Select a calendar:
Filter May Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for May 23, 2024
-
Aviation Law & Aviation Dispute Resolution LEGAL 24-2Thu, May 23, 2024 @ 08:00 AM - 04:00 PM
Aviation Safety and Security Program
University Calendar
This course is designed to provide information on the legal risks inherent in aviation operations and an overview of the legal system as it relates to aviation safety. It provides an understanding of the various legal processes relating to aviation and discusses ways to engage aviation authorities responsibly and successfully. The judicial process, current litigation trends, legal definitions, and procedures are also covered.
Our experienced aviation lawyers, as instructors, will encourage "preventative legal medicine" to avoid legal problems. Classes are not just lectures but include interactive issue-spotting so that students can get relevant legal advice from their organizations' lawyers if and when legal problems develop.Location: Century Boulevard Building (CBB) - 920
Audiences: Everyone Is Invited
Contact: Daniel Scalese
Event Link: https://avsafe.usc.edu/wconnect/CourseStatus.awp?&course=24ALEGAL2
-
Advanced Software Safety ADVSFT 24-1
Thu, May 23, 2024 @ 08:00 AM - 04:00 PM
Aviation Safety and Security Program
University Calendar
This course builds upon the skills learned in the Software Safety (SFT) course. It is presumed and highly recommended that the student understands the importance of software safety in planning, analyzing architecture, designing, and coding and testing automated systems. The course expands upon those skills and presents opportunities to apply them in class in diverse situations using a small unmanned aerial system (sUAS) that is also weaponized.
Location: Century Boulevard Building (CBB) - 960
Audiences: Everyone Is Invited
Contact: Daniel Scalese
Event Link: https://avsafe.usc.edu/wconnect/CourseStatus.awp?&course=24AADVSFT1
-
AI Seminar-Things Multimodal LLMs Cannot See: Toward Discovering and Mitigating Perceptual Biases in Neural Networks through Visual Interventions
Thu, May 23, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Mahyar Khayatkhoei , USC/ISI
Talk Title: Things Multimodal LLMs Cannot See: Toward Discovering and Mitigating Perceptual Biases in Neural Networks through Visual Interventions
Abstract: In this talk, I will discuss our recent research on the use of pixel-space interventions for discovering and mitigating biases in visual neural networks, including in multimodal large language models (MLLMs). I will start by showcasing our discovered perceptual limitations and biases of MLLMs (including commercial ones such as GPT-4V and LLaVA). I will then discuss our simple yet effective intervention-based approach for mitigating such limitations, which can do so without requiring any training. Finally, I will more broadly discuss the problem of removing attribute-specific bias from neural networks, present our latest information theoretic bounds on this problem, and explain our adversarial input-intervention approach for removing strong attribute bias.
This event will be recorded but only shared with AI Division Leadership.
Biography: I am a Computer Scientist at the AI Division of the USC Information Sciences Institute. I received my Ph.D. and M.Sc. in computer science from Rutgers University working with Dr. Ahmed Elgammal, and my B.Sc. in electrical engineering from the University of Tehran. My research explores the theory and application of deep generative models, and has identified and resolved major bottlenecks in neural networks’ ability to learn from heterogeneous data (NeurIPS 2018), to learn high frequency features (AAAI 2022), and in their reliable evaluation (ICML 2023). My latest focus is on adopting large-scale generative neural networks to real-world mission-critical tasks. I am particularly interested in developing reliable and efficient data-driven computational models of real-world phenomena that would enhance our current physics-based models. My personal website is at https://mahyarkoy.github.io
Host: Host: Adam Russell, POC Justina Gilleland and Alma Nava
More Info: https://www.isi.edu/events/4966/things-multimodal-llms-cannot-see-toward-discovering-and-mitigating-perceptual-biases-in-neural-networks-through-visual-interventions/
Webcast: https://usc.zoom.us/j/93179461297?pwd=d2RpNWlEblhxcHRFMU9RbnRxbWJBUT09Location: Information Science Institute (ISI) - Conf Rm#1135
WebCast Link: https://usc.zoom.us/j/93179461297?pwd=d2RpNWlEblhxcHRFMU9RbnRxbWJBUT09
Audiences: Everyone Is Invited
Contact: Pete Zamar
