
Hi all, I am happy to announce that the first AI seminar of this term will be by Prof. Xiao Fu at 2 pm on Friday 9/27 in KEC 1001. The seminars are public, but are also available for credit to in-person attendees by registering for AI 507. Please follow https://engineering.oregonstate.edu/EECS/research/AI-seminars<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fengineering.oregonstate.edu%2FEECS%2Fresearch%2FAI-seminars&data=05%7C02%7Cai%40engr.oregonstate.edu%7Cbd54ca460df646cdcb6508dcdc306625%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638627347640475170%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=pBMyMoHER3xcHrFodiRukf6Z%2B1HQHs5wqB3UTrMXegY%3D&reserved=0> for future seminar announcements. See you on Friday. Best, Prasad Tadepalli Towards Provable Unaligned Multimodal Learning: A Model Identification Perspective Xiao Fu, Oregon State University 2 PM, Friday 9/27, KEC 1001 and zoom<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Foregonstate.zoom.us%2Fj%2F98357211915&data=05%7C02%7Cai%40engr.oregonstate.edu%7Cbd54ca460df646cdcb6508dcdc306625%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638627347640475170%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=qoUiKtYSx196AIFRW%2FZL3B%2FCcNp6paOS3mVPNYrIfCc%3D&reserved=0> Abstract: 2023 was "the year of AI", highlighted by the release of numerous AI models with remarkable capabilities. Multimodal learning is at the forefront of AI advancements, with state-of-the-art models like GPT-4 and Gemini emphasizing multimodal functionalities as their defining features. Despite its importance, many aspects of multimodal learning, and AI developments in general, still lack a concrete and comprehensive understanding---which is essential for building resilient and trustworthy systems. Our research focuses on the understanding of AI/ML systems to drive theory-backed advancements. From this perspective, this presentation revisits a core component of multimodal learning-Unsupervised Domain Translation (UDT). Many UDT systems, such as CycleGAN, use Distribution Matching (DM) modules, which often fail in content-aligned translations due to measure-preserving automorphism (MPA). Existing remedies fall short of guaranteed performance. In my talk, I will introduce a model identification perspective for UDT, overcoming the MPA issues and ensuring identifiability of the desired translation functions. This is the first proven identification result in UDT under CycleGAN's settings, to our knowledge. We have also broadened these concepts, providing solutions for various translation challenges, enabling provable content-style disentanglement, and offering more versatile cross-domain data generation. These advancements promise significant theoretically supported enhancements for UDT applications, particularly in annotation-limited fields such as medicine and biology. Speaker Biography Xiao Fu<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fengineering.oregonstate.edu%2Fpeople%2Fxiao-fu&data=05%7C02%7Cai%40engr.oregonstate.edu%7Cbd54ca460df646cdcb6508dcdc306625%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638627347640475170%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=G5vJybpOzBxum5RfmTnZ%2BQobViST%2F%2F%2FqNfOjVP7PPJA%3D&reserved=0> has been with the School of Electrical Engineering and Computer Science, Oregon State University since 2017, where he is currently an Associate Professor. He received the Ph.D. degree in Electronic Engineering from The Chinese University of Hong Kong, in 2014. He was a Postdoctoral Associate with the Department of Electrical and Computer Engineering, University of Minnesota - Twin Cities, from 2014 to 2017. His research interests include the broad area of machine learning and signal processing, especially theory and algorithms. Dr. Fu received the Best Student Paper Award at ICASSP 2014, the 2022 IEEE Signal Processing Society (SPS) Best Paper Award, and the 2022 IEEE SPS Donald G. Fink Overview Paper Award. He also received the Outstanding Postdoctoral Scholar Award at University of Minnesota in 2016, the Engelbrecht Early Career Faculty Award from the College of Engineering at Oregon State University in 2023, and the National Science Foundation (NSF) CAREER Award in 2022.

Hi all, In lieu of the AI Seminar, we are going to have a 'fireside chat' with our alumnus Robin Abraham, who has been inducted into the Academy of Distinguished Engineers at OSU, about his career at Microsoft and his current work in AI. Please join us in KEC 1001 on Friday at 2 pm. This meeting will be in-person only. Thanks, Prasad Speaker Biography After receiving his undergraduate degree in aerospace engineering from the Indian Institute of Technology in Kharagpur, India, Robin Abraham obtained his Ph.D. in computer science at Oregon State University in 2007. He is currently Partner General Manager of Research in Science and Strategy at Microsoft. During his 17 years with Microsoft, Abraham has developed and shepherded some of the company's most innovative and future-oriented products and services. Early on, he led efforts that boosted the installation success rate of Windows updates to 99% for an ecosystem that included more than 1 billion machines. He was also instrumental in the development of PowerApps, which allows businesses to quickly and efficiently create custom apps that support their goals. PowerApps now generates more than $2 billion in annual revenue. And he served as the principal architect for Microsoft's Ambient Computing and Robotics project, which leveraged the power of artificial intelligence for workplace safety. Abraham is particularly proud of his current assignment: leading Science Engine, one of Microsoft's most dynamic endeavors. Science Engine harnesses advances in AI and high-performance computing to transform research and development processes in industries that are anchored in hard science, including pharmaceutical development, disease modeling, material design, energy production, chemicals, manufacturing, carbon storage, and more. Web link: https://engineering.oregonstate.edu/events/fireside-chat-oregon-stater-awardee<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fengineering.oregonstate.edu%2Fevents%2Ffireside-chat-oregon-stater-awardee&data=05%7C02%7Cai%40engr.oregonstate.edu%7C159439479fc849a28e6c08dce2348b26%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638633962495248695%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=Rj4UJmXMOUiSbKOar4FZfzGscJixzXoFkQMRC0os690%3D&reserved=0>

Hi all, Please join us for a 'fireside chat' with our alumnus Robin Abraham, who has been inducted into the Academy of Distinguished Engineers at OSU, about his career at Microsoft and his current work in AI. This meeting is at 2 pm on Friday in KEC 1001 and will be in-person only. Thanks, Prasad Speaker Biography After receiving his undergraduate degree in aerospace engineering from the Indian Institute of Technology in Kharagpur, India, Robin Abraham obtained his Ph.D. in computer science at Oregon State University in 2007. He is currently Partner General Manager of Research in Science and Strategy at Microsoft. During his 17 years with Microsoft, Abraham has developed and shepherded some of the company's most innovative and future-oriented products and services. Early on, he led efforts that boosted the installation success rate of Windows updates to 99% for an ecosystem that included more than 1 billion machines. He was also instrumental in the development of PowerApps, which allows businesses to quickly and efficiently create custom apps that support their goals. PowerApps now generates more than $2 billion in annual revenue. And he served as the principal architect for Microsoft's Ambient Computing and Robotics project, which leveraged the power of artificial intelligence for workplace safety. Abraham is particularly proud of his current assignment: leading Science Engine, one of Microsoft's most dynamic endeavors. Science Engine harnesses advances in AI and high-performance computing to transform research and development processes in industries that are anchored in hard science, including pharmaceutical development, disease modeling, material design, energy production, chemicals, manufacturing, carbon storage, and more. Web link: https://engineering.oregonstate.edu/events/fireside-chat-oregon-stater-awardee<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fengineering.oregonstate.edu%2Fevents%2Ffireside-chat-oregon-stater-awardee&data=05%7C02%7Cai%40engr.oregonstate.edu%7C2f6213feb9954569e49a08dce3d8b79e%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638635767149792266%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=btTRpXpWWUMjsLo12LM%2FpccK%2FWFpC9Mi41%2BYCyHV884%3D&reserved=0>
participants (1)
-
Tadepalli, Prasad