BEGIN:VCALENDAR
PRODID:-//planitpurple.northwestern.edu//iCalendar Event//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
CLASS:PUBLIC
BEGIN:VTIMEZONE
TZID:America/Chicago
TZURL:http://tzurl.org/zoneinfo-outlook/America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:0
DTSTART;TZID=America/Chicago:20261113T110000
DTEND;TZID=America/Chicago:20261113T120000
DTSTAMP:20261017T110529Z
SUMMARY:Statistics and Data Science Seminar Series: "Counterfactual JEPAs for World Models in the Real World"
UID:647674@northwestern.edu
TZID:America/Chicago
DESCRIPTION:Counterfactual JEPAs for World Models in the Real World  Randall Balestriero\, Assistant Professor of Computer Science\, Brown University; researcher at AMI Labs  Abstract: This talk presents a sequence of recent results on Joint-Embedding Predictive Architectures (JEPAs)\, spanning self-supervised representation learning\, action-conditioned world models\, and counterfactual reasoning. We begin with LeJEPA\, which addresses representation collapse through a distributional principle: embeddings are regularized toward an isotropic Gaussian using Sketched Isotropic Gaussian Regularization\, producing a simple predictive objective with theoretical guarantees and without teacher–student networks or stop-gradient heuristics. We then introduce LeWorldModel\, which extends this construction to sequential data by learning an encoder and action-conditioned latent transition model\, (z_{t+1} \approx f_\theta(z_t\,a_t))\, end-to-end from raw observations. By combining next-embedding prediction with Gaussian latent regularization\, the model supports planning and control directly in representation space\, without reconstructing future pixels. Finally\, we discuss new directions in counterfactual JEPAs\, where object-level masking and latent interventions create structured partial-observability problems that force the predictor to model interaction-dependent dynamics rather than exploit local correlations. Throughout\, we emphasize the geometric and statistical principles connecting these methods\, and ask when latent prediction is sufficient for learning causal\, controllable abstractions of a dynamical world.   \n\nMore Info: https://statistics.northwestern.edu/events/seminars/fall-seminars.html
LOCATION:Chambers Hall\, Ruan Conference Room – lower level\, 600 Foster St\, Evanston\, IL 60208
TRANSP:OPAQUE
URL:https://statistics.northwestern.edu/events/seminars/fall-seminars.html
CREATED:20220914T050000Z
STATUS:CONFIRMED
LAST-MODIFIED:20261014T171659Z
PRIORITY:0
BEGIN:VALARM
TRIGGER:-PT10M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
END:VEVENT
END:VCALENDAR