BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Hi! PARIS - ECPv6.18.4//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://hi-paris.fr
X-WR-CALDESC:Events for Hi! PARIS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20270328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20271031T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20280326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20281029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20261130T110000
DTEND;TZID=Europe/Paris:20261130T120000
DTSTAMP:20261013T102249Z
CREATED:20261013T102249Z
LAST-MODIFIED:20261013T102249Z
UID:10000042-1796036400-1796040000@hi-paris.fr
SUMMARY:AI Seminar Cycle: When Generators Condition on Themselves - Exposure Bias in Visual Autoregressive Models
DESCRIPTION:Autoregressive models have emerged as a powerful alternative to diffusion for image and video generation\, making them a natural fit for streaming and interactive video world models. However\, because they generate content step by step and condition on their own previous outputs\, they remain vulnerable to exposure bias—where early errors propagate and shape the entire generation process. \nIn this talk\, Angela Yao (Associate Professor at the National University of Singapore) presents recent research from her group on mitigating exposure bias across the generation pipeline. The session covers key advances\, including tokenizer and generator regularization\, pixel-level quality alignment post-training\, training-free guidance to reinforce historical consistency\, and reinforcement learning strategies designed to maintain long-horizon stability in video world models.
URL:https://hi-paris.fr/event/ai-seminar-cycle-when-generators-condition-on-themselves-exposure-bias-in-visual-autoregressive-models/
CATEGORIES:Innovation,Research
ORGANIZER;CN="Hi! PARIS":MAILTO:contact@hi-paris.fr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20261203T140000
DTEND;TZID=Europe/Paris:20261203T153000
DTSTAMP:20261112T105257Z
CREATED:20261112T105257Z
LAST-MODIFIED:20261112T105257Z
UID:10000044-1796306400-1796311800@hi-paris.fr
SUMMARY:Hi! PARIS Reading groups “Fairness in AI” – Session 2
DESCRIPTION:This session investigates the theoretical foundations of fair regression constrained by demographic parity within the unawareness framework—where explicit disparate treatment is disallowed. Expanding on existing models that permit such treatment\, the talk addresses how to characterize optimal fair regression functions when minimizing quadratic loss\, demonstrating how the solution maps to a barycenter problem with optimal transport costs. \nFurthermore\, the session examines the interplay between optimal fair cost-sensitive classification and fair regression. It shows that nestedness among classifier decision sets is both necessary and sufficient for equivalence between the two\, allowing optimal classifiers to be thresholded directly from the fair regression function (and vice versa). \nPaper: https://jmlr.org/beta/papers/v27/24-1338.html \nRegister here!
URL:https://hi-paris.fr/event/hi-paris-reading-groups-fairness-in-ai-session-2/
CATEGORIES:Research
ORGANIZER;CN="Hi! PARIS":MAILTO:contact@hi-paris.fr
LOCATION:https://us02web.zoom.us/meeting/register/7RpXASOnTGWkKAeo8CCtfA#/registration
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20270414T110000
DTEND;TZID=Europe/Paris:20270414T120000
DTSTAMP:20261006T092408Z
CREATED:20261006T092408Z
LAST-MODIFIED:20261006T092408Z
UID:10000040-1807700400-1807704000@hi-paris.fr
SUMMARY:AI Seminar Cycle: Nuria Oliver (ELLIS Alicante)
DESCRIPTION:Join us for a session of the 2026–2027 Hi! PARIS × ELLIS AI Seminar Cycle\, featuring Nuria Oliver (ELLIS Alicante). \nNuria’s research areas include human-centered AI\, trustworthy AI\, and explainable AI. \nTalk title and abstract coming soon. \nRegister Now !
URL:https://hi-paris.fr/event/ai-seminar-cycle-nuria-oliver-ellis-alicante/
CATEGORIES:Research
ORGANIZER;CN="Hi! PARIS":MAILTO:contact@hi-paris.fr
END:VEVENT
END:VCALENDAR