{"count":203,"next":null,"previous":"https://memento.epfl.ch/api/v1/events/?format=json&limit=10&offset=190&ordering=cancel_reason","results":[{"id":71933,"title":"Controlling and Guiding Generative Models for Three-Dimensional Shape Optimization","slug":"controlling-and-guiding-generative-models-for-thre","event_url":"https://memento.epfl.ch/event/controlling-and-guiding-generative-models-for-thre","visual_url":null,"visual_large_url":null,"visual_maxsize_url":null,"lang":"en","start_date":"2026-07-07","end_date":"2026-07-07","start_time":"11:00:00","end_time":"13:00:00","description":"<u>EDIC candidacy exam</u><br>\r\nExam president: Prof. Martin Rajman<br>\r\nThesis advisor: Prof. Pascal Fua<br>\r\nCo-examiner: Prof. Mark Pauly<br>\r\n<br>\r\n<u>Abstract</u><br>\r\nOptimizing 3D shapes within the latent spaces of deep generative models is fundamental to computer assisted engineering, yet remains prone to a critical failure mode we term manifold drift: the tendency of gradient-based optimization to move latent vectors away from the manifold of valid shapes. This problem is exacerbated in state-of-the-art 3D shape generative models that operate in increasingly high-dimensional latent spaces where valid shapes occupy a vanishingly small fraction of the full space. Existing mitigation strategies, including latent regularization and flow-matching approaches, either sacrifice expressiveness, demand a difficult trade-off between objective guidance and generative fidelity that remains prone to manifold drift, or are computationally infeasible to scale to modern, large-capacity 3D shape models. We introduce a novel optimizer-corrector framework that alternates between gradient steps for objective minimization and guided flow matching to drive the latent state back to the valid shape manifold. By decoupling objective minimization from flow-based correction, optimizing freely and correcting strictly, this alternating design avoids inherent trade-offs, preserving geometric validity without sacrificing expressiveness while remaining computationally feasible on modern 3D shape models. We demonstrate its effectiveness across generative priors of varying complexity, from simple vector latent spaces to large-scale architectures across a variety of downstream optimization tasks, including aerodynamic drag reduction and object compliance optimization.<br>\r\n<br>\r\n<u>Selected papers</u><br>\r\n ","image_description":"","creation_date":"2026-05-22T13:14:54","last_modification_date":"2026-05-22T13:14:54","link_label":"","link_url":"","canceled":"False","cancel_reason":"","place_and_room":"BC 333","url_place_and_room":"https://plan.epfl.ch/?room==BC%20333","url_online_room":"","spoken_languages":[],"speaker":"Emilien Seiler","organizer":"","contact":"edic@epfl.ch","is_internal":"False","theme":"","vulgarization":{"id":1,"fr_label":"Tout public","en_label":"General public"},"registration":{"id":3,"fr_label":"Entrée libre","en_label":"Free"},"keywords":"EDIC candidacy exam","file":null,"icalendar_url":"https://memento.epfl.ch/event/export/120840/","category":{"id":1,"code":"CONF","fr_label":"Conférences - Séminaires","en_label":"Conferences - Seminars","activated":true},"academic_calendar_category":null,"domains":[],"mementos":["https://memento.epfl.ch/api/v1/mementos/48/?format=json","https://memento.epfl.ch/api/v1/mementos/6/?format=json","https://memento.epfl.ch/api/v1/mementos/27/?format=json"]},{"id":71934,"title":"Future of Health Grant","slug":"future-of-health-grant-3","event_url":"https://memento.epfl.ch/event/future-of-health-grant-3","visual_url":"https://memento.epfl.ch/image/33245/200x112.jpg","visual_large_url":"https://memento.epfl.ch/image/33245/720x405.jpg","visual_maxsize_url":"https://memento.epfl.ch/image/33245/max-size.jpg","lang":"en","start_date":"2026-07-31","end_date":"2026-07-31","start_time":"11:00:00","end_time":"12:00:00","description":"<p>The <strong>Future of Health Grant</strong> is a support program dedicated to accelerating early‑stage digital health startups developing solutions relevant to the Swiss healthcare system.<br>\r\nCreated by CSS and the EPFL Innovation Park, it combines equity‑free funding, expert guidance and access to healthcare stakeholders to help founders progress from prototype to real‑world validation.<br>\r\n<br>\r\n<strong>For whom</strong>\r\n</p><ul>\r\n\t<li>For early‑stage digital health startups developing solutions that can be applied within the Swiss healthcare system.</li>\r\n\t<li>Eligible teams may be based in Switzerland or abroad, provided their innovation is relevant to Swiss clinical, operational or preventive care contexts.</li>\r\n\t<li>The program targets founders at the prototype, MVP or early validation stage.</li>\r\n</ul>\r\n<strong>What you gain</strong>\r\n\r\n<ul>\r\n\t<li><strong>equity‑free financial support</strong> at three possible levels (CHF 10k, 30k or 50k), depending on project maturity and needs</li>\r\n\t<li>teams benefit from <strong>structured coaching</strong>, <strong>industry mentoring</strong></li>\r\n\t<li>access to <strong>paid specialists</strong> through the “CxO as a Service” model</li>\r\n\t<li>The program also facilitates <strong>real‑world validation</strong> opportunities with healthcare professionals, hospitals, insurers and ecosystem partners in Switzerland</li>\r\n</ul>\r\n<strong>How it works</strong><br>\r\n<br>\r\nThe program operates fully virtually and follows a milestone‑based approach. Selected startups receive regular guidance from experts in digital health, business development and regulatory pathways. Each team works toward defined objectives, with progress reviewed at set intervals. The program supports founders in strengthening their product, business model and clinical relevance.<br>\r\n<strong>Program context</strong><br>\r\n<br>\r\nLaunched in 2022, the Future of Health Grant is an initiative of <strong>CSS</strong> and the <strong>EPFL Innovation Park</strong>. Its mission is to accelerate the adoption of impactful digital health solutions by bridging early‑stage innovation with the needs of real healthcare systems.","image_description":"","creation_date":"2026-05-22T13:39:38","last_modification_date":"2026-05-22T13:39:44","link_label":"Webpage","link_url":"https://future-of-health.org/","canceled":"False","cancel_reason":"","place_and_room":"","url_place_and_room":"","url_online_room":"","spoken_languages":["https://memento.epfl.ch/api/v1/spoken_languages/2/?format=json"],"speaker":"","organizer":"<a href=\"https://future-of-health.org/\">Future of Health Grant</a>, a programm powered by Fondation EPFL Innovation Park","contact":"Mathilde Durvy <a href=\"mailto:info@fohg.ch\">info@fohg.ch</a>","is_internal":"False","theme":"","vulgarization":{"id":2,"fr_label":"Public averti","en_label":"Informed public"},"registration":{"id":1,"fr_label":"Sur inscription","en_label":"Registration required"},"keywords":"","file":null,"icalendar_url":"https://memento.epfl.ch/event/export/120842/","category":{"id":17,"code":"DEADLINE","fr_label":"Echéance","en_label":"Deadline","activated":true},"academic_calendar_category":null,"domains":[],"mementos":["https://memento.epfl.ch/api/v1/mementos/422/?format=json"]},{"id":71936,"title":"Understanding and Predicting the Membrane Permeability of Macrocyclic Peptides Based on Large-Scale Data","slug":"understanding-and-predicting-the-membrane-permeabi","event_url":"https://memento.epfl.ch/event/understanding-and-predicting-the-membrane-permeabi","visual_url":"https://memento.epfl.ch/image/33247/200x112.jpg","visual_large_url":"https://memento.epfl.ch/image/33247/720x405.jpg","visual_maxsize_url":"https://memento.epfl.ch/image/33247/max-size.jpg","lang":"en","start_date":"2026-09-15","end_date":"2026-09-15","start_time":"16:15:00","end_time":"17:15:00","description":"<p>Macrocyclic peptides are promising molecules for targeting intracellular protein–protein interactions and other challenging biological targets. However, their poor membrane permeability often limits their biological and therapeutic applications. Understanding the structural factors that govern passive membrane permeation is therefore essential for the rational design of cell-permeable macrocyclic peptides.<br>\r\n<br>\r\nIn this seminar, I will present our recent efforts to understand and predict the membrane permeability of macrocyclic peptides using large-scale experimental data, conformational analysis, and machine learning. We aim to clarify how conformational flexibility, including molecular chameleonicity, influences membrane permeability.<br>\r\n<br>\r\nI will also introduce our ongoing efforts toward DNA-encoded macrocyclic N-methyl peptide libraries as a future platform for discovering functional intracellular binders.</p>","image_description":"Prof. Shinsuke Sando","creation_date":"2026-05-22T16:51:02","last_modification_date":"2026-05-22T16:51:02","link_label":"Prof. Shinsuke Sando","link_url":"https://park.itc.u-tokyo.ac.jp/sandolab/index_e.html","canceled":"False","cancel_reason":"","place_and_room":"CH G1 495","url_place_and_room":"https://plan.epfl.ch/?room==CH%20G1%20495","url_online_room":"","spoken_languages":["https://memento.epfl.ch/api/v1/spoken_languages/2/?format=json"],"speaker":"Prof. Shinsuke Sando, University of Tokyo","organizer":"C. Heinis","contact":"C. Heinis","is_internal":"False","theme":"","vulgarization":{"id":3,"fr_label":"Expert","en_label":"Expert"},"registration":{"id":3,"fr_label":"Entrée libre","en_label":"Free"},"keywords":"cbseminar","file":null,"icalendar_url":"https://memento.epfl.ch/event/export/120844/","category":{"id":1,"code":"CONF","fr_label":"Conférences - Séminaires","en_label":"Conferences - Seminars","activated":true},"academic_calendar_category":null,"domains":[],"mementos":["https://memento.epfl.ch/api/v1/mementos/9/?format=json","https://memento.epfl.ch/api/v1/mementos/14/?format=json"]}]}