# Event Details - **Event Name**: ML/AI Seminar: Stephen Tu, University of Southern California - **Event Start and End Date**: Fri, 30 Oct, 2026 at 11:00 am – Fri, 30 Oct, 2026 at 12:00 pm (-04:00) - **Event Description**: Hosted by DSI Foundations Center; Department of Statistics, Columbia University; Columbia EngineeringAbout this EventREGISTRATION DEADLINE: The Columbia Morningside campus is open to the Columbia community. If you do not have an active CUID, the deadline to register is at 12:00 PM the day before the event. External guests will receive a QR code by email to enter campus.____________SpeakerStephen Tu, is an assistant professor in the Department of Electrical and Computer Engineering at the University of Southern California. His research interests span statistical learning theory, safe and optimal control, and generative modeling. Specifically, his work focuses on non-asymptotic guarantees for learning dynamical systems, rigorous analysis of distribution shift in feedback settings, safe control synthesis, and more recently foundations of generative modeling. Stephen earned his Ph.D. in Electrical Engineering and Computer Sciences (EECS) from the University of California, Berkeley. Previous to joining USC, Stephen was a research scientist at Google DeepMind Robotics where he focused on combining learning and control-theoretic approaches for robotics.____________AbstractMultistep Backwards Latent Losses Learn Unstable Linear DynamicsModel-based control synthesis relies on an accurate description of the system dynamics and the environment. When such models are unavailable or difficult to derive from first principles, they must be learned from system trajectories. Latent world models have recently emerged as a promising general-purpose approach, learning low-dimensional representations together with dynamics that evolve these representations to predict future behavior. However, it remains unclear which dynamical properties these models preserve, and whether they support control synthesis with guarantees of closed-loop stability and safety. Resolving these questions is essential to establishing latent world modeling as a reliable tool for control design. In this talk, we initiate a study of the dynamical properties captured by latent world model designs. For trajectory data generated by a linear dynamical system, we show that multi-step backward latent reconstruction losses recover the system’s unstable subspace, provided the latent dimension is large enough to represent the unstable modes. We then show that an H-infinity controller synthesized using the learned latent dynamics stabilizes the original system. Crucially, both multi-step prediction and reconstruction in the original space (i.e., backward reconstruction) are necessary for this guarantee: removing either can lead to an unstable closed-loop system. Although our analysis focuses on linear systems, experiments on high-dimensional nonlinear systems reveal behavior consistent with our theoretical findings. - **Event URL**: https://allevents.in/new-york/ml-ai-seminar-stephen-tu-university-of-southern-california/100001999106806272 - **Event Categories**: workshops, science-fair - **Interested Audience**: - total_interested_count: 0 - **Event Highlights**: - Doors Open At: 10:45 AM - Duration: 1 hour - Location: School of Social Work - Room 903 - Languages: English ## Ticket Details - **Ticket Price Range**: min: 0, max: 0, currency: USD ## Event venue details - **city**: New York - **state**: NY - **country**: United States - **location**: School of Social Work - Room 903 - **lat**: 40.8102222 - **long**: -73.9581853 - **full address**: School of Social Work - Room 903, 1255 Amsterdam Avenue, New York, United States ## Event gallery - **Alt text**: ML/AI Seminar: Stephen Tu, University of Southern California - **Image URL**: https://cdn-az.allevents.in/events10/banners/da78e2936a06e3c98c98fb71067ca87b7f681cf8224adcfb2f9a6e586e22a308-rimg-w1200-h594-dce8f8f8-gmir.jpg?v=1789555593 ## FAQs - **Q**: When and where is ML/AI Seminar: Stephen Tu, University of Southern California being held? - **A:** ML/AI Seminar: Stephen Tu, University of Southern California takes place on Fri, 30 Oct, 2026 at 11:00 am to Fri, 30 Oct, 2026 at 12:00 pm at School of Social Work - Room 903, 1255 Amsterdam Avenue, New York, United States. - **Q**: Who is organizing ML/AI Seminar: Stephen Tu, University of Southern California? - **A:** ML/AI Seminar: Stephen Tu, University of Southern California is organized by Data Science Institute, Columbia University. - **Q**: Who is this event for? Is it right for me? - **A:** ML/AI Seminar: Stephen Tu, University of Southern California is ideal for curious learners, students, and skill-builders looking to gain hands-on knowledge and practical expertise in a focused, interactive setting. Whether you're a first-time attendee or a longtime enthusiast in New York, this event is thoughtfully curated to deliver a standout experience worth every moment. If ML/AI Seminar: Stephen Tu, University of Southern California sounds like your kind of event, don't wait - spots fill up fast. ## Structured Data (JSON-LD) ```json [ { "@context": "https://schema.org", "@type": "Event", "name": "ML/AI Seminar: Stephen Tu, University of Southern California", "image": "https://cdn-az.allevents.in/events10/banners/da78e2936a06e3c98c98fb71067ca87b7f681cf8224adcfb2f9a6e586e22a308-rimg-w1200-h594-dce8f8f8-gmir.jpg?v=1789555593", "startDate": "2026-10-30T11:00:00-04:00", "endDate": "2026-10-30T12:00:00-04:00", "url": "https://allevents.in/new-york/ml-ai-seminar-stephen-tu-university-of-southern-california/100001999106806272", "eventStatus": "https://schema.org/EventScheduled", "location": { "@type": "Place", "name": "School of Social Work - Room 903", "address": { "@type": "PostalAddress", "streetAddress": "1255 Amsterdam Avenue", "postalCode": "10027", "addressLocality": "New York", "addressRegion": "NY", "addressCountry": "US" }, "geo": { "@type": "GeoCoordinates", "latitude": "40.8102222", "longitude": "-73.9581853" } }, "eventAttendanceMode": "https://schema.org/OfflineEventAttendanceMode", "description": "Hosted by DSI Foundations Center; Department of Statistics, Columbia University; Columbia Engineering", "offers": [ { "@type": "AggregateOffer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-09-16", "availabilityEnds": "2026-10-30T12:00:00-04:00", "validFrom": "2026-09-16", "lowPrice": "0.00", "highPrice": "0.00", "price": "0.00", "url": "https://allevents.in/new-york/ml-ai-seminar-stephen-tu-university-of-southern-california/100001999106806272" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-09-16", "availabilityEnds": "", "validFrom": "2026-09-16", "url": "https://allevents.in/new-york/ml-ai-seminar-stephen-tu-university-of-southern-california/100001999106806272", "price": 0, "name": "Columbia University Community" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-09-16", "availabilityEnds": "", "validFrom": "2026-09-16", "url": "https://allevents.in/new-york/ml-ai-seminar-stephen-tu-university-of-southern-california/100001999106806272", "price": 0, "name": "Columbia University Alumni" }, { "@type": "Offer", "availability": "https://schema.org/InStock", "priceCurrency": "USD", "availabilityStarts": "2026-09-16", "availabilityEnds": "", "validFrom": "2026-09-16", "url": "https://allevents.in/new-york/ml-ai-seminar-stephen-tu-university-of-southern-california/100001999106806272", "price": 0, "name": "General Admission" } ], "organizer": [ { "@type": "Organization", "name": "Data Science Institute Columbia University", "url": "https://allevents.in/org/data-science-institute-columbia-university/17754885" } ] } ] ```