Select a calendar:
Filter May Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for May 31, 2024
-
PhD Dissertation Defense - Xin Qin
Fri, May 31, 2024 @ 09:30 AM - 11:30 PM
Thomas Lord Department of Computer Science
University Calendar
Presentation title: Data-driven and Logic-based Analysis of Learning-enabled Cyber-Physical Systems
Names of the guidance committee members: Jyotirmoy Deshmukh, Chao Wang, Souti Chattopadhyay, and Yan Liu
Abstract:
Rigorous analysis of cyber-physical systems (CPS) is becoming increasingly important, particularly for safety-critical applications incorporating learning-enabled components. Given a system requirement such as "if the system deviates from the center of the road, it should return to the center in time," we aim to evaluate how well the system satisfies this requirement in uncertain environments. The defense will center around three main pillars: (1) performing verification for initial states and during the runtime of the system, (2) demonstrating how to reuse verification results for unseen systems, and (3) designing new specification languages to alleviate sensitivity to noise. Since these three pillars all involve a similar approach of black-box modeling and analysis using properties related to specification languages, we anticipate that future work could integrate the results from various stages of this thesis. This integration would facilitate the sharing and reuse of findings at each stage, thereby enhancing system safety analysis and improving the scalability of the reasoning process.
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Ellecia Williams
-
Human-AI Interaction: From Supporting Surgical Training to Inspecting Social Bias in LLMs
Fri, May 31, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Rafal Kocielnik, California Institute of Technology
Talk Title: Human-AI Interaction: From Supporting Surgical Training to Inspecting Social Bias in LLMs
Series: AI Seminar
Abstract: *Meeting hosts only admit on-line guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom. If you’re an outside visitor, please inform us at (aiseminars-poc(at)isi.edu) to make us aware of your attendance so we can admit you. Specify if you will attend remotely or in person at least one business day prior to the event Provide your: full name, job title and professional affiliation and arrive at least 10 minutes before the seminar begins. If you do not have access to the 6th Floor for in-person attendance, please check in at the 10th floor main reception desk to register as a visitor and someone will escort you to the conference room location.
In this talk, I will present my recent contributions to Human-AI interaction, focusing on two distinct projects looking at opportunities and challenges involved in the use of modern AI. In the first part of my talk, I will present my work on leveraging AI in clinician education, specifically within the surgical context. I will detail my work on utilizing multimodal deep-learning techniques to analyze formative feedback from surgeons to trainees in the context of real-world robot-assisted surgeries. This project marks a significant step forward in harnessing contemporary AI for the specialized domain of surgical education, receiving the best paper award at the ML4H conference. For the second part of my talk, I will focus on Human-AI interaction in the context of empowering domain experts (e.g., social scientists and ethicists) to inspect modern generative AI for the presence of harmful stereotypes. I will describe our BiasTestGPT framework which offers two important contributions: 1) a novel approach for generating high-quality synthetic data for social bias testing at scale and 2) a user-friendly and open-sourced interface for engaging the general public and domain experts in the inspection of modern AI. Together, these projects demonstrate opportunities in leveraging Human-AI interaction for supporting specialized domains and helping inspect the challenges in AI itself. This event will be recorded. It will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI.
Biography: RafaÅ Kocielnik is a Postdoctoral Researcher at Caltech's Computing+Mathematical Sciences department, where he also collaborates with Cedars-Sinai Medical Center and Activision Blizzard gaming company. He holds an M.Sc. in Computer Science from the Polish-Japanese Academy of Information Technology, a P.D.Eng. in Industrial Design from Eindhoven University of Technology and completed his Ph.D. in Human-Centered Design & Engineering at the University of Washington, Seattle, in 2021. His focus was on designing engaging conversational interactions for health and behavior change. Awarded a CRA Computing Innovation Fellowship in 2021, his research at Caltech explores the intersection of AI and HCI with applications in surgical training, social bias testing in Generative AI, and toxicity mitigation in gaming. He has received Best Paper awards at CSCW and ML4H, with an Honorable Mention at CUI, underscoring his interdisciplinary focus and commitment to advancing AI and HCI for human-centered applications. Visit links below to subscribe and for details on upcoming seminars: https://www.isi.edu/isi-seminar-series/ https://www.isi.edu/events/
Host: Myrl Marmarelis and Justina Gilleland + Maura Covaci
More Info: https://www.isi.edu/events/4976/human-ai-interaction-from-supporting-surgical-training-to-inspecting-social-bias-in-llms/
Webcast: https://usc.zoom.us/j/99601436181?pwd=d0Y5eTZPbHRjM2t3NHc5cXRMNkE1dz09Location: Information Science Institute (ISI) - Conf Rm#1135-1137
WebCast Link: https://usc.zoom.us/j/99601436181?pwd=d0Y5eTZPbHRjM2t3NHc5cXRMNkE1dz09
Audiences: Everyone Is Invited
Contact: Pete Zamar
