Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for March
-
Alfred E. Mann Department of Biomedical Engineering
Fri, Mar 01, 2024 @ 11:00 AM - 12:00 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Michelle Khine- Professor of Biomedical Engineering and Associate Dean of Undergraduate Education, Professor of Biomedical Engineering and Associate Dean of Undergraduate Education UC Irvine
Talk Title: Soft Electronics for Ubiquitous Physiological Monitoring
Abstract: While great advances in medicine has been made in the past century, the overall infrastructure of the healthcare system has not progressed. Patients are still expected to travel to a centralized location for discrete, reactionary based care where the healthcare provider only has a brief window to assess the patient’s health. Unless the symptoms are overt at the time of examination, the subjective evaluation relies heavily on the self-reporting of symptoms from the patient. This often results in delayed or improper diagnoses. In contrast, we know that physiological signals precede clinical deterioration. We have developed a suite of soft, low-cost, unobtrusive, Band-Aid © like physiological sensors to continuously monitor patients cardiovascular and pulmonary functions. We seek to continuously quantify subtle physiological changes to predict – and eventually prevent -- the onset of acute clinical events.
Biography: Michelle Khine, Ph.D. is a Professor of Biomedical Engineering and Associate Dean of Undergraduate Education at UC Irvine. She was the founding Director of Faculty Innovation at the Samueli School of Engineering and founding Director of BioENGINE (BioEngineering Innovation and Entrepreneurship) at UC Irvine. Prior to joining UC Irvine, she was an Assistant & Founding Professor at UC Merced. Michelle received her BS and MS from UC Berkeley in Mechanical Engineering and her PhD in Bioengineering from UC Berkeley and UCSF. She is the Scientific Founder of 6 start-up companies. Michelle was the recipient of the TR35 Award and named one of Forbes 10 Revolutionaries’ and by Fast Company Magazine as one of the 100 Most Creative People in Business. She was awarded the NIH New Innovator s Award and was named by Marie Claire magazine as Women on Top: Top Scientist. Michelle is a Fellow of AIMBE (American Institute of Medical and Biological Engineering) and a Fellow of the National Academy of Inventors.
Host: Maral Mousavi
Location: Olin Hall of Engineering (OHE) - 100 B
Audiences: Everyone Is Invited
Contact: Carla Stanard
-
Semiconductors & Microelectronics Seminar - Yiyang Li, Friday, March 1st at 2pm in EEB 248
Fri, Mar 01, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Yiyang Li, University of Michigan
Talk Title: How to Store Information Indefinitely using Ions
Series: Semiconductors & Microelectronics Technology
Abstract: Ion-based memory devices including resistive memory and electrochemical memory present promising opportunities for embedded nonvolatile memory, in-memory computing, and neuromorphic computing. Such devices switch resistance states through the electrochemical migration of oxygen vacancies in transition metal oxides. In this talk, we present our recent research on the materials thermodynamics principles that govern ion motion in oxygen-based resistive memory. Using a combination of device measurements, materials characterization, and multiscale physical modeling, we find that oxygen vacancies do not obey Fick's First Law of diffusion as conventionally believed, but instead undergo composition phase separation, which enables diffusion against the concentration gradient. This phase separation is critical to the ability of resistive memory to retain information for long, and potentially indefinite, periods of time. Finally, we utilize this understanding of phase separation in transition metal oxides to engineer exceptionally long retention times in three-terminal electrochemical memory.
Biography: Yiyang Li is an Assistant Professor of Materials Science and Engineering at the University of Michigan, where he conducts research on ionic memory and energy storage. Trained as an electrochemist, he received his PhD at Stanford University in 2016, and was appointed a Harry Truman Fellow at Sandia National Labs. Yiyang received the Intel Rising Star Faculty Award in 2022.
Host: J Yang, H Wang, C Zhou, S Cronin, W Wu
More Information: Yiyang Li_2024-03-01.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
CS Colloquium: Emily Tseng (Cornell University) - Digital Safety and Security for Survivors of Technology-Mediated Harms
Mon, Mar 04, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Emily Tseng, Cornell University
Talk Title: Digital Safety and Security for Survivors of Technology-Mediated Harms
Series: Computer Science Colloquium
Abstract: Platforms, devices, and algorithms are increasingly weaponized to control and harass the most vulnerable among us. Some of these harms occur at the individual and interpersonal level: for example, abusers in intimate partner violence (IPV) use smartphones and social media to surveil and stalk their victims. Others are more subtle, at the level of social structure: for example, in organizations, workplace technologies can inadvertently scaffold exploitative labor practices. This talk will discuss my research (1) investigating these harms via online measurement studies, (2) building interventions to directly assist survivors with their security and privacy; and (3) instrumenting these interventions as observatories, to enable scientific research into new types of harms as attackers and technologies evolve. I will close by sharing my vision for centering inclusion and equity in digital safety, security and privacy, towards brighter technological futures for us all.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Emily Tseng is a PhD candidate in Information Science at Cornell University. Her research develops the systems, interventions, and design principles we need to make digital technology safe and affirming for everyone. Emily’s work has been published at top-tier venues in human-computer interaction (ACM CHI, CSCW) and computer security and privacy (USENIX Security, IEEE Oakland). For 5 years, she has worked as a researcher-practitioner with the Clinic to End Tech Abuse, where her work has enabled specialized security services for over 500 survivors of intimate partner violence (IPV). Emily is the recipient of a Microsoft Research PhD Fellowship, Rising Stars in EECS, Best Paper Awards at CHI, CSCW, and USENIX Security, and third place in the Internet Defense Prize. She has interned at Google and with the Social Media Collective at Microsoft Research. She holds a B.A. from Princeton University.
Host: Jesse Thomason
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
AME Seminar
Mon, Mar 04, 2024 @ 01:30 PM - 02:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Preston Culbertson, California Institute of Technology
Talk Title: To Err is Robotic: Enabling Robust Autonomy with Risk-Sensitivity
Abstract: Despite significant recent advances in robot learning and perception, achieving robust robot behavior for real-world, dynamic tasks like dexterous manipulation remains elusive. This challenge stems from the uncertainty inherent in robots' geometric models, perception systems, and controllers, particularly during dynamic interactions with the environment. This talk explores how risk-sensitivity can provide a principled, practical approach to addressing these robustness issues directly. First, I will discuss our work showing Neural Radiance Fields (NeRFs) — typically trained for novel view synthesis — can be used for both collision avoidance and localization, repurposing them as a versatile, probabilistic occupancy model for robotics. Next, we will turn to the problem of real-time, risk-sensitive planning more broadly. Specifically, I will present work combining stochastic control barrier functions (CBFs), which provide rigorous probabilistic safety/performance guarantees, with deep generative dynamics models to yield a lightweight, data-driven approach to risk-sensitive control. We have demonstrated that our method (running onboard a quadrotor at 100Hz) enables aggressive, yet safe flight with a completely unmodeled and uninstrumented slung load. The talk will conclude with a discussion of some lessons learned and future directions in risk-sensitive robotics.
Biography: Preston Culbertson is a postdoctoral scholar in the AMBER Lab at Caltech. His research interests lie at the intersection of robotics, machine learning, optimization, and computer vision. Specifically, his research explores how to enable robust robot behavior for dynamic, contact-rich tasks like manipulation, locomotion, and navigation, emphasizing new tools for understanding risk and uncertainty for autonomous systems. Preston earned his PhD from Stanford University, mentored by Prof. Mac Schwager, where his work on collaborative manipulation and robot assembly was awarded the NASA Space Technology Research Fellowship and the 'Best Manipulation Paper' award at ICRA 2018.
More Info: https://ame.usc.edu/seminars/
Webcast: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09Location: Olin Hall of Engineering (OHE) - 406
WebCast Link: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
ECE-EP seminar - Rishabh Sahu, Monday, March 4th at 2pm in EEB 248
Mon, Mar 04, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Rishabh Sahu, Postdoctoral scholar, IST Austria
Talk Title: Building Quantum Networks with Quantum Electrooptics
Series: ECE-EP Seminar
Abstract: In the last few decades, a myriad of physical systems such as photons, atoms, ions and spins have been explored for various different quantum technologies such as computation, communication and meteorology. Until now, no single physical system has been suitable for all the different quantum applications and, therefore, different systems are utilized in different spheres usually without any intercompatibility between them. A solution to this emerging chaos in the quantum landscape is to build hybrid quantum networks where various quantum systems with their unique advantages can be connected together to build a combined system able to perform better than the sum of its aggregates. The nodes in such a network would be connected using flying qubits - telecom wavelength optical photons - which would also allow these nodes to be separated by long distances. There has been some progress in this direction, particularly attempts to make trapped ions and solid state qubits compatible with optical photons. However, making microwave technologies such as superconducting qubits compatible with high energy optics is more challenging due to the large energy gap between the two. In this talk, I will present how quantum electro optics can be used to establish a quantum bridge between microwave and optical frequencies. Such a bridge would not only allow connection of superconducting quits over a long distance but also would be a key step in making future hybrid quantum networks a reality.
Biography: Rishabh completed his bachelor's and master's degree in Physics at the Indian Institute of Technology, Kanpur. His research mainly involved studying orbital angular momentum of light, in particular, sorting photons in this basis to get a multidimensional basis for photons. His master's thesis involved simulating Maxwell's equation using Finite Difference Time Domain (FDTD) method. Rishabh started graduate school at ISTA in fall of 2018 and joined the Fink group in 2019. He graduated in 2023 and works now as a postdoc on new cavity electrooptics experiments.
Host: ECE-EP
Webcast: https://usc.zoom.us/j/97370470279?pwd=NGZ4aWdGUHRjUUtrQllkemVIV3lxQT09More Information: Rishabh Sahu Seminar Announcement.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
WebCast Link: https://usc.zoom.us/j/97370470279?pwd=NGZ4aWdGUHRjUUtrQllkemVIV3lxQT09
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
CSC/CommNetS-MHI Seminar: Magnus Egerstedt
Mon, Mar 04, 2024 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Magnus Egerstedt, Dean of Engineering, Professor | Department of Electrical Engineering and Computer Science | University of California, Irvine
Talk Title: Mutualistic interactions in heterogeneous multi-robot systems
Series: CSC/CommNetS-MHI Seminar Series
Abstract:
The typical approach to multi-robot systems is to divide the team-level tasks into suitable building blocks and have the robots solve their respective subtasks in a coordinated manner. However, by bringing together robots with different capabilities, it should be possible to arrive at completely new capabilities and skill-sets. In other words, the whole becomes greater than the sum of its parts. In this talk, we will formalize this idea through the composition of barrier functions for encoding the collaborative arrangements in terms of expanding and contracting the reachable and safe sets. Inspired by the ecological concept of a mutualism, i.e., the interaction between two or more species that benefit everyone involved, the formalism is contextualized in a long-duration setting, i.e., for robots deployed over long time scales where optimality have to take a backseat to "survivability".
Biography:
Dr. Magnus Egerstedt is the Dean of Engineering and a Professor in the Department of Electrical Engineering and Computer Science at the University of California, Irvine. Prior to joining UCI, Egerstedt was on the faculty at the Georgia Institute of Technology. He received the M.S. degree in Engineering Physics and the Ph.D. degree in Applied Mathematics from the Royal Institute of Technology, Stockholm, Sweden, the B.A. degree in Philosophy from Stockholm University, and was a Postdoctoral Scholar at Harvard University. Dr. Egerstedt conducts research in the areas of control theory and robotics, with particular focus on control and coordination of multi-robot systems. Magnus Egerstedt is a Fellow of IEEE and IFAC, a member of the Royal Swedish
Academy of Engineering Science, and currently serves as the President of the IEEE Control Systems Society. He has received a number of teaching and research awards, including the Ragazzini Award, the O. Hugo Schuck Best Paper Award, and the Alumni of the Year Award from the Royal Institute of Technology.
Host: Dr Lars Lindemann, llindema@usc.edu | Dr Mihailo Jovanovic, mihailo@usc.edu
More Info: https://csc.usc.edu/seminars/2024Spring/egerstedt.html
More Information: 2024.03.04 CSC Seminar - Magnus Egerstedt.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
Audiences: Everyone Is Invited
Contact: Miki Arlen
Event Link: https://csc.usc.edu/seminars/2024Spring/egerstedt.html
-
Intellisense Networking Event and Resume Review
Mon, Mar 04, 2024 @ 06:30 PM - 07:30 PM
USC Viterbi School of Engineering
Conferences, Lectures, & Seminars
Join WIE for an engaging session with Intellisense featuring accomplished engineers and recruiters! Students will be able to enjoy free burritos while getting their resumes reviewed individually by recruiters, learning about Intellisense, gaining insight from current engineers, and growing their network. Don't miss this chance to gain valuable insights from industry experts! Undergraduate and graduate students are welcome.
Location: Sign into EngageSC to View Location
Audiences: Everyone Is Invited
Contact: Thelma Federico Zaragoza
Event Link: https://engage.usc.edu/WIE/rsvp?id=396051
-
CS Colloquium: Angelina Wang (Princeton University) - Operationalizing Responsible Machine Learning: From Equality Towards Equity
Tue, Mar 05, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Angelina Wang, Princeton University
Talk Title: Operationalizing Responsible Machine Learning: From Equality Towards Equity
Abstract: With the widespread proliferation of machine learning, there arises both the opportunity for societal benefit as well as the risk of harm. Approaching responsible machine learning is challenging because technical approaches may prioritize a mathematical definition of fairness that correlates poorly to real-world constructs of fairness due to too many layers of abstraction. Conversely, social approaches that engage with prescriptive theories may produce findings that are too abstract to effectively translate into practice. In my research, I bridge these approaches and utilize social implications to guide technical work. I will discuss three research directions that show how, despite the technically convenient approach of considering equality acontextually, a stronger engagement with societal context allows us to operationalize a more equitable formulation. First, I will introduce a dataset tool that we developed to analyze complex, socially-grounded forms of visual bias. Then, I will provide empirical evidence to support how we should incorporate societal context in bringing intersectionality into machine learning. Finally, I will discuss how in the excitement of using LLMs for tasks like human participant replacement, we have neglected to consider the importance of human positionality. Overall, I will explore how we can expand a narrow focus on equality in responsible machine learning to encompass a broader understanding of equity that substantively engages with societal context.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Angelina Wang is a Computer Science PhD student at Princeton University advised by Olga Russakovsky. Her research is in the area of machine learning fairness and algorithmic bias. She has been recognized by the NSF GRFP, EECS Rising Stars, Siebel Scholarship, and Microsoft AI & Society Fellowship. She has published in top machine learning (ICML, AAAI), computer vision (ICCV, IJCV), interdisciplinary (Big Data & Society), and responsible computing (FAccT, JRC) venues, including spotlight and oral presentations. Previously, she has interned with Microsoft Research and Arthur AI, and received a B.S. in Electrical Engineering and Computer Science from UC Berkeley.
Host: Bistra Dilkina
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
Epstein Institute, ISE 651 Seminar Class
Tue, Mar 05, 2024 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Jing Dong, DeRosa Family Associate Professor of Business, Decision, Risk, and Operations Division, Columbia Business School
Talk Title: Stochastic Gradient Descent with Adaptive Data
Host: Dr. Renyuan Xu
More Information: March 5, 2024.pdf
Location: Social Sciences Building (SOS) - SOS Building, B2
Audiences: Everyone Is Invited
Contact: Grace Owh
-
CS Colloquium: Chang Xiao (Adobe Research) - Augmented Interaction Between Physical and Digital Realm
Wed, Mar 06, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Chang Xiao, Adobe Research
Talk Title: Augmented Interaction Between Physical and Digital Realm
Series: Computer Science Colloquium
Abstract: Today's computing devices, including mobile phones, wearable devices, and VR/AR headsets, have become increasingly powerful and accessible to almost everyone. They offer a direct and immersive interaction with digital worlds. But what if we could use these devices to access interactive physical worlds as well, expanding our interaction space and unlocking greater interactive potential? In this talk, I will discuss our work on integrating both physical and digital systems to create a new computing environment. Leveraging techniques from AI/ML, Computer Vision, and Computational Design, we propose several interactive systems and sensing techniques that provide users with unified, low-cost, tangible, and intuitive experiences. These approaches unlock the potential of using the physical environment as computer interfaces in the era of Extended Reality (XR) and spatial computing, bridging the gap between physical and digital spaces.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Chang Xiao is currently a Research Scientist at Adobe Research. He obtained his PhD from Columbia University in 2021. His broad interests lie at the intersection of HCI, AI/ML, and AR/VR, with a special focus on leveraging AI/ML to develop novel interaction and sensing techniques. His work has been published in a wide spectrum of top computer science venues, including CHI, UIST, SIGGRAPH, NeurIPS, CVPR, and ICLR. His research has gained impact beyond academia, having been successfully integrated into multiple Adobe products and receiving widespread attention, including media interviews and coverage by CNN, Adweek, CACM, and IEEE Spectrum. During his PhD studies, he received the Snap Research Fellowship and the Cheung-Kong Innovation Doctoral Fellowship.
Host: Heather Culbertson
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
AME Seminar
Wed, Mar 06, 2024 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Hannah Lu, MIT
Talk Title: Physics-Aware Data-Driven Modeling and Uncertainty Quantification for Large-Scale Environmental Problems
Abstract: Data-driven modeling of complex systems is a rapidly evolving field facilitated by the concurrent rise of data science. To alleviate the prohibitively expensive computational costs of repeated full-model simulations in uncertainty quantification, data-driven modeling is often used to describe the behaviors of the complex system by predicting the quantities of interest directly. In this talk, I will present my contributions to this field with an emphasis on (1) improving model performance by using physics-aware machine learning techniques, (2) quantifying uncertainties in the system’s response, and (3) inferring the key parameters of the physics-based models from measured data. Examples of applications will be focused on large-scale geological carbon sequestration—an important strategy for reducing greenhouse gas emissions to the atmosphere and mitigating climate change. The objective is to develop a convenient computing toolbox to provide more accurate scientific information at cheaper computational costs for better environmental management and decision-making.
Biography: Hannah Lu is a postdoc associate at MIT, affiliated with the Department of Aeronautics and Astronautics, Department of Civil Environmental Engineering, Earth Resources Laboratory and Laboratory for Information and Decision Systems. She obtained her Ph.D. from Energy Science and Engineering at Stanford Doerr School of Sustainability. Her research interests lie in the field of scientific computing, reduced order modeling, uncertainty quantification and machine learning in applications of environmental fluid mechanics. She received EDGE Doctoral Fellowship, Frank G. Miller Fellowship Award and Henry J. Ramey, Jr. Fellowship Award from Stanford University; Student Travel Award from SIAM Conference on UQ; NSF Fellowship from MMLDT-CSET Conference; Travel Grant from NSF-funded HydroML Symposium; and a first-place USNCCM17 Best Presentation Award in postdoc category.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Webcast: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09Location: James H. Zumberge Hall Of Science (ZHS) - 252
WebCast Link: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
CS Colloquium: Ben Lengerich (MIT) - Contextualized learning for adaptive yet persistent AI in biomedicine
Thu, Mar 07, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ben Lengerich, MIT
Talk Title: Contextualized learning for adaptive yet persistent AI in biomedicine
Series: Computer Science Colloquium
Abstract: Machine learning models often exhibit diminished generalizability when applied across diverse biomedical contexts (e.g., across health institutions), leading to a significant discrepancy between expected and actual performance. To address this challenge, this presentation introduces "contextualized learning", a meta-learning paradigm designed to enhance model adaptability by learning meta-relationships between dataset context and statistical parameters. Using network inference as an illustrative example, I will show how contextualized learning estimates context-specific graphical models, offering insights such as personalized gene expression analysis for cancer subtyping. The talk will also discuss trends towards “contextualized understanding”, bridging statistical and foundation models to standardize interpretability. The primary aim is to illustrate how contextualized learning and understanding contribute to creating learning systems that are both adaptive and persistent, facilitating cross-context information sharing and detailed analysis.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Ben Lengerich is a Postdoctoral Associate and Alana Fellow at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) and the Broad Institute of MIT and Harvard, where he is advised by Manolis Kellis. His research in machine learning and computational biology emphasizes the use of context-adaptive models to understand complex diseases and advance precision medicine. Through his work, Ben aims to bridge the gap between data-driven insights and actionable medical interventions. He holds a PhD in Computer Science and MS in Machine Learning from Carnegie Mellon University, where he was advised by Eric Xing. His work has been recognized with spotlight presentations at conferences including NeurIPS, ISMB, AMIA, and SMFM, financial support from the Alana Foundation, and recognition as a "Rising Star in Data Science” by the University of Chicago and UC San Diego.
Host: Willie Neiswanger
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
ECE Seminar: Sarah H. Cen
Thu, Mar 07, 2024 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Sarah H. Cen, EECS Dept, MIT
Talk Title: Paths to AI Accountability
Abstract: We have begun grappling with difficult questions related to the rise of AI, including: What rights do individuals have in the age of AI? When should we regulate AI and when should we abstain? What degree of transparency is needed to monitor AI systems? These questions are all concerned with AI accountability: determining who owes responsibility and to whom in the age of AI. In this talk, I will discuss the two main components of AI accountability, then illustrate them through a case study on social media. Within the context of social media, I will focus on how social media platforms filter (or curate) the content that users see. I will review several methods for auditing social media, drawing from concepts and tools in hypothesis testing, causal inference, and LLMs.
Biography: Sarah is a final-year PhD student at MIT in the Electrical Engineering and Computer Science Department advised by Professor Aleksander Madry and Professor Devavrat Shah. Sarah utilizes methods from machine learning, statistical inference, causal inference, and game theory to study responsible computing and AI policy. Previously, she has written about social media, trustworthy algorithms, algorithmic fairness, and more. She is currently interested in AI auditing, AI supply chains, and IP Law x Gen AI.
Host: Drs. Urbashi Mitra (ubli@usc.edu) and Mahdi Soltanolkotabi (soltanol@usc.edu)
Webcast: https://usc.zoom.us/j/97190024349?pwd=a0NTY2J5WjdKQUsvL3BtdTBSNGZTQT09Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
WebCast Link: https://usc.zoom.us/j/97190024349?pwd=a0NTY2J5WjdKQUsvL3BtdTBSNGZTQT09
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
NL Seminar - Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Thu, Mar 07, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Zixiang Chen, UCLA
Talk Title: Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Series: NL Seminar
Abstract: REMINDER: This talk will be a live presentation only, it will not be recorded. Meeting hosts only admit 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 provide your: Full Name, Title and Name of Workplace to (nlg-seminar-host(at)isi.edu) beforehand so we’ll be aware of your attendance. Also, let us know if you plan to attend in-person or virtually. More Info for NL Seminars can be found at: https://nlg.isi.edu/nl-seminar/. Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). In this talk, I will introduce our newest fine-tuning method, Self-Play Fine-Tuning (SPIN), which improves LLMs without the need for additional human-annotated data. SPIN utilizes a self-play mechanism, where the LLM enhances its capabilities by generating its own training data through interactions with instances of itself. Specifically, the LLM generates its own training data from its previous iterations, refining its policy by discerning these self-generated responses from those obtained from human-annotated data. As a result, SPIN unlocks the full potential of human-annotated data for SFT. Our empirical results show that SPIN can improve the LLM’s performance across a variety of benchmarks and even outperform models trained through direct preference optimization (DPO) supplemented with extra GPT-4 preference data. Additionally, I will outline the theoretical guarantees of our method. For more details and access to our codes, visit our GitHub repository (https://github.com/uclaml/SPIN).
Biography: Zixiang Chen is currently a Ph.D. student in computer science at the Department of Computer Science, University of California, Los Angeles (UCLA), advised by Prof. Quanquan Gu. He obtained his bachelor’s degree in mathematics from Tsinghua University. He is broadly interested in the theory and applications of deep learning, optimization, and control, with a focus on generative models, representation learning, and multi-agent reinforcement learning. Recently, he has been utilizing AI to enhance scientific discovery in the domain of public health. He was a visiting graduate student in the theory of reinforcement learning program at the Simons Institute for the Theory of Computing. If speaker approves to be recorded for this NL Seminar talk, it will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI. Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/
Host: Jon May and Justin Cho
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://youtu.be/Fg4C6YZcqQ4Location: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689
WebCast Link: https://youtu.be/Fg4C6YZcqQ4
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
Quantum Science & Technology Seminar - David Vitali - Friday, March 8th at 10am in EEB 248
Fri, Mar 08, 2024 @ 10:00 AM - 11:30 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: David Vitali, Univeristy of Camerino, Italy
Talk Title: Quantum Sensing and Quantum State Manipulation in Cavity Optomechanics
Series: Quantum Science & Technology Seminar Series
Abstract: Cavity Optomechanics offers the possibility to generate and manipulate quantum states of mesoscopic mechanical resonators allowing the realization of useful components of quantum networks, and at the same time testing fundamental aspects of physics theories. We will review recent proposals for generating multipartite entangled states of mechanical resonators and also their exploitation for quantum sensing of weak forces and signals.
Biography: David Vitali graduated in Physics at the University of Pisa in 1988 and obtained his PhD in Physics from the Scuola Normale Superiore of Pisa in 1994. He has been Visiting Lecturer at the University of North Texas (USA), at the Ecole Normale Superieure in Paris, at the University of Queensland , Brisbane (Australia), and at the University of Vienna. He is Full Professor of Theoretical Physics at the University of Camerino since 2015. He is the author of 193 publications in international refereed journals, with more than 10700 citations and Hirsch index h = 52 referring to the SCOPUS database. He has carried out research in many subfields of Quantum Optics and Quantum Information Theory, such as entanglement manipulation, quantum communication and quantum key distribution, quantum optics implementation of quantum technologies. In 2015 he was named APS Fellow of the American Physical Society, "For groundbreaking work on cavity opto-mechanics, which proved to provide an ideal and flexible environment for quantum information processing and quantum-limited sensing; for proposing pioneering techniques to control decoherence in quantum systems." In 2021 he was nominated OPTICA Senior Member, and he has coordinated various European projects and many National projects, all related to quantum technologies and quantum optomechanics.
Host: Quntao Zhang, Wade Hsu, Mengjie Yu, Jonathan Habif & Eli Levenson-Falk
More Information: David Vitali Seminar Flyer.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
ECE-S Seminar - Zhijian Liu
Fri, Mar 08, 2024 @ 10:30 AM - 11:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Zhijian Liu, PhD Candidate | Massachusetts Institute of Technology
Talk Title: Efficient Deep Learning with Sparsity: Algorithms, Systems, and Applications
Abstract: Machine learning is widely used across a broad spectrum of applications. However, behind its remarkable performance lies an increasing gap between the demand for and supply of computation. On the demand side, the computational costs of machine learning models have surged dramatically, driven by ever-larger input and model sizes. On the supply side, as Moore's Law slows down, hardware no longer delivers increasing performance within the same power budget.
In this talk, I will discuss my research efforts to bridge this demand-supply gap through the lens of sparsity. I will begin by discussing my research on input sparsity. First, I will introduce algorithms that systematically eliminate the least important patches/tokens from dense input data, such as images, enabling up to 60% sparsity without any loss in accuracy. Then, I will present the system library that we have developed to effectively translate the theoretical savings from sparsity to practical speedups on hardware. Our system is up to 3 times faster than the leading industry solution from NVIDIA. Following this, I will touch on my research on model sparsity, highlighting a family of automated, hardware-aware model compression frameworks that surpass manual solutions in accuracy and reduce the design process from weeks of human efforts to mere hours of GPU computation. Finally, I will present several examples demonstrating the use of sparsity to accelerate computation-intensive AI applications, such as autonomous driving, language modeling, and high-energy physics. I will conclude this talk with an overview of my ongoing work and my vision towards building more efficient and accessible AI.
Biography: Zhijian Liu is a Ph.D. candidate at MIT, advised by Song Han. His research focuses on efficient machine learning. He has developed efficient ML algorithms and provided them with effective system/algorithm support. He has also contributed to accelerating computation-intensive AI applications in computer vision, natural language processing, and scientific discovery. His work has been featured as oral and spotlight presentations at conferences such as NeurIPS, ICLR, and CVPR. He was selected as the recipient of the Qualcomm Innovation Fellowship and the NVIDIA Graduate Fellowship. He was also recognized as a Rising Star in ML and Systems by MLCommons and a Rising Star in Data Science by UChicago and UCSD. Previously, he was the founding research scientist at OmniML, which was acquired by NVIDIA.
Host: Mahdi Soltanolkotabi, soltanol@usc.edu | Peter Beerel, pabeerel@usc.edu
More Info: https://usc.zoom.us/j/96790337008?pwd=ZDljTkhHYjRQaUovUmJTSHZhR1ovUT09
Webcast: https://usc.zoom.us/j/96790337008?pwd=ZDljTkhHYjRQaUovUmJTSHZhR1ovUT09More Information: 2024.03.08 ECE Seminar - Zhijian Liu.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
WebCast Link: https://usc.zoom.us/j/96790337008?pwd=ZDljTkhHYjRQaUovUmJTSHZhR1ovUT09
Audiences: Everyone Is Invited
Contact: Miki Arlen
Event Link: https://usc.zoom.us/j/96790337008?pwd=ZDljTkhHYjRQaUovUmJTSHZhR1ovUT09
-
AI Seminar
Fri, Mar 08, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Yu-Ru Lin, Univ. of Pitt., Univ of Pitt
Talk Title: A Gateway to Trustworthy AI: Using Visual Analytics to Unmask Coincidental Correlations
Abstract: Join Zoom Meeting https://usc.zoom.us/s/99782858348?pwd=MnlSdGlTVWNETGFFbDQ4OWRmakdEQT09 Meeting ID: 997 8285 8348 Passcode: 580559 Register in advance for this webinar: https://usc.zoom.us/webinar/register/WN_xxYy3NkSQpidFYRY3fg_Ew In the realm of machine learning and data-driven decision-making, the risk of spurious and biased associations poses significant challenges to the integrity and reliability of AI systems. In this talk, I will introduce how visual analytic designs can empower data practitioners in navigating these complex issues. First, through a human-in-the-loop workflow, we tackle the problem of AI blindspots in classification models, where key patterns are often missed or misleading. Our design offers visually interpretable statistical methods to quantify and understand concept associations. It also includes debiasing techniques to address misleading patterns in data. Second, we tackle Simpson’s Paradox, a phenomenon where associations in data appear contradictory at different levels of aggregation, leading to cognitive confusion and incorrect interpretations. Our design offers an intuitive causal analysis framework and a human-centric workflow, enabling users to identify, understand, and prevent spurious associations, leading to more accountable causal decision-making. Together, these design frameworks contribute to making AI more trustworthy, offering robust tools for overcoming the challenges of spurious and biased associations in machine learning through advanced visual analytics.
Biography: Website: http://www.yurulin.com/ Yu-Ru Lin is an Associate Professor in the School of Computing and Information and the Research Director of the Institute for Cyber Law, Policy, and Security (Pitt Cyber) at the University of Pittsburgh, where she directs the PITT Computational Social Dynamics Lab (PICSO LAB). Her research lies at the intersection of Computational Social Science, Data Mining, and Visualization. She specializes in using social network and text data along with statistical learning tools and social theories to study phenomena spanning societal events and policy, anomalous behaviors, and other crucially important complex patterns concerning collective attention and actions, as well as human and social dynamics in response to societal risks. Her work has appeared in prestigious scientific venues and has been featured in the press, including WSJ, The Boston Globe, The Atlantic, MIT News, and NPR. She has authored or co-authored more than 100 refereed journal and conference papers and served on more than 50 conference program committees in the areas of big data, network science, and computational social science. She has served as a chair/co-chair of leading computational social science, web mining, and social media conferences such as AAAI ICWSM and TheWebConference/WWW (Web & Society Track). She currently serves as an Editor-in-Chief of AAAI ICWSM and an Associate Editor for multiple journals, including PLOS ONE, Springer EPJ Data Science, Nature's Scientific Reports, and Frontiers in Big Data. She was selected as a Fellow of Kavli Frontiers of Science, National Academy of Sciences (NAS).
Host: Fred Morstatter and Zhuoyu Shi
More Info: https://www.isi.edu/events/4389/ai-seminar-a-gateway-to-trustworthy-ai-using-visual-analytics-to-unmask-coincidental-correlations/
Webcast: https://www.youtube.com/watch?v=2uZOOM6-nooLocation: Information Science Institute (ISI) - Virtual Only
WebCast Link: https://www.youtube.com/watch?v=2uZOOM6-noo
Audiences: Everyone Is Invited
Contact: Pete Zamar
-
**No Epstein Institute, ISE 651 Seminar Class - Spring Recess**
Tue, Mar 12, 2024 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Talk Title: **NO SEMINAR - SPRING RECESS**
Location: Social Sciences Building (SOS) - SOS Building, B2
Audiences: Everyone Is Invited
Contact: Grace Owh
-
Alfred E. Mann Department of Biomedical Engineering
Wed, Mar 13, 2024 @ 11:00 AM - 12:00 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Ishwar K. Puri, Professor of Aerospace and Mechanical Engineering
Talk Title: Playing with Magnets
Abstract: Control over coalescing particles as they interact, grow, and form patterns leads to a wide array of life science and nanotechnology applications. We consider engineered clusters, such as annuli, spheroids, and organoids, that better mimic in vitro physiological constructs than 1D monolayer structures. Here, we describe a macroscale contactless and label-free field-guided magnetic method that prints in-situ three-dimensional particle assemblies of different morphologies and sizes using non-adherent cells (RBCs) and adherent cells, such as MCF-7, over relatively short timespans. Potential applications of the method include biosensing, high-throughput drug testing, and other patient-specific treatments.
Biography: Ishwar K. Puri is professor of aerospace and mechanical engineering at the University of Southern California. He is a fellow of the Canadian Academy of Engineering, the American Association for the Advancement of Science and the American Society of Mechanical Engineers, and holds the Engineering Medal for Engineering Excellence awarded by Professional Engineers Ontario and the Ontario Society of Professional Engineers. Puri is the author of over 200 archival publications and books that have been cited over 9,400 times per Google Scholar with an H-Index of 54, and is ranked among the top 2% of scientists in the world based on the citations publications between 1965-2019. He has founded and mentored startups. He also oversees the USC Office of Research and Innovation that guides the university’s research programs.
Host: Peter Wang
Location: Michelson Center for Convergent Bioscience (MCB) - 102
Audiences: Everyone Is Invited
Contact: Carla Stanard
-
Munushian Distinguished Lecture - George Malliaras, Friday, March 15th at 3pm in EEB 132
Fri, Mar 15, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: George Malliaras, University of Cambridge
Talk Title: Technology for Bioelectronic Medicine
Series: Munushian Visiting Seminar Series
Abstract: Neurological conditions affect one in six people, imposing significant health, economic and societal burden. Bioelectronic medicine aims to restore or replace neurological function with the help of implantable electronic devices. Unfortunately, significant technological limitations prohibit these devices from reaching patients at scale, as implants are bulky, require invasive implantation procedures, elicit a pronounced foreign body response, and show poor treatment specificity and off-target effects. Over the past decade, new devices made using methods from microelectronics industry have been shown to overcome these limitations. Recent literature provides powerful demonstrations of thin film implants that are miniaturised, ultra-conformal, stretchable, multiplexed, integrated with different sensors and actuators, bioresorbable, and minimally invasive. I will discuss the state-of-the-art of these new technologies and the barriers than need to be overcome to reach patients at scale.
Biography: George Malliaras is the Prince Philip Professor of Technology at the University of Cambridge. He leads the Bioelectronics Laboratory, an interdisciplinary group of scientists, engineers and clinicians who translate advances in electronics to better tools for healthcare. George received a BS from the Aristotle University, Greece, a PhD from the University of Groningen, the Netherlands, and did a postdoc at the IBM Almaden Research Center, USA. Before joining Cambridge, he was a faculty member at Cornell University in the USA, where he also served as the Director of the Cornell NanoScale Facility, and at the School of Mines of St. Etienne in France. His research has been recognized with awards from the European Academy of Sciences (Blaise Pascal Medal), the Materials Research Society (Mid-Career Researcher Award), the New York Academy of Sciences (Blavatnik Award for Young Scientists), the US National Science Foundation (Faculty Early Career Development Award), and DuPont (Young Professor Award). He was awarded an Honorary Doctorate from the University of Linköping (Sweden), elected Fellow of the Materials Research Society and of the Royal Society of Chemistry, and is a member of the Academia Europaea and of the European Academy of Sciences. He serves as a Deputy Editor of Science Advances.
Host: ECE-Electrophysics
More Information: George Malliaras Flyer.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
CS Colloquium: TBA
Mon, Mar 18, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: TBA, TBA
Talk Title: TBA
Series: Computer Science Colloquium
Host: Heather Culbertson
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
ECE Seminar: Marcelo Orenes-Vera, "Navigating Heterogeneity and Scalability in Modern Chip Design"
Mon, Mar 18, 2024 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Marcelo Orenes-Vera, PhD Candidate, Dept of CS, Princeton University
Talk Title: Navigating Heterogeneity and Scalability in Modern Chip Design
Abstract: Abstract: The pursuit of continued improvements in performance and energy efficiency, following the end of Moore's Law and Dennard scaling, marks a pivotal moment in system architecture. As modern systems leverage parallelism and hardware specialization to achieve these goals, new challenges arise:
(1) The complexity of the system grows with the number of distinct hardware components, making it difficult to verify that it will behave correctly and securely;
(2) Parallelizing applications across more processing elements increases the pressure on the memory hierarchy and the network to supply data, which results in severe bottlenecks for data-and communication-intensive applications such as graph analytics and sparse linear algebra.
These challenges call for re-thinking our software abstractions and hardware designs to achieve scalable and efficient systems, as well as introducing robust methodologies to ensure their correctness and security. This talk presents my work on scalable data-centric architectures that co-design the hardware with a migrate-compute-to-the-data programming model to outperform the best results from the Graph500 list. Moreover, this architecture offers a chiplet-based design that enables post-silicon re-configuration of critical resources like the memory hierarchy or network-on-chip for a cost-efficient integration based on different deployment targets. In addition, this talk also introduces two formal-verification-based tools that assist the design of verifiably correct and secure hardware RTL by leveraging high-level abstraction primitives. In addition to facilitating the design process, my verification work also identified and fixed security vulnerabilities and correctness bugs in widely used open-source hardware projects.
Biography: Marcelo is a PhD candidate at Princeton University advised by Margaret Martonosi and David Wentzlaff. His research focuses on Computer Architecture, from hardware RTL design and verification to software programming models of novel architectures. He has previously worked in the hardware industry at Arm, contributing to the design and verification of three GPU projects; at Cerebras Systems, creating high-performance kernels for the Wafer-Scale Engine; and at AMD Research, contributing to design next-generation data centers optimized for large graph structure traversal. At Princeton, he has contributed in two chip tapeouts that aims to improve the performance, power and programmability of ML and Graph workloads. His contributions to scalable data-centric architectures were recognized with the gold medal at the ACM/SIGMICRO 2022 SRC and with an honorable mention at the IEEE Top Picks of 2023.
Host: Dr. Massoud Pedram, pedram@usc.edu
Webcast: https://usc.zoom.us/j/98003769115?pwd=Sm5JU2RUN1N4Qnd6UkZSOTFEdFpzZz09Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
WebCast Link: https://usc.zoom.us/j/98003769115?pwd=Sm5JU2RUN1N4Qnd6UkZSOTFEdFpzZz09
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
NL Seminar-Do Androids Know They're Only Dreaming of Electric Sheep?
Mon, Mar 18, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Sky Wang, Columbia University
Talk Title: Do Androids Know They're Only Dreaming of Electric Sheep?
Series: NL Seminar
Abstract: REMINDER: This talk will be a live presentation only, it will not be recorded. Meeting hosts only admit 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 provide your: Full Name, Title and Name of Workplace to (nlg-seminar-host(at)isi.edu) beforehand so we’ll be aware of your attendance. Also, let us know if you plan to attend in-person or virtually. More Info for NL Seminars can be found at: https://nlg.isi.edu/nl-seminar/ We design probes trained on the internal representations of a transformer language model that are predictive of its hallucinatory behavior on in-context generation tasks. To facilitate this detection, we create a span-annotated dataset of organic and synthetic hallucinations over several tasks. We find that probes trained on the force-decoded states of synthetic hallucinations are generally ecologically invalid in organic hallucination detection. Furthermore, hidden state information about hallucination appears to be task and distribution-dependent. Intrinsic and extrinsic hallucination saliency varies across layers, hidden state types, and tasks; notably, extrinsic hallucinations tend to be more salient in a transformer's internal representations. Outperforming multiple contemporary baselines, we show that probing is a feasible and efficient alternative to language model hallucination evaluation when model states are available.
Biography: If speaker approves to be recorded for this NL Seminar talk, it will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI. Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/ Sky is a Ph.D. candidate in Computer Science at Columbia University advised by Zhou Yu and Smaranda Muresan. His research primarily revolves around Natural Language Processing (NLP), with broad interests in the area where NLP meets Computational Social Science (CSS). Here, his research primarily revolves around three major areas: (1) revealing and designing for social difference and inequality, (2) cross-cultural NLP, and (3) mechanistic interpretability. His research is supported by a NSF Graduate Research Fellowship and has received two outstanding paper awards at EMNLP. He has previously been an intern at Microsoft Semantic Machines, Google Research, and Amazon AWS AI.
Host: Jon May and Justin Cho
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://www.youtube.com/watch?v=Pm0ljFMg0cwLocation: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=Pm0ljFMg0cw
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
Machine Learning Center Seminar: Lily Weng (UC San Diego) - Towards Interpretable Deep Learning
Mon, Mar 18, 2024 @ 12:00 PM - 01:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Lily Weng, UC San Diego
Talk Title: Towards Interpretable Deep Learning
Series: Machine Learning Center Seminar Series
Abstract: Deep neural networks (DNNs) have achieved unprecedented success across many scientific and engineering fields in the last decades. Despite its empirical success, however, they are notoriously black-box models that are difficult to understand their decision process. Lacking interpretability is one critical issue that may seriously hinder the deployment of DNNs in high-stake applications, which need interpretability to trust the prediction, to understand potential failures, and to be able to mitigate harms and eliminate biases in the model.
In this talk, I'll share some exciting results in my lab on advancing explainable AI and interpretable machine learning. Specifically, I will show how we could bring interpretability into deep learning by leveraging recent advances in multi-modal models. I'll present two recent works [1,2] in our group on demystifying neural networks and interpretability-guided neural network design, which are the important first steps to enable Trustworthy AI and Trustworthy Machine Learning. I will also briefly overview our other recent efforts on Trustworthy Machine Learning and automated explanations for LLMs [3].
[1] Oikarinen and Weng, CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks, ICLR 23 (spotlight)
[2] Oikarinen, Das, Nguyen and Weng, Label-Free Concept Bottleneck Models, ICLR 23
[3] Lee, Oikarinen etal, The Importance of Prompt Tuning for Automated Neuron Explanations, NeurIPS 23 ATTRIB workshop
Biography: Lily Weng is an Assistant Professor in the Halicioglu Data Science Institute at UC San Diego. She received her PhD in Electrical Engineering and Computer Sciences (EECS) from MIT in August 2020, and her Bachelor and Master degree both in Electrical Engineering at National Taiwan University. Prior to UCSD, she spent 1 year in MIT-IBM Watson AI Lab and several research internships in Google DeepMind, IBM Research and Mitsubishi Electric Research Lab. Her research interest is in machine learning and deep learning, with primary focus on trustworthy AI. Her vision is to make the next generation AI systems and deep learning algorithms more robust, reliable, explainable, trustworthy and safer. For more details, please see https://lilywenglab.github.io/.
Host: Yan Liu
Location: Ronald Tutor Hall of Engineering (RTH) - 306
Audiences: Everyone Is Invited
Contact: CS Events
-
AME Seminar
Mon, Mar 18, 2024 @ 01:30 PM - 02:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Rachel Holladay, MIT
Talk Title: Dexterous Decision-Making for Real-World Robotic Manipulation
Abstract: For a robot to prepare a meal or clean a room, it must make a large array of decisions, such as what objects to clean first, where to grasp each ingredient and tool, how to open a heavy, overstuffed cabinet, and so on. To enable robots to tackle these tasks, I decompose the problem into two interdependent layers: generating a series of subgoals (i.e., a strategy) and solving for the robot behavior that achieves each of these subgoals. Critically, to accomplish a rich set of manipulation tasks, these subgoal solvers must account for force, motion, deformation, contact, uncertainty and partial observability.My research contributes models and algorithms that enable robots to reason over both the geometry and physics of the world in order to solve long-horizon manipulation tasks. In this talk, I will first discuss how this approach has enabled robots to perform tasks that require reasoning over and exerting force, like opening a childproof medicine bottle with a single arm. Next, I will present an abstraction for the complex physics of frictional pushing and demonstrate its application within the context of in-hand manipulation. Finally, I will illustrate how robots can make robust choices in the face of uncertainty. For example, this empowers robots to reliably chop up fruit of unknown ripeness!
Biography: Rachel Holladay is a Ph.D. student in the Electrical Engineering and Computer Science Department at the Massachusetts Institute of Technology. Her research focuses on developing algorithms and models that enable robots to robustly perform long-horizon, contact-rich manipulation tasks in everyday environments. She received her B.S. in Computer Science and Robotics from Carnegie Mellon University.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Webcast: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09Location: Olin Hall of Engineering (OHE) - 406
WebCast Link: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
CSC/CommNetS-MHI Seminar: Nickolay Atanasov
Mon, Mar 18, 2024 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Nickolay Atanasov, Assistant Professor of Electrical and Computer Engineering | University of California, San Diego
Talk Title: Elements of generalizable mobile robot autonomy
Abstract: This seminar will discuss mobile robot autonomy in novel, unstructured, changing environments. It will argue that successful generalization requires motion, environment, and task models that can be constructed and adapted from streaming sensor observations and interaction among multiple robots. Four elements of generalizable mobile robot autonomy will be presented: 1) physics-informed motion-model learning using neural ordinary differential equations, 2) online mapping using object and semantic information, 3) multi-robot coordination using distributed optimization, and 4) task modeling and planning using automata labeled with object semantics.
Biography: Nikolay Atanasov is an Assistant Professor of Electrical and Computer Engineering at the University of California San Diego, La Jolla, CA, USA. He obtained a B.S. degree in Electrical Engineering from Trinity College, Hartford, CT, USA in 2008, and M.S. and Ph.D. degrees in Electrical and Systems Engineering from University of Pennsylvania, Philadelphia, PA, USA in 2012 and 2015, respectively. Dr. Atanasov's research focuses on robotics, control theory, and machine learning with emphasis on active perception problems for autonomous mobile robots. He works on probabilistic models and inference techniques for simultaneous localization and mapping (SLAM) and on optimal control and reinforcement learning techniques for autonomous navigation and uncertainty minimization. Dr. Atanasov's work has been recognized by the Joseph and Rosaline Wolf award for the best Ph.D. dissertation in Electrical and Systems Engineering at the University of Pennsylvania in 2015, the Best Conference Paper Award at the IEEE International Conference on Robotics and Automation (ICRA) in 2017, the NSF CAREER Award in 2021, and the IEEE RAS Early Academic Career Award in Robotics and Automation in 2023.
Host: Dr. Lars Lindemann, llindema@usc.edu
More Info: https://csc.usc.edu/seminars/2024Spring/atanasov.html
More Information: 2024.03.18 CSC Seminar - Nikolay Atanasov.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
Audiences: Everyone Is Invited
Contact: Miki Arlen
Event Link: https://csc.usc.edu/seminars/2024Spring/atanasov.html
-
CS Colloquium: Sherry Yang - Decision Making with Internet-Scale Knowledge
Tue, Mar 19, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Sherry Yang, UC Berkeley
Talk Title: Decision Making with Internet-Scale Knowledge
Abstract: Machine learning models pretrained on internet data have acquired broad knowledge about the world but struggle to solve complex tasks that require extended reasoning and planning. Sequential decision making, on the other hand, has empowered AlphaGo’s superhuman performance, but lacks visual, language, and physical knowledge about the world. In this talk, I will present my research towards enabling decision making with internet-scale knowledge. First, I will illustrate how language models and video generation are unified interfaces that can integrate internet knowledge and represent diverse tasks, enabling the creation of a generative simulator to support real-world decision-making. Second, I will discuss my work on designing decision making algorithms that can take advantage of generative language and video models as agents and environments. Combining pretrained models with decision making algorithms can effectively enable a wide range of applications such as developing chatbots, learning robot policies, and discovering novel materials. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Sherry is a final year PhD student at UC Berkeley advised by Pieter Abbeel and a senior research scientist at Google DeepMind. Her research aims to develop machine learning models with internet-scale knowledge to make better-than-human decisions. To this end, she has developed techniques for generative modeling and representation learning from large-scale vision, language, and structured data, coupled with developing algorithms for sequential decision making such as imitation learning, planning, and reinforcement learning. Sherry initiated and led the Foundation Models for Decision Making workshop at NeurIPS 2022 and 2023, bringing together research communities in vision, language, planning, and reinforcement learning to solve complex decision making tasks at scale. Before her current role, Sherry received her Bachelor’s degree and Master’s degree from MIT advised by Patrick Winston and Julian Shun.
Host: Dani Yogatama
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
Alfred E. Mann Department of Biomedical Engineering
Tue, Mar 19, 2024 @ 11:00 AM - 12:00 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Wilson Wong, Ph.D., Associate Professor of Biomedical Engineering an Allen Distinguished Investigator
Talk Title: Engineering Vaccines, Cell and GeneTherapies using Synthetic Biology
Abstract: In this seminar, I will share with you some of the work that my trainees and colleagues have done on using synthetic biology in various areas, such as foundational circuit engineering, cellular immunotherapy, and vaccines. I will discuss our work on improving the specificity and safety of CAR T cell therapy against cancer using synthetic biology and biomaterials. I will also share our recent discovery on engineering self-amplifying RNA with reduced innate immune response and improved protein expression, leading to a highly potent COVID-19 vaccine as demonstrated in a lethal live virus challenge in mice.
Biography: Dr. Wilson Wong is an Associate Professor of Biomedical Engineering and an Allen Distinguished Investigator at Boston University. He is an expert in immune cell engineering and synthetic biology for therapeutic applications. Dr. Wong’s research has been published in numerous high-impact journals, including Nature, Nature Biotechnology, Cell, and PNAS. Dr. Wong has been recognized with multiple academic career awards, including the NIH New Innovator Award, the ACS Synthetic Biology Young Investigator Award, the NSF CAREER Award, and the Allen Distinguished Investigator Award. He has co-founded three companies, with one in the clinical stage. Dr. Wong has a BS in Chemical Engineering from the University of California, Berkeley, and a PhD in Chemical and Biomolecular Engineering from the University of California, Los Angeles. Dr. Wong completed his postdoctoral studies in the laboratory of Professor Wendell Lim at the University of California, San Francisco.
Host: Peter Wang
Location: Corwin D. Denney Research Center (DRB) - 145
Audiences: Everyone Is Invited
Contact: Carla Stanard
-
ECE-S Seminar - Dr. Peipei Zhou
Tue, Mar 19, 2024 @ 01:00 PM - 02:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Peipei Zhou, Assistant Professor | Department of Electrical Computer Engineering | University of Pittsburgh
Talk Title: Efficient Programming on Heterogeneous Accelerators for Sustainable Computing
Abstract: There is a growing call for increasingly agile computational power for edge and cloud infrastructure to serve the computationally complex needs of ubiquitous computing devices. One important challenge is addressing the holistic environmental impacts of these computing systems. A life-cycle view of sustainability for computing systems is necessary to reduce environmental impacts such as greenhouse gas emissions from these computing systems in different phases: manufacturing, operational, and disposal/recycling. My research investigates how to efficiently program and map widely used workloads on heterogeneous accelerators and seamlessly integrate them with existing computing systems towards sustainable computing.
In this talk, I will first discuss how new mapping solutions, i.e., composing heterogeneous accelerators within system-on-chip with both FPGAs and AI tensor cores, achieve orders of magnitude energy efficiency gains when compared to monolithic accelerator mapping designs for various applications, including deep learning, security, and others. Then, I will apply such novel mapping solutions to show how design space explorations are performed when composing heterogeneous accelerators in latency-through tradeoff analysis. I will further discuss how such mapping and scheduling can be applied to other computing systems, such as GPUs, to improve energy efficiency and, therefore, reduce the operational carbon cost. Finally, I will introduce the REFRESH FPGA chiplets, explain why REFRESH chiplets help reduce the embodied carbon cost, and discuss the challenges and opportunities.
Biography: Peipei Zhou is a tenure-track assistant professor in the Department of Electrical Computer Engineering at the University of Pittsburgh. She received her Ph.D. in Computer Science (2019) and M.S. in Electrical and Computer Engineering (2014) from UCLA, and her B.S. in Electrical and Computer Engineering (2012) from Southeast University. Her research investigates architecture, programming abstraction, and design automation tools for reconfigurable computing and heterogeneous computing. She has published 30 papers in IEEE/ACM computer system and design automation conferences and journals including FPGA, FCCM, DAC, ICCAD, ISPASS, TCAD, TODAES, TECS, IEEE Micro, etc. Her work has won the 2019 IEEE TCAD Donald O. Pederson Best Paper Award. Other awards include the 2023 ACM/IEEE IGSC Best Viewpoint Paper Finalist, the 2018 IEEE ISPASS Best Paper Nominee, and the 2018 IEEE/ACM ICCAD Best Paper Nominee.
Host: Dr. Peter Beerel, pabeerel@usc.edu
More Info: https://usc.zoom.us/j/92387554175?pwd=ZmFRL0NnZE1sLy82dzBiSXYzbUFVdz09
Webcast: https://usc.zoom.us/j/92387554175?pwd=ZmFRL0NnZE1sLy82dzBiSXYzbUFVdz09More Information: 2024.03.19 ECE-S Seminar - Peipei Zhou.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
WebCast Link: https://usc.zoom.us/j/92387554175?pwd=ZmFRL0NnZE1sLy82dzBiSXYzbUFVdz09
Audiences: Everyone Is Invited
Contact: Miki Arlen
Event Link: https://usc.zoom.us/j/92387554175?pwd=ZmFRL0NnZE1sLy82dzBiSXYzbUFVdz09
-
ECE-EP Seminar - Yue (Joyce) Jiang, Tuesday, March 19th at 2pm in EEB 248
Tue, Mar 19, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Yue (Joyce) Jiang, JILA, University of Colorado Boulder
Talk Title: Exploring Quantum Harmony between Superconducting Circuits & Cold Atoms
Series: ECE-EP Seminar
Abstract: Join me in this talk as I share my research journey in quantum information science, transitioning from cold atoms to superconducting circuits and exploring their harmonious collaboration in advancing quantum science and technology. In the first part, I will discuss the demonstration of a quantum-enhanced sensing technique at microwave frequencies using superconducting circuits to accelerate the search for weak signals arising from physics beyond the Standard Model, with a specific focus on axion dark matter searches. Shifting gears in the second part, we will delve into quantum optics experiments that utilize the nonlinear interaction between the cold atomic ensemble and optical photons, unveiling the fascinating realm of non- Hermitian quantum optics. Wrapping up, we will explore the exciting science that leverages the strengths of both systems, utilizing superconducting-atomic hybrid systems to bridge the gap between quantum information science in microwave and optical frequencies.
Biography: Yue (Joyce) Jiang is a postdoctoral research associate at JILA. She earned her Ph.D. in Physics from the Hong Kong University of Science and Technology under the guidance of Prof. Shengwang Du in 2020, focusing on studying the nonlinear interaction between photons and laser-cooled atomic ensembles. Currently at JILA, she works with Prof. Konrad Lehnert on developing quantum-enhanced sensing techniques for weak signal detection using superconducting circuits.
Host: ECE-EP
Webcast: https://usc.zoom.us/j/93212540080?pwd=ODI5cXJ2N0RQQW9CNE9MQW5Ea3A0dz09More Information: Yue (Joyce) Jiang Seminar Announcement.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
WebCast Link: https://usc.zoom.us/j/93212540080?pwd=ODI5cXJ2N0RQQW9CNE9MQW5Ea3A0dz09
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
Epstein Institute, ISE 651 Seminar Class
Tue, Mar 19, 2024 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Gokce Dayanikli, Assistant Professor, Department of Statistics, University of Illinois Urbana-Champaign
Talk Title: Finding Optimal Policies for Large Populations: An Application to Epidemic Control
Host: Dr. Renyuan Xu
More Information: March 19, 2024.pdf
Location: Social Sciences Building (SOS) - SOS Building, B2
Audiences: Everyone Is Invited
Contact: Grace Owh
-
CS Colloquium: Mengyuan Li - Confidential Computing and Trusted Execution Environment: Challenges, Opportunities, and the Future
Wed, Mar 20, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Mengyuan Li, MIT
Talk Title: Confidential Computing and Trusted Execution Environment: Challenges, Opportunities, and the Future
Abstract: Confidential Computing, or Trusted Execution Environment (TEE), represents a cutting-edge design in server-grade CPUs. This technology acts as a protective shield for cloud tasks, safeguarding the confidentiality and integrity of cloud workloads against a range of threats, including attacks from privileged software, physical attackers, and untrustworthy hypervisors. As the demand for secure private data handling continues to rise, the adoption of Confidential Computing has become widespread across various industries. Evidence of this includes the adoption of TEE in server-grade CPUs from major vendors like Intel, AMD, and ARM. Furthermore, leading cloud service providers, such as AWS, Google Cloud, Microsoft Azure, and IBM Cloud, now offer commercial Confidential Computing services. In this talk, I will outline my contributions to the study of complex, heterogeneous Confidential Computing systems. I will share my insights into two real-world vulnerabilities we uncovered within commercial Confidential Computing systems, along with our joint efforts with CPU manufacturers to address these issues in the latest server-grade CPUs. At the hardware design level, I will discuss a novel ciphertext side-channel attack targeting hardware-accelerated memory encryption, which is a crucial hardware feature to protect the memory of cloud workloads. Moving to the software system design level, I will illustrate how inadequately designed TEE operating systems can pose a threat to the security of Confidential VMs. Finally, I will outline my ongoing efforts and future directions in enhancing the security and effectiveness of Confidential Computing and my research vision towards building secure and performant hardware systems. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Mengyuan Li is a postdoctoral researcher at CSAIL, MIT, under the guidance of Prof. Mengjia Yan. His research focuses on bringing security and trust to hardware systems, with a recent concentration in Confidential Cloud Computing and Trusted Execution Environments. To this end, he has identified real-world hardware vulnerabilities in commodity CPUs, which have been acknowledged by manufacturers through hardware CVEs and several security bulletins. Additionally, he has collaborated closely with industry teams such as AMD, Intel, WolfSSL, and Alibaba Cloud to develop mitigations and design commercial trustworthy hardware systems. His research findings have been published in top security and privacy venues, including S&P, Usenix Security, and CCS, and have been recognized by the CCS 2021 Best Paper Runner-up Award. Before MIT, Mengyuan earned his Ph.D. in Computer Science and Engineering from The Ohio State University (OSU) in 2022.
Host: Seo Jin Park
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
AME Seminar
Wed, Mar 20, 2024 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Pedro Saenz, University of North Carolina at Chapel Hill
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Webcast: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09Location: James H. Zumberge Hall Of Science (ZHS) - 252
WebCast Link: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
CS Colloquium: Andrew Ilyas - Making machine learning predictably reliable
Thu, Mar 21, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Andrew Ilyas, MIT
Talk Title: Making machine learning predictably reliable
Abstract: Despite ML models' impressive performance, training and deploying them is currently a somewhat messy endeavor. But does it have to be? In this talk, I overview my work on making ML “predictably reliable”---enabling developers to know when their models will work, when they will fail, and why.To begin, we use a case study of adversarial inputs to show that human intuition can be a poor predictor of how ML models operate. Motivated by this, we present a line of work that aims to develop a precise understanding of the ML pipeline, combining statistical tools with large-scale experiments to characterize the role of each individual design choice: from how to collect data, to what dataset to train on, to what learning algorithm to use. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Andrew Ilyas is a PhD student in Computer Science at MIT, where he is advised by Aleksander Madry and Constantinos Daskalakis. His research aims to improve the reliability and predictability of machine learning systems. He was previously supported by an Open Philanthropy AI Fellowship.
Host: Vatsal Sharan
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
NL Seminar -The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI
Thu, Mar 21, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Anthony Chen and Shayne Longpre, MIT
Talk Title: The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI
Abstract: REMINDER: This talk will be a live presentation only, it will not be recorded. Meeting hosts only admit 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 provide your: Full Name, Title and Name of Workplace to (nlg-seminar-host(at)isi.edu) beforehand so we’ll be aware of your attendance. Also, let us know if you plan to attend in-person or virtually. More Info for NL Seminars can be found at: https://nlg.isi.edu/nl-seminar/ The arms race to train language models on vast, diverse, and inconsistently documented datasets has raised pressing concerns about the legal and ethical risks for practitioners. To remedy these practices threatening data transparency and understanding, we introduce the Data Provenance Initiative, a multi-disciplinary effort between legal and machine learning experts to systematically audit and trace 1800+ text datasets. We develop tools and standards to trace the lineage of these datasets, from their source, creators, series of license conditions, properties, and subsequent use. Our landscape analysis highlights the sharp divides in composition and focus of commercially open vs closed datasets, with closed datasets monopolizing important categories: lower resource languages, more creative tasks, richer topic variety, newer and more synthetic training data.
Biography: Bio 1:Anthony Chen is an engineer at Google DeepMind doing research on factuality and long-context language models. He received his PhD from UC Irvine last year where he focused on generative evaluation and factuality in language models. Bio 2: Shayne Longpre is a PhD candidate at MIT with a focus on data-centric AI, language models, and their societal impact. If speakers approve to be recorded for this NL Seminar talk, it will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI. Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/
Host: Jon May and Justin Cho
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://www.youtube.com/watch?v=np9HeJN6miwLocation: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=np9HeJN6miw
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
USC SleepHuB Special Seminar
Thu, Mar 21, 2024 @ 12:00 PM - 01:00 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Rebecca Spencer, Ph.D., Professor of Psychological and Brain Sciences and Director of the Sleep Lab Core Facility -University of Massachusetts at Amherst
Talk Title: Cognitive benefits of sleep in spite of sleep loss in older adults
Abstract: Sleep benefits memory consolidation in young adults. Evidence suggests that this benefit reflects the active reorganization of memories, moving them from short-term hippocampal storage which is susceptible to interference to long-term more stable storage in the neocortex. Synchronized oscillations in the hippocampus and neocortex during slow wave sleep underlie this memory stabilization. Older adults have reduced slow wave sleep and yet, in many cases, sleep-dependent memory consolidation is preserved. It is important to understand this resilience as it may speak to ways to prevent or intervene in age-related memory loss. In my talk, I will present studies demonstrating the benefits of sleep on memories in older adults as well as the limitations of this process. I will also present some evidence of possible mechanisms supporting memory consolidation in the face of reduced slow wave sleep with aging. These studies hold relevance for those studying aging from a clinical and cognitive perspective.
Biography: Rebecca Spencer, Ph.D., is Professor of Psychological and Brain Sciences and Director of the Sleep Lab Core Facility in the Institute of Applied Life Sciences at the University of Massachusetts, Amherst. Her research focuses on the role of sleep in cognition and brain changes, specifically lifespan changes in sleep-dependent cognitive processing. In young children, she is interested in how the high levels of sleep during development relate to the massive amount of learning and brain development at this age. In old adults, she studies how age-related changes in sleep contribute to changes in memory and emotion processing. After graduating from Purdue with a PhD in neuroscience in 2002, she went to UC Berkeley where she was a postdoctoral fellow and research scientist in the Helen Wills Neuroscience Institute until 2008. She was the recipient of a NIH Pathways to Independence Award (K99/R00). Her work is currently funded by 3 NIH R01 awards and an NSF grant. She chairs the Associated Professional Sleep Societies (APSS) Program Committee.
Host: Dr. Michael Khoo
Location: Ethel Percy Andrus Gerontology Center (GER) - 224
Audiences: Everyone Is Invited
Contact: Carla Stanard
-
ECE-EP seminar - Saransh Sharma, Thursday, March 21st at 2pm in EEB 248
Thu, Mar 21, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Saransh Sharma, Massachusetts Institute of Technology
Talk Title: Miniaturized Biomedical Devices for Navigation, Sensing and Stimulation
Series: ECE-EP Seminar
Abstract: Medical electronic devices are an integral part of the healthcare system today and are used in a variety of applications around us. The design of such devices has several stringent requirements, the key being miniaturization, low-power operation, and wireless functionality. In this talk, I will present CMOS-based miniaturized, low-power and wireless biomedical devices in three broad domains: (a) in-vivo navigation and tracking, (b) in-vivo sensing of biomarkers and physiological signals, and (c) in-vivo stimulation and drug delivery. For the first part, I will talk about ingestible and implantable devices that can be used to achieve sub-mm tracking accuracy in 3D and in real time inside the human body, which is very useful for localizing devices in the GI tract, during precision surgeries and minimally invasive procedures. In the second part, I will present the design of a novel on-chip 3D magnetic sensor that is highly miniaturized and low- power, thus making it suitable for many biomedical applications. In the last part, I will briefly talk about my recent work on a wearable device for multi-modal sensing from sweat, followed by ongoing work on devices for stimulation and drug-delivery. I will end the talk with a glimpse of my future research direction.
Biography: Saransh Sharma received the B.Tech. degree in Electronics and Electrical Communication Engineering from IIT Kharagpur, India, in 2017 and the M.S. and Ph.D. degree in Electrical Engineering from Caltech, Pasadena, CA, USA, in 2018 and 2023 respectively. He is currently a post- doctoral scholar at MIT, Cambridge, MA, USA. His research is on integrated circuits and systems design, with special emphasis on low-power biomedical applications. He was a recipient of the Demetriades-Tsafka-Kokkalis award for best PhD thesis at Caltech in biotechnology and related fields, the Jakob van Zyl Predoctoral Research award at Caltech, Lewis Winner Award for Outstanding Paper at ISSCC 2024, Charles Lee Powell Fellowship at Caltech, and Excellence in Mentorship award at Caltech for mentoring undergraduate and graduate research students.
Host: ECE-EP
Webcast: WldndTF6ZGZPbHFJUT09More Information: Saransh Sharma Seminar Announcement.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
WebCast Link: WldndTF6ZGZPbHFJUT09
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
Alfred E. Mann Department of Biomedical Engineering
Fri, Mar 22, 2024 @ 11:00 AM - 11:50 AM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Tejal Desai, Ph.D., The Sorensen Family Dean of Engineering Brown University
Talk Title: Therapeutic Biomaterials: Engineering Material Structure to Modulate Biologic Delivery
Abstract: The ability to deliver therapeutics within and across biologic barriers is a much sought after goal. In this talk, I will discuss our recent work in developing nanostructured materials for biologic delivery as well as injectable micro/nanoscale materials for the reduction of fibrosis and immune activation. By incorporating micro and nanoscale features into biomaterials, one can modulate properties such as tissue permeability, matrix production, and cell activation. The understanding of how small-scale topographies can influence the biological microenvironment allows us to design platforms for applications in therapeutic delivery and tissue regeneration. Micro and nanostructured materials can add functionality to current drug delivery platforms while becoming an enabling technology leading to new basic discoveries in the pharmaceutical and biological sciences
Biography: Tejal A. Desai assumed the role of Sorensen Family Dean of Engineering at Brown University, effective September 1, 2022. An accomplished biomedical engineer and academic leader, Desai’s research spans multiple disciplines including materials engineering, cell biology, tissue engineering, and pharmacological delivery systems to develop new therapeutic interventions for disease. She seeks to design new platforms, enabled by advances in micro and nanotechnology, to overcome challenges in therapeutic delivery. With more than 260 peer-reviewed articles and patents, Desai’s research has earned her numerous recognitions including Technology Review’s Top 100 Young Innovators, Popular Science’s Brilliant 10 and the Dawson Biotechnology Award. She served as president of the American Institute for Medical and Biological Engineering from 2020 to 2022 and is a fellow of AIMBE, IAMBE, CRS, and BMES. She was elected to the National Academy of Medicine in 2015, the National Academy of Inventors in 2019, and to the National Academy of Engineering in 2024. Desai was also awarded the 2023 Robert A. Pritzker Distinguished Lecture Award at the Biomedical Engineering Society Annual Meeting — the highest honor the organization can bestow upon an individual who has demonstrated impactful leadership and accomplishments in biomedical engineering science and practice. Prior to coming to Brown, she was the Deborah Cowan Endowed Professor of the Department of Bioengineering & Therapeutic Sciences at University of California, San Francisco (UCSF); and Professor in Residence, Department of Bioengineering, UC Berkeley (UCB). She served as director of the NIH training grant for the Joint UCSF/UCB Graduate Program in Bioengineering for over 15 years and founding director of the UCSF/UCB Master’s Program in Translational Medicine. She was also chair of the department of Bioengineering and Therapeutic Sciences at UCSF from 2014-2021 and the Inaugural Director of the UCSF Engineering and Applied Sciences Initiative known as HIVE (Health Innovation Via Engineering). A vocal advocate for education and outreach to historically underrepresented groups in STEM, Desai’s work to break down institutional barriers to equity and cultivate a climate of inclusion has earned numerous honors and awards, including the AWIS Judith Poole Award in Mentorship, the 2021 UCSF Chancellors Award for the Advancement of Women, and the 2022 Controlled Release Woman in Science Award. As president of AIMBE (2020-2022), she led advocacy efforts for increased scientific funding and addressing workforce disparities in science/engineering. To foster the next generation of scientists, she was involved in the SF Science Education partnership and has worked with outreach organizations such as the Lawrence Hall of Science, PBS, and the UN Women’s council to develop hand-on exhibits and videos related to nanotechnology and women in engineering.
Host: Eunji Chung
Location: Olin Hall of Engineering (OHE) - 100B
Audiences: Everyone Is Invited
Contact: Carla Stanard
-
USC Symposium on Frontiers of Generative AI Models in Science and Society
Mon, Mar 25, 2024 @ 08:30 AM - 06:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Various, USC Machine Learning Center
Talk Title: USC Symposium on Frontiers of Generative AI Models in Science and Society
Abstract: The USC Machine Learning Center and Computer Science Department is excited to host the syposium on "Frontiers of Generative AI Models in Science and Society". Experts in generative AI models will discuss recent progresses and their applications in science and soceity.
Keynote Speakers: Alessandro Vespignani (Northeastern University), Nitesh Chawla (Notre Dame), Yizhou Sun (UCLA), & Jian Ma (CMU)
Spotlight Speakers: Jieyu Zhao, Robin Jia, Yue Wang, Vatsal Sharan, & Ruishan Liu (USC Thomas Lord Department of Computer Science)
Host: USC Machine Learning Center
More Info: https://www.eventbrite.com/e/usc-symposium-on-frontiers-of-generative-ai-models-in-science-and-society-tickets-860269668737?aff=oddtdtcreator
Location: Michelson Center for Convergent Bioscience (MCB) - 101
Audiences: Everyone Is Invited
Contact: Thomas Lord Department of Computer Science
-
CS Colloquium: Junzhe Zhang - Towards Causal Reinforcement Learning
Mon, Mar 25, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Junzhe Zhang, Columbia University
Talk Title: Towards Causal Reinforcement Learning
Abstract: Causal inference provides a set of principles and tools that allows one to combine data and knowledge about an environment to reason with questions of a counterfactual nature - i.e., what would have happened if the reality had been different - even when no data of this unrealized reality is currently available. Reinforcement learning provides a collection of methods that allows the agent to reason about optimal decision-making under uncertainty by trial and error - i.e., what would the consequences (e.g., subsequent rewards, states) be had the action been different? While these two disciplines have evolved independently and with virtually no interaction, they operate over various aspects of the same building block, i.e., counterfactual reasoning, making them umbilically connected. This talk will present a unified theoretical framework, called causal reinforcement learning, that explores the nuanced interplays between causal inference and reinforcement learning. I will discuss a recent breakthrough in partial identification that allows one to infer unknown causal effects from a combination of model assumptions and available data. Delving deeper, I will then demonstrate how this method could be applicable to address some practical challenges in classic reinforcement learning tasks, including robust off-policy evaluation from confounded observations and accelerating online learning with offline data. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Junzhe Zhang is a postdoctoral research scientist in the Causal AI lab at Columbia University. He obtained his doctoral degree in Computer Science at Columbia University, advised by Elias Bareinboim. His research centers on causal inference theory and its applications in reinforcement learning, algorithmic fairness, and explainability. His works have been selected for oral presentations in top refereed venues such as NeurIPS.
Host: Sven Koenig
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
ECE Seminar: Dr. Guanghan Meng, "Capturing Life: Optical Microscopy for in vivo Deep Tissue Imaging at High Spatiotemporal Resolution"
Mon, Mar 25, 2024 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Guanghan Meng, Postdoctoral Scholar, Dept of EECS, UC Berkeley
Talk Title: Capturing Life: Optical Microscopy for in vivo Deep Tissue Imaging at High Spatiotemporal Resolution
Abstract: Optical microscopy has become an indispensable tool for non-invasive, high-resolution in vivo imaging of living organisms. Its capability to provide insights into real-time physiological and pathological processes within the body underscores its significance in bioscience and medicine. However, conventional optical microscopy methods have certain limitations. For instance, multiphoton fluorescence microscopy, the method of choice for in vivo imaging through scattering tissue such as the mammalian brains, delivers excellent resolution but falls short in speed for capturing rapid biological activities, such as blood flow dynamics. On the other hand, optical coherence tomography (OCT), a label-free deep-tissue imaging method, stands as a powerful instrument in contemporary optometry clinics, but its high cost limits its broad use, especially in lower-income communities. In this presentation, I will share my research on the development of high-speed multiphoton fluorescence microscopy and cost-effective OCT for brain and eye imaging, respectively, through the utilization of both optical engineering and computational methods.
Biography: Dr. Guanghan Meng, currently a postdoctoral scholar in the Department of Electrical Engineering and Computer Science at the University of California, Berkeley, focuses on advancing high-speed, high-resolution fluorescence, and label-free microscopy technologies for deep tissue imaging in vivo. Having earned her PhD from the same university, her doctoral research spanned the disciplines of Molecular and Cell Biology and Physics, primarily concentrating on enhancing two-photon fluorescence microscopy for mouse brain imaging. At present, she is working on computational label-free imaging with a specific interest in the human eye. Guanghan has been recognized with various best presentation awards at scientific conferences and is a recipient of the Berkeley Center for Innovation in Vision and Optics (CIVO) postdoctoral fellowship. Guanghan is also an invited lecturer at the 17th Edition of the Frontiers in Neurophotonics Summer School in Quebec City, Canada in 2024.
Host: Dr. Justin Haldar, jhaldar@usc.edu
Webcast: https://usc.zoom.us/j/96234786783?pwd=eXF0NnlvNEhPRHllS1NDUEFZWklSdz09Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
WebCast Link: https://usc.zoom.us/j/96234786783?pwd=eXF0NnlvNEhPRHllS1NDUEFZWklSdz09
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
CSC/CommNetS-MHI Seminar: Chandra Murthy
Mon, Mar 25, 2024 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Chandra Murthy, Professor, Department of Electrical Communication Engineering | Indian Institute of Science, Bangalore, India
Talk Title: Sparsity-aware Bayesian Inference and its Applications
Series: CSC/CommNetS-MHI Seminar Series
Abstract: This talk presents a set of tools based on a Bayesian framework to address the general problem of sparse signal recovery, and discusses the challenges associated with them. Bayesian methods offer superior performance compared to convex optimization-based methods and are largely parameter tuning-free. They also have the flexibility necessary to deal with a diverse range of measurement modalities and structured sparsity in signals than hitherto possible. We discuss recent developments towards providing rigorous theoretical guarantees for these methods. Further, we show that, by re-interpreting the Bayesian cost function as a technique to perform covariance matching, one can develop new and ultra-fast Bayesian algorithms for sparse signal recovery. As example applications, we discuss the utility of these algorithms in the context of (a) 5G communications with several case studies such as wideband time-varying channel estimation, low-resolution ADCs, etc, and (b) controllability and observability of linear dynamical systems under sparsity constraints.
Biography: Chandra R. Murthy is a professor in the department of Electrical Communication Engineering at the Indian Institute of Science, Bangalore, India. His research interests are in sparse signal recovery, energy harvesting-based communication, performance analysis, and optimization of 5G and beyond communications. Papers coauthored by him have received Student/Best Paper Awards at the NCC 2014, IEEE ICASSP 2018, IEEE ISIT 2021, IEEE SPAWC 2022, and NCC 2023. He is a senior area editor for the IEEE Transactions on Signal Processing and the IEEE Transactions on Information Theory. He is an elected member of the IEEE SPS SAM Technical Committee. He is an IEEE Fellow (Class of 2023), and a fellow of the Indian National Academy of Engineering (2023).
Host: Dr. Urbashi Mitra, ubli@usc.edu
More Information: 2024.03.25 CSC Seminar - Chandra Murthy.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
Audiences: Everyone Is Invited
Contact: Miki Arlen
-
CS Colloquium: Xiang Anthony Chen - Catalyzing AI Advances with Human-Centered Interactive Systems
Tue, Mar 26, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Xiang Anthony Chen, UCLA
Talk Title: Catalyzing AI Advances with Human-Centered Interactive Systems
Abstract: Despite the unprecedented advances in AI, there has always been a gap between how well an AI model performs and how such performance can serve humanity. In this seminar, I will describe my past work to close this gap. Specifically, I develop human-centered interactive systems that catalyze advances in AI to achieve three levels of objectives: aligning with human values, assimilating human intents, and augmenting human abilities. Further, I will discuss my ongoing and future research, focused on AI for scientific discovery, AI with Theory of Mind, and AI-mediated human communication. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Xiang ‘Anthony' Chen is an Assistant Professor in UCLA's Department of Electrical & Computer Engineering. He received a Ph.D. in the School of Computer Science at Carnegie Mellon University. Anthony's area of expertise is Human-Computer Interaction (HCI). His research employs human-centered design methods to build systems that catalyze advances in AI to better serve humanity, supported by NSF CAREER Award, ONR YIP Award, Google Research Scholar Award, Intel Rising Star Award, Hellman Fellowship, NSF CRII Award, and Adobe Ph.D. Fellowship. Anthony’s work has resulted in 55+ publications with three best paper awards and three honorable mentions in top-tier HCI conferences.
Host: Heather Culbertson
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CAIS Webinar: Dr. Jessica Ridgway (University of Chicago) - Predictive Analytics for Engagement in HIV Care
Tue, Mar 26, 2024 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Jessica Ridgway, University of Chicago
Talk Title: Predictive Analytics for Engagement in HIV Care
Abstract: Engagement in care is essential for the health of people with HIV, but only half of people with HIV in the U.S. receive regular medical care. Dr. Ridgway will discuss her research utilizing machine learning models based on electronic medical record data to predict engagement in care among people with HIV. She has developed machine learning models using structured data as well as natural language processing of unstructured clinical notes. She will discuss challenges and pitfalls in utilizing electronic medical record data for HIV-related predictive modeling, as well as implications for implementation in clinical practice.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Jessica Ridgway, MD, MS, is an Associate Professor of Medicine in the Section of Infectious Diseases and Global Health and Director of Medical Informatics at the University of Chicago. She is Director of Predictive Analytics for the Chicago Center for HIV Elimination. Her research focuses on utilizing large electronic medical record databases to understand HIV epidemiology across the continuum of care and implementation of clinical informatics interventions to improve HIV care and prevention.
Host: USC Center for Artificial Intelligence in Society (CAIS)
More Info: https://usc.zoom.us/webinar/register/WN_gEn8OHXBQnmpYiWc9hJimw
Location: Zoom only - https://usc.zoom.us/webinar/register/WN_gEn8OHXBQnmpYiWc9hJimw
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/webinar/register/WN_gEn8OHXBQnmpYiWc9hJimw
-
ECE-EP Seminar - Zaijun Chen, Tuesday, March 26th at 2pm in EEB 248
Tue, Mar 26, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Zaijun Chen, University of Southern California
Talk Title: Large-Scale Photonic Circuits for AI Computing and Metrology
Series: ECE-EP Seminar
Abstract: The rapid expansion of artificial intelligence (AI), internet of things (IoT) and 5G/6G mobile networks is creating an urgent need for energy-efficient, scalable computing hardware. Optical computing is emerging to enable new computing paradigms with high optical bandwidth, parallel processing, and low-loss data movement. However, the scalability of existing optical accelerators is limited by the electro-optic conversion efficiency, large photonic device footprints, lack of optical nonlinearity, etc. In this talk, I will present our computing approaches to overcomes these bottlenecks with hyperdimensional multiplexing. Our experimental results have realized large-scale AI processing in models with half a million parameters, a full-system energy efficiency at few femtojoule per operation (fJ/OP) and computing density of 6 TOP/(mm2·s). This computing efficiency and density outperform the state-of-the-art digital processors for the first time, with 100 folds improvement. In the last part, I will cover some interferometry techniques based on laser frequency combs for broadband, high-speed precision sensing and metrology at quantum-limited sensitivity.
Biography: Zaijun Chen is a research assistant professor at the Ming Hsieh Department of Electrical and Computer Engineering at USC. He accomplished his Ph.D. degree (summa cum laude) in Prof. Theodor W. Haensch's (Nobel laureate 2005) group at Max-Planck Institute of Quantum Optics (MPQ) in 2019, and postdoc with Prof. Dirk Englund at MIT. He is a recipient of 2023 SPIE best paper award for Machine learning and Artificial intelligence, 2023 Sony faculty Innovation Award, 2023 Optica Foundation Challenge Award, and leading PI in a 2023 DARPA project (NaPSAC). He is an early career editor of Advanced Photonics.
Host: ECE-Electrophysics
More Information: Zaijun Chen Seminar Announcement.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
Epstein Institute, ISE 651 Seminar Class
Tue, Mar 26, 2024 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Xuan Song, Assistant Professor, James A. Chisman Faculty Fellow, Department of Industrial & Systems Engr, Iowa Technology Institute
Talk Title: Toward Mild Additive Manufacturing for Extremes
Host: Prof. Yong Chen
More Information: March 26, 2024.pdf
Location: Social Sciences Building (SOS) - SOS Building, B2
Audiences: Everyone Is Invited
Contact: Grace Owh
-
CS Colloquium: Paul Liang - Foundations of Multisensory Artificial Intelligence
Wed, Mar 27, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Paul Liang, CMU
Talk Title: Foundations of Multisensory Artificial Intelligence
Abstract: Building multisensory AI systems that learn from multiple sensory inputs such as text, speech, video, real-world sensors, wearable devices, and medical data holds great promise for impact in many scientific areas with practical benefits, such as in supporting human health and well-being, enabling multimedia content processing, and enhancing real-world autonomous agents. In this talk, I will discuss my research on the machine learning principles of multisensory intelligence, as well as practical methods for building multisensory foundation models over many modalities and tasks. In the first half, I will present a theoretical framework formalizing how modalities interact with each other to give rise to new information for a task. These interactions are the basic building blocks in all multimodal problems, and their quantification enables users to understand their multimodal datasets and design principled approaches to learn these interactions. In the second part, I will present my work in cross-modal attention and multimodal transformer architectures that now underpin many of today’s multimodal foundation models. Finally, I will discuss our collaborative efforts in scaling AI to many modalities and tasks for real-world impact on mental health, cancer prognosis, and robot control. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Paul Liang is a Ph.D. student in Machine Learning at CMU, advised by Louis-Philippe Morency and Ruslan Salakhutdinov. He studies the machine learning foundations of multisensory intelligence to design practical AI systems that integrate, learn from, and interact with a diverse range of real-world sensory modalities. His work has been applied in affective computing, mental health, pathology, and robotics. He is a recipient of the Siebel Scholars Award, Waibel Presidential Fellowship, Facebook PhD Fellowship, Center for ML and Health Fellowship, Rising Stars in Data Science, and 3 best paper/honorable mention awards at ICMI and NeurIPS workshops. Outside of research, he received the Alan J. Perlis Graduate Student Teaching Award for instructing courses on multimodal ML and advising students around the world in directed research.
Host: Willie Neiswanger / Xiang Ren
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Teodora Baluta - New Algorithmic Tools for Rigorous Machine Learning Security Analysis
Wed, Mar 27, 2024 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Teodora Baluta, National University of Singapore
Talk Title: New Algorithmic Tools for Rigorous Machine Learning Security Analysis
Abstract: Machine learning security is an emerging area with many open questions lacking systematic analysis. In this talk, I will present three new algorithmic tools to address this gap: (1) algebraic proofs; (2) causal reasoning; and (3) sound statistical verification. Algebraic proofs provide the first conceptual mechanism to resolve intellectual property disputes over training data. I show that stochastic gradient descent, the de-facto training procedure for modern neural networks, is a collision-resistant computation under precise definitions. These results open up connections to lattices, which are mathematical tools used for cryptography presently. I will also briefly mention my efforts to analyze causes of empirical privacy attacks and defenses using causal models, and to devise statistical verification procedures with ‘probably approximately correct’ (PAC)-style soundness guarantees. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Teodora Baluta is a Ph.D. candidate in Computer Science at the National University of Singapore. She enjoys working on security problems that are both algorithmic in nature and practically relevant. She is one of the EECS Rising Stars 2023, a Google PhD Fellow, a Dean’s Graduate Research Excellence Award recipient and a President’s Graduate Fellowship recipient at NUS. She interned at Google Brain working in the Learning for Code team. Her works are published in security (CCS, NDSS), programming languages/verification conferences (OOPSLA, SAT), and software engineering conferences (ICSE, ESEC/FSE). More details are available on her webpage: https://urldefense.com/v3/__https://teobaluta.github.io/__;!!LIr3w8kk_Xxm!pCgCXC327otABpiCTruPDSq7pyOXJEWhQ5X0UekIkZhAzt8Q0u0y5QtnemfzYURw7fop1LHm8tR_SY5JCA$ .
Host: Mukund Raghothaman
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
AME Seminar
Wed, Mar 27, 2024 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Shima Shahab, Virginia Tech
Talk Title: Ultrasound-Responsive Intelligent Material Systems
Abstract: Intelligent material systems, often known as smart materials, may adapt their behavior in response to changes in external stimuli. The use of smart materials in numerous sensitive applications has increased the demand for a remote, wireless, efficient, and physiologically safe stimulus. These needs will be addressed in this presentation by using Focused Ultrasound (FUS) as an external trigger. To achieve the desired response of an ultrasound-responsive smart structure, FUS has the unique property of maintaining both spatial and temporal control and propagating over large distances with low losses. Shape Memory Polymers (SMPs) and piezoelectric (PZT) materials will be discussed as ultrasound-responsive smart materials. First, we will look into the acoustic-thermoelastic dynamics of ultrasound-stimulated SMPs in order to develop next-generation delivery, sensing, and morphing devices. When activated by FUS, SMPs can be manipulated into any temporary shape and then recover to their stress-free permanent shape. FUS is a promising stimulus with the unique and superior capacity to cause localized heating, activate various intermediate shapes, and enable noninvasive shape recovery in polymers. Second, we'll go through the fundamentals of PZT-based Ultrasonic Power Transfer (UPT) systems. UPT along with acoustic holograms is a new technique that relies on piezoelectric receivers to receive FU in selective patterns. UPT is used to wirelessly charge modest to high-power electronics in biomedical implants and enclosed electronic devices working in unmanned aerial and undersea vehicles. Finally, holographic lenses, also referred to as acoustic holograms, will be discussed. These lenses are utilized to generate complicated FUS fields. They save the desired wavefront's phase profile, which is utilized to reconstruct the acoustic pressure field when illuminated by a single acoustic source. Because of its robustness, simplicity, and low cost, the use of holographic lenses for sound modification in medical applications has attracted interest in recent years. Ultrasound-guided thermal therapy is one such application that use the absorbed acoustic field to generate a therapeutic effect within the human body.
Biography: Shima Shahab is Mary V. Jones Faculty Fellow and an Associate Professor in the Department of Mechanical Engineering at Virginia Tech. She completed her Ph.D. and M.S. in Mechanical Engineering at Georgia Institute of Technology. Dr. Shahab is the Director of Multiphysics Intelligent and Dynamical Systems (MInDS) laboratory and an Associate Editor of Journal of Intelligent Material Systems and Structures (JIMSS). Her theoretical and experimental research program focuses on the intersection of smart materials and dynamical systems for various interdisciplinary applications such as contactless ultrasound power transfer, ultrasound responsive polymer-based systems, ultrasound atomization, and acoustic holograms. Dr. Shahab has served as principal investigator on research grants from the National Science Foundation, Alpha Foundation, Oakridge National Laboratory, and Ford Motor Company. In addition to a recent NSF CAREER award, Dr. Shahab is the recipient of ASME Gary Anderson Early Achievement Award. The award recognizes a young researcher on the rise who has already made significant contributions to the field of Adaptive Structures and Material Systems. More at https://me.vt.edu/people/faculty/shahab-shima.html
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Webcast: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09Location: James H. Zumberge Hall Of Science (ZHS) - 252
WebCast Link: https://usc.zoom.us/j/95892885119?pwd=QXZOZUhrcTJRYk5qZzZwVThrTytVZz09
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
CS Colloquium: Yangsibo Huang - Auditing Policy Compliance in Machine Learning Systems
Thu, Mar 28, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Yangsibo Huang, Princeton University
Talk Title: Auditing Policy Compliance in Machine Learning Systems
Abstract: As the capabilities of large-scale machine learning models expand, so too do their associated risks. There is an increasing demand for policies that mandate these models to be safe, privacy-preserving, and transparent regarding data usage. However, there are significant challenges with developing enforceable policies and translating the qualitative mandates into quantitative, auditable, and actionable criteria. In this talk, I will present my work on addressing the challenges. I will first share my exploration of privacy leakage and mitigation strategies in distributed training. Then, I will explore strategies for auditing compliance with data transparency regulations. I will also examine methods to quantify and assess the fragility of safety alignments in Large Language Models. Finally, I will discuss my plans for future research directions, including collaboration with policy researchers and policymakers. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Yangsibo Huang is a Ph.D. candidate and Wallace Memorial Fellow at Princeton University. She has been doing research at the intersection of machine learning, systems, and policy, with a focus on auditing and improving machine learning systems’ compliance with policies, from the perspectives of privacy, safety, and data usage. She interned at Google AI, Meta AI, and Harvard Medical School and was named an EECS rising star in 2023.
Host: Yue Zhao
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
ECE-S Seminar - Dr. Amrita Roy Chowdhury
Thu, Mar 28, 2024 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Amrita Roy Chowdhury, CRA/CCC CIFellow, University of California, San Diego
Talk Title: Data Privacy in the Decentralized Era
Abstract: Data is today generated on smart devices at the edge, shaping a decentralized data ecosystem comprising multiple data owners (clients) and a service provider (server). Clients interact with the server with their personal data for specific services, while the server performs analysis on the joint dataset. However, the sensitive nature of the involved data, coupled with inherent misalignment of incentives between clients and the server, breeds mutual distrust. Consequently, a key question arises: How to facilitate private data analytics within a decentralized data ecosystem, comprising multiple distrusting parties?
My research shows a way forward by designing systems that offer strong and provable privacy guarantees while preserving complete data functionality. I accomplish this by systematically exploring the synergy between cryptography and differential privacy, exposing their rich interconnections in both theory and practice. In this talk, I will focus on two systems, CryptE and EIFFeL, which enable privacy-preserving query analytics and machine learning, respectively.
Biography: Amrita Roy Chowdhury is a CRA/CCC CIFellow at University of California-San Diego, working with Prof. Kamalika Chaudhuri. She graduated with her PhD from University of Wisconsin-Madison and was advised by Prof. Somesh Jha. She completed her Bachelor of Engineering in Computer Science from the Indian Institute of Engineering Science and Technology, Shibpur where she was awarded the President of India Gold Medal. Her work explores the synergy between differential privacy and cryptography through novel algorithms that expose the rich interconnections between the two areas, both in theory and practice. She has been recognized as a Rising Star in EECS in 2020 and 2021, and a Facebook Fellowship finalist, 2021. She has also been selected as a UChicago Rising Star in Data Science, 2021.
Host: Dr. Viktor Prasanna, prasanna@usc.edu
More Info: https://usc.zoom.us/j/94200520726?pwd=U1ZSd3VUVzIrMVI3QUE3d25hVzIvZz09
Webcast: https://usc.zoom.us/j/94200520726?pwd=U1ZSd3VUVzIrMVI3QUE3d25hVzIvZz09More Information: 2024.03.28 ECE-S Seminar - Amrita Roy Chowdhury.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 248
WebCast Link: https://usc.zoom.us/j/94200520726?pwd=U1ZSd3VUVzIrMVI3QUE3d25hVzIvZz09
Audiences: Everyone Is Invited
Contact: Miki Arlen
Event Link: https://usc.zoom.us/j/94200520726?pwd=U1ZSd3VUVzIrMVI3QUE3d25hVzIvZz09
-
NL Seminar-Informative Example Selection for In-Context Learning
Thu, Mar 28, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Shivanshu Gupta, UCI
Talk Title: Informative Example Selection for In-Context Learning
Series: NL Seminar
Abstract: Meeting hosts only admit 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 (nlg-seminar-host(at)isi.edu) beforehand so we’ll be aware of your attendance and let you in. In-person attendance will be permitted for USC/ISI faculty, staff, students only. Open to the public virtually via the zoom link. For more information on the NL Seminar series and upcoming talks, please visit: https://nlg.isi.edu/nl-seminar/ In-context Learning (ICL) uses large language models (LLMs) for new tasks by conditioning them on prompts comprising a few task examples. With the rise of LLMs that are intractable to train or hidden behind APIs, the importance of such a training-free interface cannot be overstated. However, ICL is known to be critically sensitive to the choice of in-context examples. Despite this, the standard approach for selecting in-context examples remains to use general-purpose retrievers due to the limited effectiveness and training requirements of prior approaches. In this talk, I'll posit that good in-context examples demonstrate the salient information necessary to solve a given test input. I'll present efficient approaches for selecting such examples, with a special focus on preserving the training-free ICL pipeline. Through results with a wide range of tasks and LLMs, I'll demonstrate that selecting informative examples can indeed yield superior ICL performance.
Biography: Shivanshu Gupta is a Computer Science Ph.D. Candidate at the University of California Irvine, advised by Sameer Singh. Prior to this, he was a Research Fellow at LinkedIn and Microsoft Research India, and completed his B.Tech. and M.Tech. in Computer Science at IIT Delhi. His primary research interests are systematic generalization, in-context learning, and multi-step reasoning capabilities of large language models. If speaker approves to be recorded for this NL Seminar talk, it will be posted on the USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI. Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/
Host: Jon May and Justin Cho
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://www.youtube.com/watch?v=Vqvy4XIOtcELocation: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=Vqvy4XIOtcE
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
ECE-EP Faculty Candidate - Srujan Meesala, Thursday, March 28th at 2pm in EEB 248
Thu, Mar 28, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Srujan Meesala, Caltech
Talk Title: Generating quantum correlations between light and Microwaves with a chip-scale device
Series: ECE-EP Seminar
Abstract: Experimental capabilities in modern quantum science and engineering allow the control of quantum states in a variety of solid-state systems such as superconducting circuits, atomic-scale defect centers, and chip-scale optical and acoustic structures. Controlling interactions between physically different qubits across such platforms is a frontier in the quest to build quantum hardware at scale and to probe the coherence limits of solid-state devices. I will present recent progress on constructing a quantum interconnect between superconducting qubits and optical photons. By integrating specially engineered optical, mechanical, and superconducting microwave components in a chip-scale transducer, we made a photon pair source and used it to generate single optical and microwave photons in entangled pairs. Such devices can be used to connect superconducting qubits in distant cryogenic nodes using room-temperature fiber-optic communication channels. I will discuss open challenges with such transducers and a few near-term routes to address them. I will conclude with results from a different set of experiments where we used nanomechanical devices to control the electronic structure and coherence limits of a spin qubit in an atomic-scale defect center.
Biography: Srujan Meesala is an IQIM Postdoctoral Scholar at Caltech in Oskar Painter's research group. He received his PhD from Harvard where he worked in Marko Loncar's research group.
Host: ECE-EP
More Information: Srujan Meesala Seminar Announcement.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
CS Colloquium: Ram Sundara Raman - Global Investigation of Network Connection Tampering
Thu, Mar 28, 2024 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ram Sundara Raman, University of Michigan
Talk Title: Global Investigation of Network Connection Tampering
Abstract: As the Internet's user base and criticality of online services continue to expand daily, powerful adversaries like Internet censors are increasingly monitoring and restricting Internet traffic. These adversaries, powered by advanced network technology, perform large-scale connection tampering attacks seeking to prevent users from accessing specific online content, compromising Internet availability and integrity. In recent years, we have witnessed recurring censorship events affecting Internet users globally, with far-reaching social, financial, and psychological consequences, making them important to study. However, characterizing tampering attacks at the global scale is an extremely challenging problem, given intentionally opaque practices by adversaries, varying tampering mechanisms and policies across networks, evolving environments, sparse ground truth, and safety risks in collecting data. In this talk, I will describe my research on building empirical methods to characterize connection tampering globally and investigate the network technology enabling tampering. First, I will describe a modular design for the Censored Planet Observatory that enables it to remotely and sustainably measure Internet censorship longitudinally in more than 200 countries. I will introduce time series analysis methods to detect key censorship events in longitudinal Censored Planet data, and reveal global censorship trends. I will also briefly describe methods to detect connection tampering using purely passive data. Next, I will introduce novel network measurement methods for locating and examining network devices that perform censorship. Finally, I will describe exciting ongoing and future research directions, such as building intelligent measurement platforms. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Ram Sundara Raman is a PhD candidate in Computer Science and Engineering at the University of Michigan, advised by Prof. Roya Ensafi. His research lies in the intersection of computer security, privacy, and networking, employing empirical methods to study large-scale Internet attacks. Ram has been recognized as a Rising Star at the Workshop on Free and Open Communications on the Internet (FOCI), and was awarded the IRTF Applied Networking Research Prize in 2023. His work has helped produce one of the biggest active censorship measurement platforms, the Censored Planet Observatory, and has helped prevent large-scale attacks on end-to-end encryption.
Host: Jyo Deshmukh
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
Alfred E. Mann Department of Biomedical Engineering
Fri, Mar 29, 2024 @ 11:00 AM - 11:50 AM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Hadley Sikes, Ph.D., The Willard Henry Dow Professor and Graduate Officer in Chemical Engineering, and PI in the Antimicrobial Resistance Interdisciplinary Research Group in Singapores CREATE campus MIT
Talk Title: Protein and reaction engineering for accessible, scalable medical diagnostics
Abstract: Paper-based medical diagnostic tests have an appealingly low cost of goods and can be very simple to operate. However, new tests typically take months to a year or more to develop, driving up costs. A longstanding focus in our lab has been developing and applying an engineering design approach to new medical diagnostic tests. One of the slow and expensive steps in developing diagnostic immunoassays is identification of pairs, or sets in the case of multiplexed assays, of affinity reagents that simultaneously bind non-overlapping target epitopes and also do not cross-react with one another or complex matrix components. Engineered binding molecules derived from a thermophilic organism will be presented as alternatives to antibodies, human or camelid, along with a method for selecting pairs or sets of these reagents for diagnostic immunoassays. Analysis of reaction rates and fluid flow within paper-based tests suggested further protein engineering strategies to improve sensitivity. Generalized assay design principles for integrating these engineered proteins into antigen and serology tests will be discussed, as well as innovations in scalable manufacturing of test formats beyond conventional lateral flow tests. Finally, key elements of the commercialization process for new diagnostic tests will be presented, including protection of intellectual property, technology transfer to partners, manufacturing under ISO13485 certification, usability and clinical testing, and regulatory filings.
Biography: Hadley D. Sikes is the Willard Henry Dow Professor and Graduate Officer in Chemical Engineering at the Massachusetts Institute of Technology and a PI in the Antimicrobial Resistance Interdisciplinary Research Group in Singapores CREATE campus. She advises a team of researchers in the application of physical principles to design, synthesize, characterize, and test molecules for utility in detecting and understanding disease. Hadley earned degrees in chemistry, a BS at Tulane University (D.K. Schwartz lab) and a PhD Stanford University (C.E.D. Chidsey lab) and trained as a postdoctoral scholar in chemical engineering at the University of Colorado, Boulder (C.N. Bowman lab), and at the California Institute of Technology (F.H. Arnold lab) prior to joining the faculty at MIT. Hadley is an Associate Editor at Bioengineering and Translational Medicine.
Host: Maral Mousavi
Location: Olin Hall of Engineering (OHE) - 100B
Audiences: Everyone Is Invited
Contact: Carla Stanard
