BEGIN:VCALENDAR VERSION:2.0 PRODID:-//elias-ai - ECPv6.18.1//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: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/Rome:20261212T080000 DTEND;TZID=Europe/Rome:20261212T170000 DTSTAMP:20261014T124814Z CREATED:20261014T124811Z LAST-MODIFIED:20261014T124814Z UID:12793-1797062400-1797094800@elias-ai.eu SUMMARY:ELIAS @ NeurIPS2026 | Foundations of Agentic Systems Theory (FAST) workshop DESCRIPTION:The Foundations of Agentic Systems Theory (FAST) workshop will take place on December 12\, 2026 in Paris\, held at NeurIPS 2026. FAST brings together researchers from AI\, complex systems\, developmental biology\, organizational sociology and cognitive science to ask how the behavior of systems of LLM-based agents emerges\, and how it can be understood and controlled. \n\n \n 12 DecWorkshop day\, 2026\n ParisPalais des Congrès\n 4Keynote speakers\n 8Research topics\n \n\n About the workshop\n\n The most interesting and consequential behaviors of complex systems often arise not from the parts in isolation\, but from the patterns of interaction between them. Current development of agentic AI has largely focused on building more capable individual agents\, which risks underestimating both the capabilities and the risks of agents once they become widespread. \n\n Existing theory from control\, game and economic theory\, operations research and the social sciences does not map cleanly onto agentic AI: LLM-based agents are neither idealized rational agents nor culturally shaped human agents. FAST provides a venue to investigate which mechanisms of emergent behavior carry over to systems of LLM-based agents\, which properties of the underlying agents facilitate or impede them\, and how far system-wide outcomes can be controlled or induced. Interdisciplinary participation is strongly encouraged\, through both contributions and invited talks. \n\n Topics of interest\n\n \n Mechanisms of emergent capabilities and behaviors in agentic systems\n Evaluation\, detection\, and bounding of emergent capabilities or failure modes\n Harness engineering and (neuro-symbolic) scaffolding\n Theory of mind and recursive social cognition\n Formation of norms\, conventions\, and collective bias in populations of agents\n Compositional safety and governance\n Definitions and philosophy of agency and emergence in engineered systems\n Observability\, monitorability and controllability of populations of agents\n \n\n Keynote speakers\n\n \n Michael LevinTufts UniversityStudies bioelectricity\, morphogenesis and collective cognition\, and how competent parts compose into collective agents with goals of their own.\n Danielle PerszykAmazon AGI SF LabCognitive scientist leading the human-computer interaction team\, working on practical AI agents that act in digital and physical environments.\n Winnie StreetGoogle ResearchResearches social cognition in large language models\, including theory of mind and its implications for alignment and group dynamics.\n Atoosa KasirzadehCarnegie Mellon University / Google DeepMindPhilosopher of AI ethics and governance\, working on AI existential risk and on characterizing AI agents for alignment and governance.\n \n\n Program\n\n The workshop opens with brief remarks from the organizers\, followed by a mix of keynotes\, contributed talks\, poster sessions and a panel\, with networking breaks throughout to maximize discussion time. \n\n \n Keynotes30-minute keynote talks from leading researchers across cognitive science\, biology\, philosophy and AI.\n Contributed talks and postersTwo contributed talk sessions and two poster sessions presenting accepted papers.\n Panel discussionAn hour-long panel\, “Mind to machines: Emergence\, methods\, and risks”\, moderated by Joshua Krook. Panelists will be announced closer to the workshop.\n \n\n The detailed schedule will be posted on the workshop website once paper decisions have been finalized. \n\n Important dates\n\n \n September 5\, 2026 (AoE)Paper submission deadline\n September 29\, 2026 (AoE)Acceptance notification\n December 12\, 2026Workshop\n December 20\, 2026 (AoE)Camera-ready deadline\n \n\n Submission information\n\n \n Full papersUp to 7 pages\, excluding references and appendices. For mature or completed research.\n Short papersUp to 4 pages\, excluding references and appendices. For ongoing work\, early-stage ideas\, or the release of benchmarks and datasets.\n \n\n Submissions are made through OpenReview using the NeurIPS 2026 template\, and must be anonymized for double-blind review. Accepted papers are presented as posters or contributed talks. Papers are non-archival\, so work under submission elsewhere is welcome. \n\n Registration\n\n Registrations for the NeurIPS Europe event have sold out\, and a waitlist is open. Registration is complimentary for financial aid recipients\, volunteers\, top reviewers\, ACs/SACs\, and authors of papers at affinity events. A second call for volunteers\, open to PhD students and postdocs and including free registration\, will open in early October. The venue is the Palais des Congrès de Paris. \n\n Organizers\n\n \n Erik MiehlingIBM Research - Ireland\n Madeline ReineckeUniversity of Oxford\n Hamza MostafaUniversity of Waterloo\n Jordan McAfooseIBM Research - Zurich\n Irina RishUniversité de Montréal / Mila\n Djallel BouneffoufIBM Research - Yorktown Heights\n \n\n \n December 12\, 2026 · Paris. Foundations of Agentic Systems Theory at NeurIPS 2026. Questions? Write to fast.workshop.team@gmail.com or visit the workshop website. URL:https://elias-ai.eu/event/elias-neurips2026-fast-workshop/ CATEGORIES:Conferences,Workshops ATTACH;FMTTYPE=image/png:https://elias-ai.eu/wp-content/uploads/2026/10/ELIASFAST2026.png END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Rome:20261213T080000 DTEND;TZID=Europe/Rome:20261213T170000 DTSTAMP:20261014T140431Z CREATED:20261014T134930Z LAST-MODIFIED:20261014T140431Z UID:12827-1797148800-1797181200@elias-ai.eu SUMMARY:ELIAS @ NeurIPS2026 | Representations for the Physical Sciences (R/PS) workshop DESCRIPTION:The Representations for the Physical Sciences (R/PS) workshop will take place on December 13\, 2026 in Paris\, held in conjunction with NeurIPS 2026. R/PS provides a tightly scoped forum bringing together machine learning researchers\, computational scientists\, and physicists to explore how representation learning can unlock breakthroughs across physical systems. \n\n \n 13 DecWorkshop day\, 2026\n ParisSorbonne University\n 5Invited speakers\n 4Core themes\n \n\n About the workshop\n\n Physical data are inherently continuous\, multi-scale\, non-Euclidean\, and strictly bound by physical laws. While standard machine learning architectures have driven massive successes in vision and language\, standard pretext tasks\, patching\, and loss functions often fail to preserve underlying physical symmetries\, conservation principles\, and sub-grid dynamics. \n\n For its first edition\, the R/PS workshop addresses the foundational representation learning bottleneck in physical systems. We focus on four key interconnected themes: self-supervision under physical constraints\, out-of-distribution transfer to actionable regimes\, adaptive simulation sampling\, and discrete tokenization of continuous physical modalities. \n\n Core themes\n\n \n \n Self-Supervision\n Learning with no labels\n Extracting physical structures from abundant unlabeled data while ensuring SSL pretext objectives preserve conservation laws and physical constraints.\n \n \n Transfer Learning\n Falsifiable generalization\n Ensuring model predictions extrapolate reliably into physically meaningful OOD regimes where wet-lab or high-fidelity validation is expensive.\n \n \n Sampling\n Adaptive data generation\n Leveraging simulators (MD\, DFT\, CFD\, PDE solvers) and experimental loops to shape the training distribution via adaptive sampling.\n \n \n Tokenization\n Physical modalities\n Designing novel tokenization schemes for continuous\, multi-scale\, and geometric data without destroying sub-grid dynamics or symmetries.\n \n \n\n Topics of interest\n\n \n Self-supervised objectives preserving physical constraints & conservation laws\n Out-of-distribution extrapolation & falsifiable embedding evaluation\n Adaptive simulation & closed-loop data generation with PDE/DFT solvers\n Geometric\, continuous\, and multi-scale tokenization for physical data\n Research Notes on open problems\, benchmarks\, paradigms\, and datasets\n Physics-informed foundation models and geometric representations\n \n\n Invited speakers\n\n \n \n Nils Thuerey\n Technical University of Munich\n Researches deep learning\, partial differential equations\, and fluid dynamics simulations.\n \n \n Jean-Philippe Vert\n Bioptimus\n Specializes in machine learning for biology\, genomics\, and precision medicine.\n \n \n Mark Girolami\n University of Cambridge\n Focuses on statistical ML\, uncertainty quantification\, and engineering applications.\n \n \n Francesco Locatello\n ISTA\n Works on causal representation learning\, causal discovery\, and AI for scientific discovery.\n \n \n Jigyasa Nigam\n Flatiron Institute\n Researches atomistic systems and physically constrained machine learning.\n \n \n\n Program & Format\n\n The workshop is a single-day in-person event featuring invited keynotes\, oral presentations of accepted short papers\, interactive poster sessions\, and community discussions. \n\n \n KeynotesInvited talks by leading researchers at the intersection of physics\, AI\, and scientific computing.\n Contributed Talks & PostersOral and poster presentations selected from peer-reviewed short paper submissions.\n Discussion & NetworkingStructured time for interdisciplinary exchange\, open discussions\, and collaboration.\n \n\n Important dates\n\n \n July 29\, 2026 (AoE)Call for papers opens\n August 29\, 2026 (AoE)Paper submission deadline\n September 29\, 2026 (AoE)Author notification\n December 13\, 2026Workshop day\n \n\n Submission information\n\n \n \n Short Papers\n Up to 4 pages (excluding references and appendices) for mature or ongoing research.\n \n \n Research Notes\n Accessible explanations of open problems\, paradigms\, datasets\, or algorithms. Clarity & usefulness emphasized.\n \n \n\n Submissions must consist of a single anonymized PDF following the NeurIPS LaTeX format. Accepted papers are non-archival and will be presented via poster or oral presentation. \n\n Venue & Location\n\n The workshop takes place at Room 108\, Campus Pierre et Marie Curie\, Sorbonne University (4 Pl. Jussieu\, 75005 Paris\, France) as part of the NeurIPS 2026 Paris events. \n\n Organizers\n\n \n Pietro NovelliItalian Institute of Technology\n Massimiliano PontilIIT / UCL\n Florence d'Alché-BucTélécom Paris / IP Paris\n Pierre GentineColumbia University\n Kara LambColumbia University\n Mathias NiepertUniversity of Stuttgart\n \n\n \n December 13\, 2026 · Paris. Representations for the Physical Sciences at NeurIPS 2026. Questions? Write to representations-physical-sciences@googlegroups.com or visit the official website. URL:https://elias-ai.eu/event/elias-neurips2026-representations-for-the-physical-sciences-r-ps-workshop/ LOCATION:NeurIPS2026\, Campus Pierre et Marie Curie\, Room 108 Sorbonne University\, 4 Pl. Jussieu\,\, Paris\, 75005\, France CATEGORIES:Conferences,Workshops ATTACH;FMTTYPE=image/png:https://elias-ai.eu/wp-content/uploads/2026/10/ELIASRPS2026-1.png END:VEVENT END:VCALENDAR