BEGIN:VCALENDAR VERSION:2.0 PRODID:-//elias-ai - ECPv6.15.17.1//NONSGML v1.0//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-WR-CALNAME:elias-ai X-ORIGINAL-URL:https://elias-ai.eu X-WR-CALDESC:Events for elias-ai REFRESH-INTERVAL;VALUE=DURATION:PT1H X-Robots-Tag:noindex X-PUBLISHED-TTL:PT1H BEGIN:VTIMEZONE TZID:Europe/Rome BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20230326T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20231029T010000 END:STANDARD BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20240331T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20241027T010000 END:STANDARD BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20250330T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20251026T010000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTART;VALUE=DATE:20240117 DTEND;VALUE=DATE:20240120 DTSTAMP:20260419T220708 CREATED:20240110T144009Z LAST-MODIFIED:20240904T180529Z UID:1520-1705449600-1705708799@elias-ai.eu SUMMARY:ELLIS Multimodal Learning Systems Workshop on Multimodal Foundation Models DESCRIPTION:Theme\n \n \n \n \n \n Multimodal foundation models are a revolutionary class of AI models that provides impressive abilities to generate content (text\, images\, sound\, videos\, protein structures\, and more)\, and do so by interactive prompts in a seemingly creative manner. These foundation models are often autoregressive\, self-supervised\, transformer-based models that are pre-trained on large volumes of data\, typically collected from the web. They already form the basis of all state-of-the-art systems in computer vision and natural language processing across a wide range of tasks and have shown impressive few-shot learning abilities. The perceived intelligence and adaptability of models like ChatGPT\, Stable Diffusion\, Gemini\, and GPT4 impress\, but their aptitude to produce inaccurate\, misleading\, or false information (and present it confidently and convincingly) makes them unsuitable for any task of importance and poses serious societal concerns. In this workshop we present recent advances on multimodal foundation models from academia and industry and discuss their impact and implications moving forward. \n \n \n \n \n \n Location\n \n \n \n \n \n The workshop is hosted at the Mathematisches Forschungsinstitut Oberwolfach (MFO). Accommodation and meals will take place in Hotel Hirschen\, which is within walking distance of the MFO. \n \n \n \n \n \n The workshop is hosted at the Mathematisches Forschungsinstitut Oberwolfach (MFO). Accommodation and meals will take place in Hotel Hirschen\, which is within walking distance of the MFO. \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n \n \n Event Programme\n \n \n\n\n \n Programme\n \n Wednesday January 17\n \n \n 15:00 - 19:00\n Arrival of attendees\, time for socializing and discussion\n \n \n 19:00 - 22:00\n Opening dinner at Hotel Hirschen\n \n \n \n Thursday January 18\n \n \n 08:00 - 09:30\n Breakfast at Hotel Hirschen\n \n \n 09:30 - 11:00\n \n Morning Session I: Foundation Models (Chair: Yiannis Kompatsiaris)\n FoMO without FOMO by Karteek Alahari (Inria)\n Towards 3D Human Foundation Models by Cristian Sminchisescu (Google)\n What multimodal foundation models cannot perceive by Cees Snoek (University of Amsterdam)\n Are Foundation Models the tool for Social Embodied AI? by Xavier Alameda-Pineda (Inria)\n \n \n \n 11:00 - 11:30\n Coffee break\n \n \n 11:30 - 12:30\n \n Morning Session II: Vision & Language (Chair: Dima Damen)\n Vocabulary-free Image Classification by Elisa Ricci (University of Trento)\n Coreference resolution in narrated images by Hakan Bilen (The University of Edinburgh)\n Vision-Language Self-Supervised Learning by Shaogang Gong (Queen Mary\, University of London)\n \n \n \n 12:30 - 14:00\n Lunch break at Hotel Hirschen\n \n \n 14:00 - 15:30\n \n Afternoon Session I: Generative AI (Chair: Karteek Alahari)\n Images & text: alignment\, generation and compression by Jakob Verbeek (Meta)\n Measuring the Quality of Generative Neural Networks - An Unsolved Problem by Juergen Gall (University of Bonn)\n Controllable generation for Analysis and Synthesis by Ioannis Patras (Queen Mary\, University of London)\n Improving Fairness using Vision-Language Driven Image Augmentation by Nicu Sebe (University of Trento)\n \n \n \n 15:30 - 16:00\n Coffee break\n \n \n 16:00 - 17:00\n \n Afternoon Session II: Multimodality (Chair: Xavier Alameda-Pineda)\n Multi-modality in Egocentric Vision - Contradictory and complementary signals by Dima Damen (University of Bristol)\n Multimodal LLMs for Document Understanding by Dimosthenis Karatzas (Universitat Autónoma de Barcelona)\n Large Multimodal Models for Media and Journalism by Yiannis Kompatsiaris (Information Technologies Institute\, CERTH)\n \n \n \n 17:00 - 18:30\n Discussion Session (Chairs: Cees Snoek & Nicu Sebe)\n \n \n 19:00 - 22:00\n Dinner at Hotel Hirschen\n \n \n \n Friday January 19\n \n \n 08:00 - 10:00\n Breakfast at Hotel Hirschen\n \n \n 10:00 onwards\n Departure\n \n \n \n\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n \n \n \n Event Footer\n \n\n\n\n\n\n \n \n Details\n Start: January 17 \n End: January 19 \n Event Category: Workshops \n \n \n Add to Calendar\n \n \n Website\n Multimodal FoMO Workshop \n Organiser\n ELLIS\, ELISE & ELIAS \n \n \n Venue\n Location: Mathematisches Forschungsinstitut Oberwolfach (MFO) \n Schwarzwaldstraße 9-11\, Oberwolfach-Walke\, 77709 Germany \n Phone: +49 (0) 7834 979-0 \n View Venue Website \n \n \n \n \n \n \n \n\n \n © 2024 ELLIS\, ELISE & ELIAS. All rights reserved. URL:https://elias-ai.eu/event/workshop-on-multimodal-foundation-models/ LOCATION:Mathematisches Forschungsinstitut Oberwolfach (MFO)\, Schwarzwaldstraße 9-11\, Oberwolfach-Walke\, 77709\, Germany CATEGORIES:Workshops ATTACH;FMTTYPE=image/png:https://elias-ai.eu/wp-content/uploads/2024/01/8-1.png END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Rome:20240116T170000 DTEND;TZID=Europe/Rome:20240116T180000 DTSTAMP:20260419T220708 CREATED:20240108T130849Z LAST-MODIFIED:20240904T163744Z UID:1452-1705424400-1705428000@elias-ai.eu SUMMARY:AI Excellence Lecture on Hybrid & Causal Machine learning in the Earth sciences DESCRIPTION:Abstract: Most problems in Earth sciences aim to do inferences about the system\, where accurate predictions are just a tiny part of the whole problem. Inferences mean understanding variables relations\, deriving models that are physically plausible\, that are simple parsimonious\, and mathematically tractable. While machine learning models excel as approximators\, they often disregard fundamental physics laws\, compromising consistency and confidence. To address these challenges\, we propose exploring the interplay between domain knowledge and machine learning. Physics-aware and hybrid machine learning models are seen as necessary steps toward understanding the data-generating process\, with causality offering significant advancements. I will discuss recent hybrid and causal machine learning methodologies to attain consistent and explainable results. This work outlines a collective\, long-term AI agenda for developing algorithms that can discover knowledge in the Earth system. \nLecturer: Professor Gustau Camps-Valls is a Full Professor in Electrical Engineering at the Universitat de Valencia. He is an expert in machine learning  algorithms for geosciences and remote sensing data analysis\, having published extensively. He has a Ph.D. in Physics and is an IEEE Distinguished Lecturer. He has received two European Research Council (ERC) grants and holds a Hirsch’s index h=88 (Google Scholar). He is also a Highly Cited Researcher since 2020. Gustau has achieved significant recognition with numerous awards and honors\, including IEEE Fellow (2018)\, ELLIS Fellow (2019)\, Fellow of the European Academy of Sciences (EurASc)\, the Academia Europeae (AE)\, and the Asia-Pacific Artificial Intelligence Association (AAIA) all in 2021. \nAbout AIDA: The four ICT-48 networks (AI4Media\, ELISE\, HumanE-AI NET\, TAILOR) and the VISION project joined forces and\, under the joint initiative of VISION and AI4Media\, founded a new joint instrument to support a world-level AI education and research programme. \nThe International AI Doctoral Academy (AIDA) has been created for offering access to knowledge and expertise and attracting PhD talents in Europe. AIDA offers free\, top-notch AI Excellence Lecture Series\, featuring senior experts and promising juniors\, encouraging active participation\, and providing easy access through multiple channels \n🔗 For more information: Artificial Intelligence Doctoral Academy – AI Excellence Lecture Series \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n \n \n \n Event Footer\n \n\n\n\n\n\n \n \n Details\n Date: January 16 \n Time: 17:00 - 18:00 \n Event Category: Lectures & Seminars \n \n AI\n ML\n \n \n \n Add to Calendar\n \n \n \n \n Website\n \n Hybrid Causal Machine Learning in the Earth Sciences\n \n \n \n Venue\n Location: ONLINE \n \n \n Organiser\n AIDA – Artificial Intelligence Doctoral Academy \n View Organiser Website \n \n \n \n © 2024 AIDA – Artificial Intelligence Doctoral Academy. All rights reserved. URL:https://elias-ai.eu/event/hybrid-causal-machine-learning-in-the-earth-sciences/ LOCATION:ONLINE CATEGORIES:Lectures & Seminars ATTACH;FMTTYPE=image/png:https://elias-ai.eu/wp-content/uploads/2024/02/7-1.png END:VEVENT END:VCALENDAR