countries. Their projects reflect this global scope, exploring how AI affects loan officers at East African banks, employees at Southeast Asian small businesses, workers in the Chilean government, job seekers in Sierra Leone and American drivers competing with autonomous taxis. AI at Work partnered with five leading economists to source, review, and select awardees. The review panel included MIT's David Autor and Nobel Laureates in Economics Daron Acemogluand Simon Johnson, University of Pennsylvania's Ioana Marinescu, University of Chicago's John List, the Abdul Latif Jameel Poverty Action Lab at MIT (JPAL), and research institution UNU-WIDER. In addition to funding, Schmidt Sciences is providing awardees with connections to its grantee network, feedback on their projects and access to computing support. These projects will also inform ongoing work between The Rockefeller Foundation, Schmidt Sciences and other foundations on scenarios for AI's impact on the labor markets. Last October,The Rockefeller Foundation collaborated with Schmidt Sciences to gather economists, AI companies and civic leaders at the Bellagio Center in Italy to develop scenarios that will inform actions that governments and companies can take to maximize the opportunities for AI to benefit the common good. * Youn Baek, postdoctoral associate, NYU Stern School of Business * Johanna Barop, doctoral candidate, Oxford University * Daniel Björkegren, assistant professor, Columbia University School of International and Public Affairs * Silvia Castro, postdoctoral researcher, INSEAD and Ludwig Maximilian University of Munich * Richard Freund, Senior Research Associate, MIDE Development and Non-Resident Researcher, UN University World Institute for Development Economics Research * Paul Gertler, Li Ka Shing Professor of Economics, UC Berkeley Haas School of Business * Luca Henkel, assistant professor, Erasmus University Rotterdam * Mitchell Hoffman, Richard F. Aster Jr. Professor of Economics, UC Santa Barbara * Ben Hyman, economist and senior researcher, California Policy Lab, UCLA * Brian Jabarian, Howard & Nancy Marks Fellow (postdoctoral), University of Chicago Booth School of Business * Hyunjin Kim, assistant professor, INSEAD * Tim Köhler, research fellow, University of Cape Town and research associate, Stellenbosch University * Johanna Barop, doctoral candidate, Oxford UniversityJoseph Levine, doctoral candidate, Oxford University * Benjamin Manning, doctoral candidate, MIT Sloan School of Management * Kristina McElheran, associate professor, University of Toronto * Jiarui (Jerry) Qian, doctoral candidate, University of Virginia * Simon Quach, assistant professor, University of Southern California * Jorge Tamayo, assistant professor, Harvard Business School * Nety Wu, doctoral candidate, INSEAD The AI at Work program plans to issue additional calls for proposals in 2026. Learn more about the program here.

$7M grant from NASA, Schmidt Sciences to upgrade arXiv. Cornell Tech has received more than $7 million from Schmidt Sciences and NASA to upgrade arXiv, an open-access research repository of more than 2.8 million articles. The funding will help arXiv - which is maintained and operated by Cornell Tech - finish migrating to cloud infrastructure and modernizing its code. It will also support the development of tools that offer personalized recommendations for discovering preprints. "I am profoundly grateful for this generous support from both Schmidt Sciences and NASA," said Greg Morrisett, the Jack and Rilla Neafsey Dean and Vice Provost of Cornell Tech. "This investment will ensure that arXiv can grow sustainably and continue to serve the needs of the global research community well into the future." Ramin Zabih, arXiv's executive director and professor of computer science at Cornell Tech, said the repository is undergoing a technology transformation to meet future challenges and respond effectively to changes affecting the research community. "The funding from Schmidt Sciences and NASA will allow us to complete our technology migration while simultaneously exploring ways to improve the service," said Zabih, who is also affiliated with the Cornell Ann S. Bowers College of Computing and Information Science. "We are grateful to Schmidt Sciences and NASA for supporting arXiv in its efforts to build a stronger foundation for the future." Schmidt Sciences' gift will allow arXiv to maintain an expanded development team and finish modernization without disrupting operations. NASA's grant will fund research into fairer, more effective discovery tools and help arXiv expand into subject areas of interest to the agency, such as planetary science. "Schmidt Sciences is thrilled to help support arXiv migrate to modern, scalable cloud technology, and ensure it can sustainably meet the accelerating demands of the global research community,"said James Ricci, director of science systems at Schmidt Sciences. "We hope that this will continue advancing open science for years to come." Founded in 1991 by Paul Ginsparg, professor of physics in the College of Arts and Sciences and of informations science in Cornell Bowers, arXiv has become a cornerstone of open science that serves scholars in physics, mathematics, computer science, quantitative biology, finance, statistics, electrical engineering and economics. In addition to the new gifts and grants, arXiv receives ongoing support from the Simons Foundation, academic libraries, universities, research organizations, professional societies and individual donors. Grace Stanley is the staff writer-editor for Cornell Tech.