Title: AI agents for scientific discoveries

Abstract: This talk will explore how generative AI agents can enable scientific discoveries. First, I will discuss how generative AI can expand researchers' creativity by designing and experimentally validating new small-molecule drugs. Next, I'll introduce the Virtual Lab—a collaborative team of AI agents conducting in silico research meetings, supported by real-world experiments, to design new therapeutics.

Bio: James Zou is an associate professor of Biomedical Data Science and, by courtesy, of CS and EE at Stanford University. He works on advancing the foundations of ML and in-depth scientific and clinical applications. Many of his innovations are widely used in tech and biotech industries. He has received a Sloan Fellowship, an NSF CAREER Award, two Chan-Zuckerberg Investigator Awards, a Top Ten Clinical Achievement Award, several best paper awards, and faculty awards from Google, Amazon, and Adobe. His research has also been profiled in popular press including the NY Times, WSJ, and WIRED.

Title: TBD

Abstract: TBD

Bio: Tanveer Syeda-Mahmood is an IBM Fellow and Global Imaging AI Leader in IBM Research. Currently, her group is leading the charge on advancing multimodal and bioinspired AI. She aims to advance the science of AI by drawing inspiration from computational models of various brain functions such as memory and learning and modeling the fusion of multiple modalities for information processing. The applications of the core technologies developed in the group are in various domains ranging from healthcare decision support, accelerated scientific discovery, to the building of next generation hybrid cloud data management and storage infrastructures. She is the General co-Chair of MICCAI 2023, the Program co-Chair of IEEE ISBI 2022, the program co-chair of CVPR 2008, a Fellow of IEEE, AIMBE, and MICCAI. She is the recipient of key awards including IBM Corporate Award 2015, Best of IBM Award 2015, 2016 and several outstanding innovation awards.

Title: TBD

Abstract: TBD

Bio: Daguang Xu is now a research manager at AI-Infra of NVIDIA. He is leading a research team in healthcare AI, focusing on developing world-class machine learning and deep learning-based methods to solve the challenging problems in medical domain. His current research interest includes but not limited to medical imaging analysis, EHR analysis, computer aided diagnosis, deep learning, pattern recognition and computer vision, etc. He has published 90+ papers on top journals and conferences and has ~50 granted or in-application patents. His team is the main developer of open source software (OSS) MONAI (https://github.com/project-monai) and NVIDIA Flare (https://github.com/nvidia/nvflare).

Title: TBD

Abstract: TBD

Bio: David Sontag is a Professor of Electrical Engineering and Computer Science at MIT, part of the Institute for Medical Engineering & Science, the Computer Science and Artificial Intelligence Laboratory, and the J-Clinic for Machine Learning in Health. His research focuses on advancing machine learning and artificial intelligence, and using these to transform health care. Previously, he was an Assistant Professor of Computer Science and Data Science at New York University.

Title: TBD

Abstract: TBD

Bio: Zachary Lipton is an Associate Professor of Machine Learning at Carnegie Mellon University (CMU). He holds appointments in the Machine Learning Department in the School of Computer Science, the Heinz School of Public Policy (courtesy) and Societal Computing (courtesy). His research spans core ML methods and theory, their applications in healthcare and natural language processing, and critical concerns, both about the mode of inquiry itself, and the impact of the technology it produces on social systems.

He is also the CTO and Chief Scientist of Abridge, a healthcare AI company defining the cutting edge of technology in the emerging ambient listening space. Their industry-leading product turns raw audio of doctor-patient conversations into high-quality drafts of after-visit documentation, freeing up doctors to focus on the patient (during the visit) and to focus mostly on last-mile edits (after the visit). Bringing this vision to life takes scientific innovation on every component of the technical stack, a commitment to focus on problem solving above aesthetic concerns, and to innovate in how to evaluate, monitor, and adapt models in light of changing patterns of usage.

Title: TBD

Abstract: TBD

Bio: Sanmi (Oluwasanmi) Koyejo is an Assistant Professor in the Department of Computer Science at Stanford University and an adjunct Associate Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign. Sanmi leads Stanford Trustworthy AI Research (STAIR), working to develop the principles and practice of trustworthy machine learning, focusing on applications to neuroscience and healthcare. Sanmi completed a Ph.D. at the University of Texas at Austin, and postdoctoral research at Stanford University. Sanmi has been the recipient of several awards, including a best paper award from the conference on uncertainty in artificial intelligence, a Skip Ellis Early Career Award, a Sloan Fellowship, a Terman faculty fellowship, an NSF CAREER award, a Kavli Fellowship, an IJCAI early career spotlight, and a trainee award from the Organization for Human Brain Mapping. Sanmi spends time at Google as a part of the Brain team, serves on the Neural Information Processing Systems Foundation Board, the Association for Health Learning and Inference Board, and as president of the Black in AI organization.

Title: TBD

Abstract: TBD

Bio: Neil Gaikwad is an Assistant Professor of Data Science and Computer Science at UNC Chapel Hill, where he also serves on the Faculty Advisory Council of the UNC Parr Center for Ethics and is a Fellow at the MIT Dalai Lama Center for Ethics and Transformative Values. Neil's research advances socially responsible design of AI systems and policy through computational approaches that align human values and ethical principles for equitable decision-making in high-stakes settings. This work has been featured in leading AI and HCI conferences as well as The New York Times, Bloomberg, WIRED, and the United Nations. Neil has been recognized with the Facebook Research Fellowship, Human Rights & Technology Fellowship, Rising Star recognition from Stanford University and the University of Chicago, and MIT's highest student honor - the Karl Taylor Compton Prize and Graduate Teaching Award. As a dedicated educator and mentor, he has guided over 30 students to publish influential papers, secure competitive fellowships, and shape AI fairness policy, while teaching at Carnegie Mellon, MIT EECS, MIT IDSS, and the MIT Media Lab. Neil holds a Ph.D. in Society-Centered AI from MIT. He is an alumnus of Carnegie Mellon University's School of Computer Science.

Title: TBD

Abstract: TBD

Bio: Bo Li is an Associate Professor in the Computer Science Department at the University of Chicago. She is on the advisory board of the Center for Artificial Intelligence Innovation (CAII) at Illinois and a member of the Information Trust Institute (ITI). She is also affiliated with several research centers aiming to broaden research collaboration and bridge different communities, such as the Advanced Digital Science Center (ADSC), the Center for Cognitive Computing Systems Research (C3SR), and the Quantum Information Science and Technology Center (IQUIST). She also serves in the Accelerated Learning and Engineering Research Training (ALERT) program. Her research focuses on trustworthy machine learning, emphasizing robustness, privacy, generalization, and their interconnections. She believes that closing today's trustworthiness gap in ML requires tackling these issues within a holistic framework driven by fundamental research focusing on each problem and their underlying interactions.

Title: TBD

Abstract: TBD

Bio: Yuyin Zhou is an Assistant Professor of Computer Science and Engineering at University of California, Santa Cruz, with research interests spanning across medical image computing, computer vision, and machine learning. Her research is centered on building transparent and trustworthy medical AI systems that can function efficiently and effectively in complex clinical environments.

Title: TBD

Abstract: TBD

Bio: Connor T, Jerzak is an Assistant Professor in the Department of Government at the University of Texas at Austin. He earned his Ph.D. in Government from Harvard University. From 2021 to 2022, he completed a postdoctoral fellowship at Linköping University in Sweden, working with the AI and Global Development Lab and serving as a Visiting Scholar at the University of Gothenburg. Since joining UT Austin in 2022, his research has spanned machine learning, economics, and political science, focusing on causal inference and quantitative methods. His work has been featured in several peer-reviewed venues. In addition, he will be teaching at Harvard University in 2024.

Title: Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data

Abstract: Foundation Models (FMs) trained on Electronic Health Records (EHRs) typically have small context windows, which prevents them from modeling full patient EHRs. We present the first systematic evaluation of the effect of context length on modeling EHR data. We find that longer context models improve predictive performance. Additionally, we measure robustness to three unique, previously underexplored properties of EHR data: (1) the prevalence of ``copy-forwarded" diagnoses which create artificial token repetition in EHR sequences; (2) the irregular time intervals between EHR events which can lead to a wide range of timespans within a context window; and (3) the natural increase in disease complexity over time which makes later tokens in the EHR harder to predict than earlier ones. Our work highlights the potential for using long-context architectures to model EHR data, and offers a case study on how to identify and quantify new challenges in modeling sequential data motivated by domains outside of natural language.

Bio: Professor Su-In Lee, the Paul G. Allen Endowed Professor of Computer Science at the University of Washington (UW), earned her PhD from Stanford University in 2009 under the guidance of Professor Daphne Koller. She joined UW in 2010 after serving as a visiting Assistant Professor at Carnegie Mellon University. Renowned for her groundbreaking work at the intersection of AI, biology, and medicine, Professor Lee has received several prestigious awards, including the Samsung Ho-Am Prize—often referred to as the "Korean Nobel Prize"— as the first woman to receive the Engineering award in its 34-year history, the International Society for Computational Biology (ISCB) Innovator Award, and the National Science Foundation (NSF) CAREER Award. She has also been honored as an ACS Research Scholar and American Institute for Medical and Biological Engineering (AIMBE) Fellow. Professor Lee is recognized as a pioneer in explainable AI (XAI) for her seminal contributions, particularly her Shapley Additive Explanations (SHAP) framework, significantly advancing the interpretability of machine learning models.

Her recent research focuses on fundamental XAI principles and techniques, as well as innovative biomedical research, spanning from basic biology to clinical medicine, which has been enabled by advancements in XAI. By fundamentally shifting how AI is integrated into biomedical research, her work addresses cutting-edge scientific questions and enables novel discoveries from high-throughput molecular data and electronic health records. This transformative integration is advancing healthcare in meaningful ways. This innovative research has resulted in highly cited publications in foundational AI, computational molecular biology, and clinical medicine.

Title: TBD

Abstract: TBD

Bio: Sarita Joshi is a Machine Learning Specialist with Google Cloud Healthcare and Life Sciences group. Sarita works with strategic customers, partners to create and execute on their healthcare transformation vision. Before joining Google Cloud, Sarita led multiple Artificial Intelligence customer transformation journeys at Amazon Web Services. She held positions including Senior Science Manager, Delivery Practice Leader for Professional Services. Sarita has several years of experience as a consultant advising clients across many industries and technical domains, including AI, ML, analytics, and SAP. She primarily held positions in Product engineering, R&D, technical consulting and business development organizations including Amazon, Accenture, Philips HealthCare, Tata Consulting, Nordstrom. She earned a master's degree in Computer Science, Specialty Data from Northeastern University and a bachelor's degree from Mumbai University.

Title: TBD

Abstract: TBD

Bio: He is a Senior AI/ML Engineer at Google, specializing in healthcare and life sciences innovation. With expertise in computational biology and foundation models, he helps organizations transform patient care through generative AI and ML solutions. His background spans bioengineering, machine learning, and clinical research, supported by engineering degrees from Stanford and Johns Hopkins. He is dedicated to developing responsible AI solutions that enhance healthcare accessibility and outcomes for diverse communities.