Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for March
-
CA DREAMS - Technical Seminar Series
.jpg)
Fri, Mar 07, 2025 @ 12:00 PM - 01:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Umesh K. Mishra, Dean, Richard A Auhll Dean of the College of Engineering at the University of California Santa Barbara
Talk Title: A Brief History and the Promise of Gallium Nitride (GaN) Electronics; the Next Wave After GaN Photonics
Abstract: In this talk, we will recount the development of GaN electronics over its history of nearly 40 years to its widepsread deployment today in commercial and DoD systems.
Biography: Umesh K. Mishra is the Richard A Auhll Dean of the College of Engineering at the University of California Santa Barbara and the Donald W. Whittier Distinguished Professor of Electrical and Computer Engineering at UC Santa Barbara. He received his B.Tech from the Indian Institute of Technology in Kanpur, India, his M.S from Lehigh University in Bethlehem, PA., and his Ph.D. in 1984 from Cornell University in Ithaca, NY. He has supervised 81 Ph.D theses to completion with 15 of them being women and 69 of them in the field of Gallium Nitride (GaN) materials and devices. 11 of his students are members of the faculty in prestigious universities, with 5 of them being women. His students have founded/co-founded 10 companies. He co-founded the first start-up in the world to commercialize RF GaN transistors and LEDs in 1996 (Nitres) which was acquired by CREE (now Wolfspeed) in 2000. Umesh co-founded Transphorm in 2007 which was honored as a Technology Pioneer at the World Economic Forum, 2013, to commercialize GaN-on-Si transistors for power conversion. Transphorm was acquired by Renesas in 2024. He has over 1000 papers (>70,000 citations; h-index 130) and over 100 patents. Umesh received several awards including the IEEE Jun-Ichi Nishizawa Medal for his contributions to the development and commercialization of GaN electronics. He is a Fellow of the IEEE, an International Fellow of the Japanese Society of Applied Physics, Fellow of the National Academy of Inventors, a Member of the National Academy of Engineering and a Distinguished Alumnus of IIT Kanpur.
Host: Dr. Steve Crago
More Info: https://www.isi.edu/events/5356/a-brief-history-and-the-promise-of-gallium-nitride-gan-electronics-the-next-wave-after-gan-photonics/
Webcast: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addonWebCast Link: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addon
Audiences: Everyone Is Invited
Contact: Amy Kasmir
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar: From Democratization to Personal Names: Reimagining NLP Practices Towards Justice
Thu, Mar 13, 2025 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Arjun Subramonian, UCLA, UCLA
Talk Title: From Democratization to Personal Names: Reimagining NLP Practices Towards Justice
Abstract: Meeting hosts only admit on-line guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom. If you’re an outside visitor, please inform us at (nlg-seminar-host(at)isi.edu) to make us aware of your attendance so we can admit you. Specify if you will attend remotely or in person at least one business day prior to the event. Provide your: full name, job title and professional affiliation and arrive at least 10 minutes before the seminar begins. If you do not have access to the 6th Floor for in-person attendance, please check in at the 10th floor main reception desk to register as a visitor and someone will escort you to the conference room location Join Zoom Meetinghttps://usc.zoom.us/j/95338734726?pwd=FwdcZrr7tyjLLiuBgg2DVS6aZKOBf7.1 Meeting ID: 953 3873 4726 Passcode: 100604 Current natural language processing (NLP) practices operate within a set of logics which codify new, and entrench existing, social inequalities and power dynamics. In this talk, I will delve into two troubling NLP practices: the discussion of "democratizing" language technologies and the association of personal names with sociodemographic characteristics. I will reveal how current use of the term "democratization" in NLP can be inconsistent and irresponsible, which risks misrepresenting the distribution of power in and public control of AI; I will further provide recommendations to strengthen progress towards democratic technologies beyond just superficial access. Furthermore, I will survey the issues inherent to associating personal names with sociodemographic attributes, covering problems of validity (e.g., systematic error, construct validity) and ethical concerns (e.g., harms, differential impact, cultural insensitivity). Then, I will offer guiding questions along with normative recommendations to avoid these pitfalls. Ultimately, constructively examining NLP practices through a critical lens is important for advancing justice in the field.
Biography: Arjun Subramonian is a Computer Science PhD candidate at the University of California, Los Angeles. Their research focuses on the fairness and ethics of machine learning and natural language processing. They are further a core organizer of Queer in AI. They are a recipient of an Amazon Fellowship, NSF NRT Fellowship, Eugene V. Cota-Robles Fellowship, and FAccT 2023 Best Paper Award. If speaker approves to be recorded for this seminar, 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/ For more information on the NL Seminar series and upcoming talks, please visit: https://www.isi.edu/research-groups-nlg/nlg-seminars/
Host: Jonathan May and Katy Felkner
More Info: https://www.isi.edu/events/5500/from-democratization-to-personal-names-reimagining-nlp-practices-towards-justice/
Webcast: https://www.youtube.com/watch?v=Rl6MIbqvPIQLocation: Information Science Institute (ISI) - Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=Rl6MIbqvPIQ
Audiences: Everyone Is Invited
Contact: Pete Zamar
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
CA DREAMS - Technical Seminar Series
.jpg)
Fri, Mar 14, 2025 @ 12:00 PM - 01:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Azita Emami, Professor, Caltech
Talk Title: Electronic-Photonic Co-Design for High-Speed Data Communication and Beyond
Abstract: Data centers continue to demand interconnect solutions with higher bandwidth densities and improved energy efficiency. Furthermore, applications such as chip-to-chip interconnects in switches, high-performance FPGAs and GPUs call for compact form-factors, high-volume production and low cost. Silicon Photonics (SiP)-based transceivers, when co-packaged with CMOS electronics, offer a promising avenue to meet these demands with speeds exceeding 100 Gb/s per wavelength. In this talk we focus on architectural and circuit-level techniques for both PICs and EICs to improve the energy-efficiency at high data rates. We will discuss how various types of optical modulators and optical architectures can be employed to achieve higher-order modulation schemes. We will first present a 100Gb/s 3D integrated Sip-CMOS PAM4 optical transmitter system. The photonic chip includes a push-pull segmented MZM structure using highly capacitive, yet optically efficient MOSCAP phase modulators. Co-design and optimum bandwidth enhancement techniques are employed to achieve high data rates and energy efficiency. Next a 100Gb/s DAC-less PAM-4 transmitter and a 200Gb/s QAM-16 transmitter in a multi-micron silicon photonics platform using binary-driven SiGe EAMs will be presented. In the second part of this talk, we will briefly show another example of co-designed electronics and photonics for sensing applications. We present a fully integrated fluorescence (FL) sensor in 65nm standard CMOS comprising on-chip bandpass optical filters, photodiodes (PDs), and processing circuitry. The metal/dielectric layers in CMOS are employed to implement low-loss cavity-type optical filters achieving a bandpass response at 600nm to 700nm range suitable to work with fluorescent proteins (FPs), which are the widely used bio-reporters for biomedical and environmental sensing.
Biography: Azita Emami is the Andrew and Peggy Cherng Professor of Electrical Engineering and Medical Engineering, and the Director of Center for Sensing to Intelligence (S2I) at Caltech. She received her M.S. and Ph.D. degrees in Electrical Engineering from Stanford University in 1999 and 2004 respectively, and her B.S. degree from Sharif University of Technology in 1996. From 2004 to 2006 she was with IBM T. J. Watson Research Center before joining Caltech in 2007. She served as the Executive Officer (Department Head) for Electrical Engineering from 2018 to 2024. Her current research interests include integrated circuits and systems, integrated photonics, high-speed data communication systems, wearable and implantable devices for neural recording, neural stimulation, sensing and drug delivery.
Host: Dr. Steve Crago
More Info: https://www.isi.edu/events/5480/electronic-photonic-co-design-for-high-speed-data-communication-and-beyond/
Webcast: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addonWebCast Link: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addon
Audiences: Everyone Is Invited
Contact: Amy Kasmir
Event Link: https://www.isi.edu/events/5480/electronic-photonic-co-design-for-high-speed-data-communication-and-beyond/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
USC-ISI Networking and Cybersecurity Seminar Talk
Mon, Mar 17, 2025 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Dr. Bhavani Thuraisingham, University of Texas at Dallas
Talk Title: Trustworthy Artificial Intelligence for Securing Transportation Systems
Series: Networking and Cybersecurity
Abstract: Artificial Intelligence (AI) techniques are being applied to numerous applications from Healthcare to Cyber Security to Finance. For example, Machine Learning (ML) algorithms are being applied to solve security problems such as malware analysis and insider threat detection. However, there are many challenges in applying ML algorithms for various applications. For example, (i) the ML algorithms may violate the privacy of individuals. This is because we can gather massive amounts of data and apply ML algorithms on the data to extract highly sensitive information. (ii) ML algorithms may show bias and be unfair to various segments of the population. (iii) ML algorithms themselves may be attacked possibly resulting in catastrophic errors including in cyber physical systems such as transportation systems.
In this presentation, we discuss our research we are conducting as part of the USDOT National University Technology Center TraCR (Transportation Cybersecurity and Resiliency) led by Clemson University. In particular, we describe (i) the application of federated machine learning techniques for detecting attacks in transportation systems; (ii) publishing synthetic transportation data sets that preserves privacy, (iii) fairness algorithms for transportation systems, and (iv) examining how GenAI systems are being integrated with transportation systems to provide security. Finally, we discuss resiliency issues with respect to transportation systems where such systems and applications must continue to operate in the midst of attacks and failures.
Biography: Dr. Bhavani Thuraisingham is the Founders Chair Professor of Computer Science and the Founding Executive Director of the Cyber Security Research and Education Institute at the University of Texas at Dallas (UTD). She is an elected Fellow of the ACM, IEEE, the AAAS, and the NAI. Her research interests are on integrating cyber security and artificial intelligence/data science including as they relate to the cloud, social media, and Transportation Systems. She has received several technical, education and leadership awards including the IEEE CS 1997 Edward J. McCluskey Technical Achievement Award, the IEEE CS 2023 Taylor L. Booth Education Award, ACM SIGSAC 2010 Outstanding Contributions Award, the IEEE Comsoc Communications and Information Security 2019 Technical Recognition Award, the IEEE CS Services Computing 2017 Research Innovation Award, the ACM CODASPY 2017 Lasting Research Award, and the ACM SACMAT 10 Year Test of Time Awards for 2018 and 2019 (for papers published in 2008 and 2009). Her 44+ year career includes industry (Honeywell), federal research laboratory (MITRE), US government (NSF) and US Academia. Her work has resulted in 140+ journal articles, 300+ conference papers, 200+ keynote and featured addresses, seven US patents, sixteen books, and over 120 panel presentations including at Fortune Media, Lloyds of London Insurance, Dell Technologies World, United Nations, and the White House Office of Science and Technology Policy. She has also written opinion columns for popular venues such as the New York Times, Inc. Magazine, Womensday.com and the Legal 500. She received her PhD from the University of Wales, Swansea, UK, and the prestigious earned higher doctorate (D. Eng) from the University of Bristol, UK. She also has a Certificate in Public Policy Analysis from the London School of Economics and Political Science. She has been featured in the book by the ACM in 2024 titled: “Rendering History: The Women of ACM-W” as one of the 30+ “Women that Changed the Face of World Wide Computing Forever.”
Host: David Balenson and Jelena Mirkovic
More Info: https://www.isi.edu/events/5645/trustworthy-artificial-intelligence-for-securing-transportation-systems/
Webcast: https://www.isi.edu/events/5645/trustworthy-artificial-intelligence-for-securing-transportation-systems/Location: Information Science Institute (ISI) - 1135/37
WebCast Link: https://www.isi.edu/events/5645/trustworthy-artificial-intelligence-for-securing-transportation-systems/
Audiences: Everyone Is Invited
Contact: Matt Binkley / Information Sciences Institute
Event Link: https://www.isi.edu/events/5645/trustworthy-artificial-intelligence-for-securing-transportation-systems/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
USC-ISI Networking and Cybersecurity Seminar Talk
Mon, Mar 17, 2025 @ 01:30 PM - 02:30 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Dr. Latifur Khan, University of Texas at Dallas
Talk Title: Generative AI including Large Language Models for Cyber-Security
Series: Networking and Cybersecurity
Abstract: In this presentation, I will explore three applications of generative AI, specifically Large Language Models (LLMs), in the domains of tabular security datasets, cyber-threat reports, and Federal and State legislation related to autonomous vehicles.
1. Learning for Tabular Security Datasets and its applications to Automotive Security.
Tabular datasets in cybersecurity present significant challenges for machine learning due to their heavily imbalanced nature—with a small number of labeled attack samples buried in a vast sea of mostly benign, unlabeled data. Semi-supervised learning leverages a small subset of labeled data alongside a large subset of unlabeled data to train a model. While semi-supervised methods have been extensively studied in image and language domains, they remain underutilized in security contexts—particularly for tabular security datasets, where challenges such as contextual information loss and class imbalance hinder machine learning performance. To address these issues, we propose MCoM (Mixup Contrastive Mixup), a novel semi-supervised learning methodology that introduces a triplet mixup data augmentation approach to mitigate the imbalanced data problem in tabular security datasets.
Many automotive security datasets are tabular in nature. We leverage these advantages to produce novel solutions for securing smart vehicles. Machine learning approaches are a natural choice for detecting such attacks based on the payload information. However, machine learning models typically require a large dataset for training. With manufacturers independently gathering this data based on their own cars, it is unlikely that all this data will be available in one place. To address this issue, we explore federated solutions that learn in a distributed manner for increased smart vehicle security. We explore challenging scenarios in which we do not assume an independent and identically distributed (IID) setting for the data. With a combination of techniques including triplet-mixup based augmentation and a data exchange scheme involving synthetically generated samples, we show that we can attain strong performance in the most challenging label distribution scenarios.
2. AI for Cybersecurity Intelligence and Policy
In this area, we will discuss several related research projects:
• Optimizing Cyber Threat Intelligence with Active Learning We propose a framework for efficiently identifying cyber-attacks, called ALERT. The ALERT framework addresses challenges in extracting actionable intelligence from complex Cyber Threat Intelligence (CTI) reports by automating the identification of attack techniques and mapping them to the MITRE ATT&CK framework. By combining active learning strategies with Large Language Models (LLMs), our approach selects only the most informative instances for annotation, achieving comparable performance with 77% less data. This significantly reduces the resource-intensive process of manual annotation by security professionals while maintaining effectiveness in threat technique extraction.
• Automating Cyber-Threat Intelligence with LLMs In collaboration with researchers from NIST, we focus on automating the extraction of attack techniques from Common Vulnerabilities and Exposures (CVE) and Cyber Threat Intelligence (CTI) reports. We then map these techniques to the standardized MITRE ATT&CK framework using a combination of LLMs and active learning. This talk will demonstrate how this curated knowledge enables security analysts to respond more effectively to cyber threats by streamlining intelligence gathering and threat attribution.
• Identifying Legislative Gaps in Autonomous Vehicle Regulations Leveraging LLMs and Retrieval-Augmented Generation (RAG), we have identified gaps in Federal and State legislation concerning data privacy and cybersecurity within the autonomous vehicle domain. This presentation will showcase how modifications or additions to existing legislative frameworks can proactively address emerging cybersecurity and privacy challenges in autonomous vehicle regulations. By integrating generative AI and LLMs into these domains, we aim to bridge critical gaps in cybersecurity, intelligence automation, and policy-making, demonstrating the transformative potential of AI in real-world applications.
3. Responsible Active Online Learning for Streaming Data
In many practical applications, machine learning systems face three interconnected challenges: processing continuous streams of incoming data, handling predominantly unlabeled datasets, and ensuring responsible and unbiased predictions across diverse demographic groups. Current approaches rarely address all three aspects effectively. We propose a framework called FACTION, which strategically identifies and selects the most valuable data points for annotation by balancing model uncertainty with ethical considerations for various subpopulations. The system additionally demonstrates exceptional capability in detecting anomalous data points within streaming contexts. Through comprehensive testing on real-world datasets and rigorous theoretical validation, FACTION shows promising results in maintaining both accuracy and responsible AI principles in evolving data landscapes. This approach could potentially be applied to transportation safety systems, particularly pedestrian detection in autonomous vehicles where cameras continuously capture diverse individuals in varying conditions. By intelligently selecting informative detection scenarios for annotation, such an application might help address potential disparities in detection accuracy while optimizing the labeling process for continuous video feeds.
*This work is funded by NSF, DOT, NIH, ONR, ARMY, and NSA.
Biography:
Dr. Latifur Khan is currently a full Professor (tenured) in the Computer Science department at the University of Texas at Dallas, USA where he has been teaching and conducting research since September 2000. He received his Ph.D. degree in Computer Science from the University of Southern California (USC) in August of 2000.
Dr. Khan is a fellow of IEEE, IET, BCS, and an ACM Distinguished Scientist. He has received prestigious awards including the IEEE Technical Achievement Award for Intelligence and Security Informatics, IEEE Big Data Security Award, and IBM Faculty Award (research) 2016. Dr. Khan has published over 300 papers in premier journals and prestigious conferences. Currently, Dr. Khan’s research focuses on big data management and analytics, data mining and its application to cyber security, and complex data management including geospatial data and multimedia data. His research has been supported by grants from NSF, NIH, the Air Force Office of Scientific Research (AFOSR), DOE, NSA, IBM, and HPE. More details can be found at www.utdallas.edu/~lkhan.
Host: David Balenson and Jelena Mirkovic
More Info: https://www.isi.edu/events/5655/generative-ai-including-large-language-models-for-cyber-security/
Webcast: https://www.isi.edu/events/5655/generative-ai-including-large-language-models-for-cyber-security/Location: Information Science Institute (ISI) - 1135/37
WebCast Link: https://www.isi.edu/events/5655/generative-ai-including-large-language-models-for-cyber-security/
Audiences: Everyone Is Invited
Contact: Matt Binkley / Information Sciences Institute
Event Link: https://www.isi.edu/events/5655/generative-ai-including-large-language-models-for-cyber-security/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Supporting Research Infrastructure Communities Through LUMI AI and AI Factories, Nordic and European Perspective
Wed, Mar 19, 2025 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Tomasz Malkiewicz, CSC - IT Center for Science in Finland
Talk Title: Supporting Research Infrastructure Communities Through LUMI AI and AI Factories, Nordic and European Perspective
Series: Scientific Computing at Large
Abstract: AI applications like large language models require significant computing resources. LUMI, Europe’s third most powerful supercomputer, is already one of the world’s most powerful AI platforms for science, playing important role in supporting European RI community. The EuroHPC Joint Undertaking (JU) has selected the hosting sites of the next EuroHPC supercomputers and AI Factories. One of the chosen hosting sites is Finland, led by CSC – IT Center for Science, together with a LUMI AI Factory consortium of five other countries: the Czech Republic, Denmark, Estonia, Norway and Poland. An AI Factory is an ecosystem that enables AI researchers and developers to have one-stop access to the high-performance computing (HPC), data sets and skills they need. The aim is to make it as easy as possible for both scientific researchers and industrial innovators to adopt AI methods on a large scale. In this talk, I will present the architecture of the LUMI infrastructure and its status, together with plans and ambitions for the near future. Then, an overview of how LUMI AI supports RI communities based on the scientific showcases and achievements will be presented. These include, for example, contributions to the Destination Earth initiative, work on large language models and breakthroughs from extreme-scale computing capabilities in many fields of science.
Biography: Malkiewicz is employed at CSC - IT Center for Science in Finland, has worked for CSC in managerial and specialist positions since 2011, and is a member of the Management Group since 2016. In 2025 he has been appointed as the Interim Director of NeIC - Nordic e-Infrastructure Collaboraiton for the year 2025. Malkiewicz has worked with NeIC as executive manager and been a part of the executive team since January 2017. Throughout the years, he has acted as project owner for several projects, Puhuri, CodeRefinery and NordIQuEst being the most recent ones. Malkiewicz holds a PhD in nuclear physics from University of Jyväskylä, Finland. Before joining CSC, he had worked as a CNRS postdoctoral researcher at the LPSC Grenoble, France.
Host: Ewa Deelman and Ciji Davis
More Info: https://www.isi.edu/events/5616/supporting-research-infrastructure-communities-through-lumi-ai-and-ai-factories-nordic-and-european-perspective/
Webcast: https://usc.zoom.us/j/95306363929Location: Information Science Institute (ISI) - Conf Rm#1137
WebCast Link: https://usc.zoom.us/j/95306363929
Audiences: Everyone Is Invited
Contact: Pete Zamar
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
CA DREAMS - Technical Seminar Series
.jpg)
Fri, Mar 21, 2025 @ 12:00 PM - 01:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Mike Shuo-Wei Chen, Professor, USC
Talk Title: High-Speed DACs towards High Performance and Efficiency
Series: CA DREAMS - Technical Seminar Series
Abstract: There are increasing interests in wideband and flexible waveform synthesis in modern communication systems. The key enabler in such applications is a high performance digital-to-analog converter (DAC). This has motivated the design community to push the digital-to-analog converter (DAC) towards higher sampling rate (>GS/s) while achieving high dynamic range. Moreover, there is an emerging trend to design a DAC with high output power, i.e. a power DAC or digital power amplifier (PA). In this talk, I will overview various digital-to-analog architectures and filtering techniques that push the envelope of DAC bandwidth, linearity and/or noise floor. A dual-rate hybrid DAC architecture has been shown to enhance dynamic range while a time-approximation filter can be applied to suppress out-of-band emission. In addition, I will introduce an emerging digital PA architecture that aims for high power backoff efficiency, namely sub-harmonic switching (SHS) PA. Validated by a series of silicon prototypes, the proposed DAC architectures when used individually or jointly show a promising path towards high performance and efficiency.
Biography: Mike Shuo-Wei Chen is a Professor in Department of Electrical and Computer Engineering at University of Southern California. As a graduate student, he proposed and demonstrated the asynchronous SAR ADC architecture, which has been adopted in industry today for low-power high-speed analog-to-digital conversion products. After joining USC in 2011, he leads an analog mixed-signal circuit group, focusing on data converters, frequency synthesizers, RF/mm-wave transceiver designs, AI-assisted analog circuit design automation, bio-inspired computing, non-uniformly sampled circuits and systems. Dr. Chen was the recipient of Qualcomm Faculty Award in 2019, NSF Faculty Early Career Development (CAREER) Award, DARPA Young Faculty Award (YFA) both in 2014. His research team received ISSCC Jack Kilby Award and RFIC best student paper award in 2022. Dr. Chen has been serving as an associate or guest editor of the IEEE Journal of Solid-State Circuit (JSSC). IEEE Open Journal of the Solid-State Circuits Society (OJ-SSCS), IEEE Solid-State Circuits Letters (SSC-L), IEEE Transactions on Circuits and Systems II: Express Briefs (TCAS-II), as well as a TPC member in IEEE Solid-State Circuits Society conferences, including the IEEE International Solid-State Circuits Conference (ISSCC), IEEE Symposium on VLSI Circuits (VLSIC), and IEEE Custom Integrated Circuits Conference (CICC). He served as Distinguished Lecturer for IEEE Solid-State Circuits Society (SSCS). He is an IEEE Fellow.
Host: Dr. Steve Crago
More Info: https://www.isi.edu/events/5642/high-speed-dacs-towards-high-performance-and-efficiency/
Webcast: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addonWebCast Link: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addon
Audiences: Everyone Is Invited
Contact: Amy Kasmir
Event Link: https://www.isi.edu/events/5642/high-speed-dacs-towards-high-performance-and-efficiency/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar-MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
Thu, Mar 27, 2025 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Julie Kallini, Stanford University
Talk Title: MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
Abstract: Meeting hosts only admit on-line guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom. If you’re an outside visitor, please inform us at (nlg-seminar-host(at)isi.edu) to make us aware of your attendance so we can admit you. Specify if you will attend remotely or in person at least one business day prior to the event. Provide your: full name, job title and professional affiliation and arrive at least 10 minutes before the seminar begins. If you do not have access to the 6th Floor for in-person attendance, please check in at the 10th floor main reception desk to register as a visitor and someone will escort you to the conference room location. Join via ZOOM: https://usc.zoom.us/j/92986255795?pwd=mbJqNRr6isZBQ9mn643fgalO5gksDs.1 Meeting ID: 929 8625 5795 Passcode: 804448. Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level models like ByT5 attempt to address these concerns, they have not gained widespread adoption—processing raw byte streams without tokenization results in significantly longer sequence lengths, making training and inference inefficient. This work introduces MrT5 (MergeT5), a more efficient variant of ByT5 that integrates a token deletion mechanism in its encoder to dynamically shorten the input sequence length. After processing through a fixed number of encoder layers, a learned delete gate determines which tokens are to be removed and which are to be retained for subsequent layers. MrT5 effectively "merges" critical information from deleted tokens into a more compact sequence, leveraging contextual information from the remaining tokens. In continued pre-training experiments, we find that MrT5 can achieve significant gains in inference runtime with minimal effect on performance, as measured by bits-per-byte. Additionally, with multilingual training, MrT5 adapts to the orthographic characteristics of each language, learning language-specific compression rates. Furthermore, MrT5 shows comparable accuracy to ByT5 on downstream evaluations such as XNLI, TyDi QA, and character-level tasks while reducing sequence lengths by up to 75%. Our approach presents a solution to the practical limitations of existing byte-level models.
Biography: Julie Kallini is a second-year Ph.D. student in Computer Science at Stanford University, advised by Christopher Potts and Dan Jurafsky. Her research focuses on natural language processing (NLP), with an emphasis on computational linguistics/cognitive science, tokenization, and model architecture. Her paper, "Mission: Impossible Language Models," won Best Paper Award at ACL 2024. Her work is supported by the NSF Graduate Research Fellowship, the Stanford School of Engineering Graduate Fellowship, and the Stanford EDGE Fellowship.Before starting her Ph.D., Julie was a software engineer at Meta, where she worked on machine learning for advertisements. Julie graduated summa cum laude from Princeton University with a B.S.E. in Computer Science and a minor in Linguistics.
Host: Jonathan May and Katy Felkner
More Info: https://usc.zoom.us/j/92986255795?pwd=mbJqNRr6isZBQ9mn643fgalO5gksDs.1
Webcast: https://www.youtube.com/watch?v=vWyi1_DXvqALocation: Information Science Institute (ISI) - Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=vWyi1_DXvqA
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://usc.zoom.us/j/92986255795?pwd=mbJqNRr6isZBQ9mn643fgalO5gksDs.1
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
AI Seminar- Designing Priors for Bayesian Neural Networks to Enhance Probabilistic Predictive Modeling in Engineering Applications
Fri, Mar 28, 2025 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Audrey Olivier, USC
Talk Title: Designing Priors for Bayesian Neural Networks to Enhance Probabilistic Predictive Modeling in Engineering Applications
Series: AI Seminar
Abstract: The conjuncton of data mining and physics-based modeling holds great potential to help design, monitor and optimize engineering systems. Efficient ML algorithms can uncover patterns from data to learn missing physics, detect abnormal behaviors and identify damaged systems, or serve as surrogates of complex mechanistic models, enabling real-time analysis or integration within optimization frameworks. However, the use of ML for engineering applications and high-consequence decision-making presents unique challenges. Engineering datasets are often noisy, sparse and imbalanced, due to the inherent randomness of the underlying physical processes and constraints on data collection. Whenever possible, ML predictors must assimilate physics-based knowledge and intuitions to improve accuracy and generalization away from training data. Most importantly, ML models must embed robust and reliable prediction of uncertainties to improve trustworthiness for high-consequence decision-making. Framing ML training within a Bayesian inference framework allows for a robust quantification of both aleatory and epistemic uncertainties that arise from data inadequacies, integration of physics intuitions through prior design, and assessment of the model’s confidence in its predictions. However, due to the high-dimensionality and non-physicality of parameters that characterize typical ML models such as neural networks, application of Bayesian methods in this context raises several technical challenges, from prior and likelihood design to posterior inference. This talk will introduce enhanced algorithms based on ensembling with anchoring for approximate Bayesian learning of neural networks. We will demonstrate the importance of carefully designing the prior, integrating knowledge from low-fidelity models via ensemble pre-training and designing parameter-space prior densities that account for low-rank correlations between neural network weights. The talk will illustrate the benefits of these methods through a variety of example applications in civil engineering, from surrogate training to accelerate materials and structural modeling, contingency analysis in power grid systems, or ambulance travel time prediction in a dense urban network to help optimize emergency medical services.
Biography: Dr. Olivier holds a Diplôme d’Ingénieur from École Centrale de Nantes, France, and a Ph.D. in Civil Engineering and Engineering Mechanics from Columbia University, USA. She held a postdoctoral appointment at Johns Hopkins University before joining the Sonny Astani Department of Civil and Environmental Engineering at the University of Southern California as an Assistant Professor in Fall 2021. Dr. Olivier’s research aims to predict and monitor civil infrastructure systems behavior under uncertainty, by combining innovations in probabilistic data analytics and mechanistic modeling. Applications span various scales, from systems to structures to materials, and include development of adaptive Bayesian filters for identification of dynamical structural systems, probabilistic surrogate models to accelerate multi-scale materials simulations or Bayesian graph neural networks for contingency analysis of power grids.
Host: Eric Boxer and Justina Gilleland
More Info: https://www.isi.edu/events/5453/designing-priors-for-bayesian-neural-networks-to-enhance-probabilistic-predictive-modeling-in-engineering-applications/
Webcast: https://usc.zoom.us/j/94409584905?pwd=Sm5LVkd0bndUdEluM3piK0NWTUQrUT09Location: Information Science Institute (ISI) - Conf Rm#1135 and Virtual
WebCast Link: https://usc.zoom.us/j/94409584905?pwd=Sm5LVkd0bndUdEluM3piK0NWTUQrUT09
Audiences: Everyone Is Invited
Contact: Pete Zamar
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
CA DREAMS - Technical Seminar Series
.jpg)
Fri, Mar 28, 2025 @ 12:00 PM - 01:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Mark Rodwell, Professor, University of California at Santa Barbara
Talk Title: The Role of InP Technologies in Next-Generation 50-300 GHz Systems
Abstract: Present InP bipolar transistors attain 1.1 THz fmax; InP field-effect transistors attain 1.5 THz. These can support emerging applications in 100-300 GHz wireless communications and imaging radar, 400-1000 Gb/s wireline and optical communications, and high-frequency instruments. After summarizing the applications and the required circuit and transistor performance, I will review transistor design, present transistor performance, and the design of next-generation THz bipolar and field-effect transistors.
Biography: Mark J. W. Rodwell (Fellow, IEEE) received the Ph.D. degree from Stanford University 1988. He holds the Doluca Family Endowed Chair in Electrical and Computer Engineering with the University of California at Santa Barbara. During 2017-2023, he directed the SRC/DARPA ComSenTer Wireless Research Center. His research group develops high-frequency transistors, ICs, and communication systems. Dr. Rodwell was a recipient of the 1997 IEEE Microwave Prize, the 1998 European Microwave Conference Microwave Prize, the 2009 IEEE IPRM Conference Award, the 2010 IEEE Sarnoff Award, the 2012 Marconi Prize Paper Award, and the 2022 SIA/SRC University Research Award. For 2024-2025, he is serving as an IEEE-MTT-S Distinguished Microwave Lecturer.
Host: Dr. Steve Crago
More Info: https://www.isi.edu/events/5442/the-role-of-inp-technologies-in-next-generation-50-300-ghz-systems/
Webcast: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addonWebCast Link: https://usc.zoom.us/j/97017422125?pwd=Dbrt8MNMrmBV3xalKQJcAiNsggFJjJ.1&from=addon
Audiences: Everyone Is Invited
Contact: Amy Kasmir
Event Link: https://www.isi.edu/events/5442/the-role-of-inp-technologies-in-next-generation-50-300-ghz-systems/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
.jpg)
.jpg)
.jpg)
.jpg)