BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//MediaFutures - ECPv6.15.13.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:MediaFutures
X-ORIGINAL-URL:https://mediafutures.no
X-WR-CALDESC:Events for MediaFutures
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Oslo
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
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20260912T111000
DTEND;TZID=Europe/Oslo:20260912T121000
DTSTAMP:20260813T231034
CREATED:20260811T093805Z
LAST-MODIFIED:20260813T080846Z
UID:23212-1789211400-1789215000@mediafutures.no
SUMMARY:PYData Seminar: Stop Early\, Decide Smarter: Bayesian Sequential Testing for LLM Benchmarking
DESCRIPTION:Ryan Marinelli will be holding a tutorial at PyData\, Amsterdam. \nEvaluating large language models is expensive. Standard benchmarking practices run fixed numbers of trials regardless of how quickly signal emerges\, wasting compute when differences are obvious and under-sampling when they are subtle. \nThis talk introduces Bayesian sequential stopping rules as a principled alternative. Rather than committing to a sample size upfront\, sequential methods continuously update a posterior over model performance and halt evaluation once sufficient evidence has accumulated\, or once further sampling is unlikely to change the conclusion. \nWe walk through the statistical foundations\, show how this framework applies to common benchmarking scenarios (accuracy comparisons\, pass@k\, agent task completion)\, and demonstrate a practical open-source Python implementation attendees can use immediately. Real benchmark datasets are used throughout to ground the approach. \nAudience: ML engineers\, researchers\, and data scientists who run model evaluations and care about making reliable comparisons without burning unnecessary compute. \nTakeaways: A conceptual understanding of sequential testing\, practical guidance on when and how to apply it\, and a working tool to take home. \nFixed-sample benchmarking is the default in NLP and LLM evaluation\, but it has two failure modes: it over-runs when models are clearly different early on\, and under-runs when tight comparisons require more evidence than the budget allows. Sequential hypothesis testing\, long standard in clinical trials and A/B testing\, offers a cleaner framework: keep sampling until a decision threshold is crossed\, or until a maximum budget is exhausted. \nThis talk applies that framework specifically to LLM and agent benchmarking and covers: \n\nThe statistical case: Why pass@k evaluation is often wasteful\, and what sequential Bayes factors and posterior stopping criteria offer instead\nDesign choices: Prior elicitation\, stopping thresholds\, and how to handle multi-model comparisons without inflating error rates\nPractical implementation: A walkthrough of a pip-installable Python package built on this framework\nLimitations and scope: When sequential testing helps\, when it doesn’t\, and how to sanity-check results\n\nThe talk is self-contained; attendees need only basic familiarity with probability and Python. \nOutline (30 min):\nMotivation: the cost of fixed-N benchmarking — 5 min\nSequential testing foundations (Bayes factors\, stopping rules) — 8 min\nDemo: the Python package on real benchmark data — 10 min\nDesign guidance\, edge cases\, and Q&A — 7 min
URL:https://mediafutures.no/event/pydata-seminar-stop-early-decide-smarter-bayesian-sequential-testing-for-llm-benchmarking/
LOCATION:NDSM-Plein 85 1033 WC Amsterdam\, NDSM-Plein 85 1033 WC Amsterdam\, Netherlands
CATEGORIES:Events
ATTACH;FMTTYPE=image/png:https://mediafutures.no/wp-content/uploads/Screenshot-2026-08-07-at-15.54.34.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20261105T130000
DTEND;TZID=Europe/Oslo:20261106T180000
DTSTAMP:20260813T231034
CREATED:20260710T123111Z
LAST-MODIFIED:20260804T130953Z
UID:23101-1793883600-1793988000@mediafutures.no
SUMMARY:Annual Meeting 26: Our public flagship conference
DESCRIPTION:Keep the date in your calendars! We are underway in planning the Annual Meeting for 2026! Please see the preliminary schedule below\, final program will be confirmed closer to the date.  \nThursday\, 5 November – Venue: Media City\n\n\n\n\nTime \n\n\nProgram \n\n\nDetails \n\n\n\n\n\n\n13:00–13:15 \n\n\nWelcome & framing \n\n\nChristopher Senf (MediaFutures) with Media Cluster Norway. Aims for the afternoon. \n\n\n\n\n13:15–14:00 \n\n\nSession A — Liquid content & journalism-as-a-service \n\n\nPaired industry + research talks (e.g. Schibsted / TV 2 with an Audience Understanding & Personalisation talk). \n\n\n\n\n14:00–14:30 \n\n\nTable discussion & project ideation \n\n\nFacilitated groups; capture concrete collaboration ideas. \n\n\n\n\n14:30–14:50 \n\n\nCoffee break \n\n\n  \n\n\n\n\n14:50–15:35 \n\n\nSession B — Young audiences\, trust & AI transparency \n\n\nPaired talks (e.g. Amedia / Bergens Tidende with a Curated Information Frameworks talk). \n\n\n\n\n15:35–16:00 \n\n\nTable discussion \n\n\nPriorities and open questions per group. \n\n\n\n\n16:00–16:15 \n\n\nCoffee break \n\n\n  \n\n\n\n\n16:15–16:55 \n\n\nSession C — Verification\, fact-checking & content moderation \n\n\nPaired talks (e.g. Faktisk.no / Factiverse with a moderation-research talk). \n\n\n\n\n16:55–17:30 \n\n\nWrap-up: shared priorities & next steps \n\n\nSynthesis of table outputs; commitments and follow-ups. \n\n\n\n\n19:30 \n\n\nConference Dinner \n\n\nROAST\, Scandic Ørnen  (separate registration) \n\n\n\n\nFriday\, 6 November – Venue: Scandic Ørnen\n\n\n\n\n08:15–09:00 \n\n\nRegistration & morning coffee \n\n\n  \n\n\n\n\n09:00–09:15 \n\n\nWelcome & opening \n\n\nChristoph Trattner — Director\, SFI MediaFutures \n\n\n\n\n09:15–09:55 \n\n\nKeynote 1 + Q&A \n\n\nProf. Claes de Vreese (University of Amsterdam) — AI\, public trust and the future of democracy  confirmed \n\n\n\n\n09:55–10:35 \n\n\nKeynote 2 + Q&A \n\n\nEzra Eeman (Director of Strategy & Innovation\, NPO) — AI and the transformation of media business models  confirmed \n\n\n\n\n10:35–11:00 \n\n\nCoffee break \n\n\n  \n\n\n\n\n11:00–12:00 \n\n\nSession 1 — AI & the Newsroom3 talks (15 min each) + joint Q&A \n\n\n• JC Lopez (Schibsted News Media) — AI & liquid news  confirmed• France TV — Skander Ben Attia (CTO) / director-level  confirmed• Prof. Johanna Pirker (TU Munich) — AI\, VR\, HCI & gamification  confirmed \n\n\n\n\n12:00–13:00 \n\n\nLunch \n\n\n  \n\n\n\n\n13:00–14:00 \n\n\nSession 2 — AI\, Verification & Trust3 talks (15 min each) + joint Q&A \n\n\n• Prof. Andreas Vlachos (Cambridge) — ML & automated fact-checking  confirmed• Maria Amelie (Factiverse)  TBC• BBC Verify —Kayleen Devlin  confirmed \n\n\n\n\n14:00–14:20 \n\n\nCoffee break \n\n\n  \n\n\n\n\n14:20–15:20 \n\n\nSession 3 — AI Safety & Democratic Impact3 talks (15 min each) + joint Q&A \n\n\n• Stuart Jennings (AI Security Institute; prev. BBC)  confirmed• Florent Daudens (Mizal AI; prev. Hugging Face)  TBC • Talk 3 — open slot; suggested: Sam Gregory (WITNESS) — provenance & synthetic-media authenticity  open slot — see notes \n\n\n\n\n15:20–15:40 \n\n\nCoffee break \n\n\n  \n\n\n\n\n15:40–16:40 \n\n\nPanel — Nordic News Media AICompany pitches + moderated debate \n\n\n15:40 — Company pitches (MediaFutures industry partners)  partners TBD16:00 — Moderated debateModerator TBC \n\n\n\n\n16:40–16:55 \n\n\nRefreshment break \n\n\n  \n\n\n\n\n16:55–17:40 \n\n\nDemo & Poster Session \n\n\n16:55 — Live demos · 17:15 — Poster pitches (lightning) \n\n\n\n\n17:40–18:15 \n\n\nNetworking reception \n\n\nDrinks; posters and demos remain open. \n\n\n\n\n18:15–18:30 \n\n\nPoster Awards & closing \n\n\nChristoph Trattner \n\n\n\n\n18:30 \n\n\nEnd of conference program \n\n\n  \n\n\n\n\n 
URL:https://mediafutures.no/event/annual-meeting-26-our-public-flagship-conference/
LOCATION:Scandic Ørnen\, Bergen
CATEGORIES:Events
ATTACH;FMTTYPE=image/png:https://mediafutures.no/wp-content/uploads/ChatGPT-Image-Jun-30-2026-11_17_33-AM.png
END:VEVENT
END:VCALENDAR