BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//AIREA - Artificial Intelligence Education and Research Alliance - ECPv6.17.4.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:AIREA - Artificial Intelligence Education and Research Alliance
X-ORIGINAL-URL:https://airea.eduhk.hk
X-WR-CALDESC:Events for AIREA - Artificial Intelligence Education and Research Alliance
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20260212T100000
DTEND;TZID=Asia/Hong_Kong:20260212T110000
DTSTAMP:20260820T052759Z
CREATED:20260210T092617Z
LAST-MODIFIED:20260820T052759Z
UID:7024-1770890400-1770894000@airea.eduhk.hk
SUMMARY:Differential Privacy in LLM Fine-Tuning: What It Protects\, What It Costs\, and What It Doesn’t
DESCRIPTION:  \n\n\n\nDate\n12 February 2026 (Thursday)\n\n\nSpeaker\nProf. Yang CAO\nAssociate Professor\nInstitute of Science Tokyo\n\n\nSeminar Title\nDifferential Privacy in LLM Fine-Tuning: What It Doesn’t\n\n\nSpeaker’s Bio\nYang Cao is an Associate Professor at the Department of Computer Science\, Institute of Science Tokyo (Science Tokyo\, formerly Tokyo Tech)\, and directing the Trustworthy Data Science and AI (TDSAI) Lab. He is passionate about studying and teaching on algorithmic trustworthiness in data science and AI. Two of his papers on data privacy were selected as best paper finalists in top-tier conferences IEEE ICDE 2017 and ICME 2020. He was a recipient of the IEEE Computer Society Japan Chapter Young Author Award 2019\, Database Society of Japan Kambayashi Young Researcher Award 2021. His research projects were/are supported by JSPS\, JST\, MSRA\, KDDI\, LINE\, WeBank\, etc.\n\n\nAbstract\nLarge language models are often fine-tuned on small and sensitive datasets\, where individual training examples can strongly influence model behavior and lead to memorization and privacy leakage. This talk focuses on differential privacy in LLM fine-tuning and explains how DP acts as a learning constraint that limits the influence of individual samples\, thereby mitigating such risks. We introduce the core intuition behind DP without assuming prior background\, review practical DP fine-tuning mechanisms\, and discuss how privacy and utility should be evaluated together. We also clarify what DP fine-tuning can and cannot protect\, and outline open challenges in privacy-aware LLM adaptation.\n\n\nVenue\nC-LP-06\n\n\n\n 
URL:https://airea.eduhk.hk/calendar/differential-privacy-in-llm-fine-tuning-what-it-protects-what-it-costs-and-what-it-doesnt/
LOCATION:C-LP-06 (STEM Innovation Hub)
CATEGORIES:AIREA Seminar
ATTACH;FMTTYPE=image/png:https://airea.eduhk.hk/wp-content/uploads/2026/02/1-banner.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20260212T110000
DTEND;TZID=Asia/Hong_Kong:20260212T120000
DTSTAMP:20260820T052440Z
CREATED:20260210T092705Z
LAST-MODIFIED:20260820T052440Z
UID:7028-1770894000-1770897600@airea.eduhk.hk
SUMMARY:人工智能通识教育实践与赋能教育未来
DESCRIPTION:Date\n12 February 2026 (Thursday)\n\n\nSpeaker\nProf. Chunying LI \nVice Dean\, Professor \nSchool of Computer Science \nGuangdong Polytechnic Normal University\n\n\nSeminar Title\nPractices of General AI Education and AI Empowerment for the Future of Education\n\n\nSpeaker’s Bio\nChun Ying\, PhD\, Professor\, Doctoral Supervisor. She currently serves as Vice Dean of the School of Computer Science\, Guangdong Polytechnic Normal University\, and Director of the Joint Laboratory for Intelligent Education (University-Enterprise Cooperation). \nShe is a Distinguished Member of China Computer Federation (CCF)\, Member of CCF Guangzhou Committee\, and Executive Member of CCF Technical Committee on Collaborative Computing. She holds a number of social appointments including Peer Review Expert for projects supported by the National Natural Science Foundation of China\, Project Review Expert of the Department of Science and Technology of Guangdong Province\, Expert of the Expert Committee for Digital Guangdong Development\, and Member of the Guangdong Working Group for Computer Discipline under the Ministry of Education’s “101 Plan”. \nIn recent years\, her research and teaching focus on intelligent education\, community detection\, knowledge graphs and recommendation algorithms. She has published more than 50 papers\, compiled and published 4 textbooks\, and filed/obtained over 20 intellectual property rights. She has presided over more than 10 research and teaching projects including those funded by the National Natural Science Foundation of China. In the past five years\, as the sole recipient or the first-ranked contributor\, she has won over 10 honors such as the Excellent Textbook Award (Higher Education Category) of Guangdong Province and the First Prize of Scientific and Technological Progress Award issued by Guangdong Artificial Intelligence Industry Association.\n\n\nAbstract\nAgainst the backdrop of an era where artificial intelligence serves as the core driving force spearheading a new round of technological revolution and industrial transformation\, strengthening general education in artificial intelligence carries vital strategic significance for fostering students’ digital literacy and computational thinking. Taking the practice of AI literacy education at Guangdong Polytechnic Normal University as an example\, this report elaborates on an innovative teaching model for general artificial intelligence courses. Centered on personalized competency cultivation\, the model relies on platforms as carriers and knowledge graphs as links. It demonstrates major practices of tiered teaching for students from diverse majors\, offering replicable and promotable valuable experience for the development of AI general education courses in various educational institutions. \nOn this basis\, centering on the core theme of “AI Empowering the Future of Education”\, the report analyzes the profound transformative potential of AI in education from four dimensions: targeted innovation of teaching models\, upgrading of talent cultivation objectives\, collaborative evolution of educational ecosystems\, and two-way empowerment of technology and ethics. Meanwhile\, it addresses practical challenges including rapid technological iteration\, balanced resource allocation and ethical norms\, and proposes countermeasures such as dynamic curriculum updates\, popularization of lightweight tools and diversified collaborative governance. The findings provide theoretical references and practical guidance for advancing high-quality development of AI general education and constructing a new paradigm of AI-enabled education.\n\n\nVenue\nC-LP-06\n\n\n\n 
URL:https://airea.eduhk.hk/calendar/%e4%ba%ba%e5%b7%a5%e6%99%ba%e8%83%bd%e9%80%9a%e8%af%86%e6%95%99%e8%82%b2%e5%ae%9e%e8%b7%b5%e4%b8%8e%e8%b5%8b%e8%83%bd%e6%95%99%e8%82%b2%e6%9c%aa%e6%9d%a5/
LOCATION:C-LP-06 (STEM Innovation Hub)
CATEGORIES:AIREA Seminar
ATTACH;FMTTYPE=image/png:https://airea.eduhk.hk/wp-content/uploads/2026/02/2-banner.png
END:VEVENT
END:VCALENDAR