Logo: University of Southern California

Events Calendar

Select a calendar:

Filter March Events by Event Type:

Events for March 23, 2023

  • PhD Thesis Proposal - Gautam Salhotra

    Thu, Mar 23, 2023 @ 09:00 AM - 11:00 AM

    Computer Science

    University Calendar

    Title: Accelerating Robot Reinforcement Learning Using Demonstrations

    Committee: Gaurav Sukhatme (Chair), SK Gupta, Laurent Itti, Stefanos Nikolaidis, Somil Bansal

    Date: Thursday March 23, 9am PST

    Reinforcement learning is a promising and, recently, popular tool to solve robotic tasks such as object manipulation and locomotion. However, it is also well known for being a very hard problem setting to explore in. In contrast, Learning from demonstrations (LfD) methods train agents to the desired solution using demonstrations from a teacher.
    I will explore the role of LfD methods to guide the exploration of RL methods, with the aim of applying it to regular object manipulation tasks. I will talk about work that uses planners and trajectory optimizers to guide RL, and then discuss the role human experts can play in LfD for RL. Finally, I will talk about proposed projects that can extend the current work to get the benefits of demonstrations while avoiding the downsides of obtaining them.

    Location: Ronald Tutor Hall of Engineering (RTH) - 406

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

  • ECE-S Seminar - Dr Stephen Xia

    Thu, Mar 23, 2023 @ 10:00 AM - 11:00 AM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars

    Speaker: Dr Stephen Xia, Postdoctoral Scholar | University of California, Berkeley

    Talk Title: Embedded Intelligence Towards Smarter, Healthier and Safer Environments

    Abstract: We have seen remarkable growth in smart devices and artificial intelligence in all aspects of our lives. Despite the ever-growing amount of AI around us, our environments are still far from truly intelligent. At the touch of a button, we have access to powerful AI that can easily outperform any human in complex tasks, yet our environments still cannot alert us to dangerous approaching vehicles, nor help us find our lost child in a busy grocery store, something all of us do regularly and intuitively. In this talk, I will present two lines of work that bridge the gap between AI and truly intelligent environments.
    First, I will introduce my work on embedded acoustic intelligence. I will start by presenting my work on embedding acoustic intelligence into wearables we commonly carry, such as headphones and helmets, to create safer cities. These low-cost and long-lasting wearables leverage novel architectures that utilize a combination of physics-based models and machine learning techniques to alert pedestrians and construction workers of dangers from oncoming vehicles, ultimately acting as a second pair of ears that create a sphere of safety around us. Next, I will discuss how we can take lessons learned from urban safety to realize a generalized selective audio filtering architecture that allows us to embed robust acoustic intelligence into a diverse set of real-time and resource-constrained applications and platforms. This architecture dynamically leverages the physics of audio and a wide range of data-driven machine learning models to allow engineers and developers to enhance and suppress custom sounds in their applications.
    Second, I will present my work on creating more configurable, adaptive, and evolving environments, which are three critical characteristics we need to realize to create truly intelligent environments. I will first touch on several works that allow anyone, regardless of their technical background, to easily deploy and configure complex sensing solutions, such as camera networks for indoor occupant tracking, without needing any domain or expert knowledge. Second, I will introduce my work on adaptive smart home systems that jointly consider human preferences and available resources within the environment to improve home automation and greatly reduce the barrier of entry for smart home technologies. Finally, I will present several works where we realize new dormant sensing and compute capabilities in several platforms, such as drones, by only leveraging processes already present, thereby "evolving" new capabilities completely for free.

    Biography: Stephen Xia is a Postdoctoral Scholar in the Department of Electrical Engineering and Computer Sciences at UC Berkeley, advised by Dr. Prabal Dutta and Dr. Xiaofan (Fred) Jiang. Stephen received his Ph.D. in 2022 from Columbia University and his B.S. in 2016 from Rice University, all in Electrical Engineering. His research lies at the intersection between systems, embedded machine learning, and signal processing, spanning areas in mobile and embedded systems, Internet-of-Things, cyber-physical systems, artificial intelligence, and smart health. His work takes a joint physics-based and data-driven approach to realize truly intelligent and autonomous environments by embedding and dynamically utilizing compute, sensing, actuation, storage, and networking resources all around us. Stephen's research has been highlighted by many popular media outlets, including Mashable, Fast Company, and Gizmodo, and has received various distinctions, including Best Demo Awards at ACM SenSys 2021, ACM/IEEE IPSN 2020, ACM/IEEE IoTDI 2018, and the Best Presentation Award at IEEE VNC 2018.

    Host: Dr Murali Annavaram, annavara@usc.edu

    Webcast: https://usc.zoom.us/j/93387896454?pwd=MVdwL2NHS1hqSXFlaFhPaE91WHVGUT09

    More Information: ECE Seminar Announcement 03.23.2023 - Stephen Xia.pdf

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 248

    WebCast Link: https://usc.zoom.us/j/93387896454?pwd=MVdwL2NHS1hqSXFlaFhPaE91WHVGUT09

    Audiences: Everyone Is Invited

    Contact: Miki Arlen

  • NL Seminar-Designing and Evaluating Language Models for Human Interaction

    Thu, Mar 23, 2023 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars

    Speaker: Mina Lee, Stanford University

    Talk Title: Designing and Evaluating Language Models for Human Interaction

    Series: NL Seminar

    Abstract: REMINDER

    Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you are highly encouraged to use your USC account to sign into Zoom.

    If you are an outside visitor, please inform us at nlg DASH seminar DASH host AT isi DOT edu beforehand so we will be aware of your attendance and let you in.

    Despite the recent advancements in language models LMs, most LMs are not optimized for, nor are they evaluated on, real-world usage with human interaction. In this talk, I will present my research on designing and evaluating LMs for human LM interaction. Concretely, I will first describe how we can support human editing needs by enabling any LM to perform text infilling at any position in a document i.e., fill in the blanks. I will then introduce CoAuthor, a platform for capturing human LM interaction in collaborative writing as rich, replayable, keystroke level interaction traces. With the platform, I demonstrate how collecting a large interaction dataset and analyzing the traces provide unique insights into LM capabilities regarding language, ideation, and collaboration. Lastly, I will propose a new framework, HALIE Human AI Language based Interaction Evaluation, that defines the components of interactive systems and evaluation metrics for human LM interaction beyond writing. I will conclude by discussing open challenges and future directions in this field.

    Biography: Mina Lee is a final year Ph.D. candidate at Stanford University, advised by Professor Percy Liang. Her research goal is to design and evaluate language models to enhance our productivity and creativity and understand how these models change the way we write. She has built various writing assistants, including an autocomplete system, a contextual thesaurus system, and a creative story writing system, as well as evaluated language models based on their ability to interact with humans and augment human capabilities.

    She was named one of MIT Technology Reviews Korean Innovators under 35 in 2022, and her work has been published in top tier venues in natural language processing e.g., ACL and NAACL, machine learning e.g., NeurIPS, and human computer interaction e.g., CHI. Her recent work on human AI collaborative writing received an Honorable Mention Award at CHI 2022 and was featured in various media outlets including The Economist.

    Host: Jon May and Justin Cho

    More Info: https://nlg.isi.edu/nl-seminar/

    Webcast: https://usc.zoom.us/j/93116592657

    Location: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689

    WebCast Link: https://usc.zoom.us/j/93116592657

    Audiences: Everyone Is Invited

    Contact: Pete Zamar

    Event Link: https://nlg.isi.edu/nl-seminar/

  • Semiconductors & Microelectronics Technology Seminar - Heng Wang, Thursday, March 23 at 11am in EEB 132

    Thu, Mar 23, 2023 @ 11:00 AM - 12:00 PM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars

    Speaker: Heng Wang, Illinois Institute of Technology

    Talk Title: The Thermoelectric Effect under Photon Excitation

    Series: Semiconductors & Microelectronics Technology

    Abstract: Thermoelectric phenomena allow energy conversion between heat and electricity, which can be used in energy harvesting, solid state refrigeration, and temperature regulation. The physical origin of these phenomena are well understood with semi-classic theories such as the Boltzmann transport theory. Carefully conducted experiments often reveal results as predicted by such theories. Nonetheless, carrier transport not only happens when the system is near thermal equilibrium, as for the case of thermoelectric phenomena, but also happens in excited systems with electrons far from thermal equilibrium. And this draws our interest over the past a few years. In this talk we will discuss the characteristic, the physical origin, and measurement strategies of the thermoelectric effect under photon excitation (which is one version of the photo-thermoelectric phenomena). We will discuss a few case studies, what can these results tell us about the materials, and potential applications. There are still much to understand with this effect and we hope this discussion could stimulate more interest and applications as well.

    Biography: Heng Wang is an assistant professor at department of Mechanical, Materials and Aerospace Engineering, Illinois Institute of Technology. He received his B.S. in materials science and engineering from Tsinghua University, China, and his PhD in materials science from California Institute of Technology. Before joining IIT he worked as a postdoctoral researcher at the Molecular Foundry, Lawrence Berkeley National Lab. He has over ten years of research experience in thermoelectric materials, physics, and devices, with more than 13000 citations. His current research interests include high-performance thermoelectric materials, as well as device design, manufacturing, and new applications. In addition, he is particularly interested in the interplay of photoelectric and thermoelectric phenomena.

    Host: J Yang, H Wang, C Zhou, S Cronin, W Wu, J. Ravichandran

    More Information: HengWang_0323.pdf

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132

    Audiences: Everyone Is Invited

    Contact: Marilyn Poplawski

  • CS Colloquium: Benjamin Eysenbach (CMU) - Self-Supervised Reinforcement Learning

    Thu, Mar 23, 2023 @ 11:00 AM - 12:00 PM

    Computer Science

    Conferences, Lectures, & Seminars

    Speaker: Benjamin Eysenbach , CMU

    Talk Title: Self-Supervised Reinforcement Learning

    Series: CS Colloquium

    Abstract: Reinforcement learning (RL) promises to harness the power of machine learning to solve sequential decision making problems, with the potential to enable applications ranging from robotics to chemistry. However, what makes the RL paradigm broadly applicable is also what makes it challenging: only limited feedback is provided for learning to select good actions. In this talk, I will discuss how we have made headway of this challenge by designing self-supervised RL methods, ones that can learn representations and skills for acting using unsupervised (reward-free) experience. These skill learning methods are practically-appealing and have since sparked a vibrant area of research. I will also share how we have answered some open theoretical questions in this area.

    This lecture satisfies requirements for CSCI 591: Research Colloquium

    Biography: Benjamin Eysenbach is a final-year PhD student at Carnegie Mellon University. His research has developed machine learning algorithms for sequential decision making. His algorithms not only achieve a high degree of performance, but also carry theoretical guarantees, are typically simpler than prior methods, and draw connections between many areas of ML and CS. Ben is the recipient of the NSF and Hertz graduate fellowships. Prior to the PhD, he was a resident at Google Research and studied math as an undergraduate at MIT.

    Host: Jyo Deshmukh

    Location: Olin Hall of Engineering (OHE) - 132

    Audiences: Everyone Is Invited

    Contact: Assistant to CS chair

  • CS Colloquium: Dr. Zhou Li (University of California Irvine) - Debugging the Fragmented DNS Infrastructure at Scale

    Thu, Mar 23, 2023 @ 04:00 PM - 05:20 PM

    Computer Science

    Conferences, Lectures, & Seminars

    Speaker: Dr. Zhou Li, University of California Irvine

    Talk Title: Debugging the Fragmented DNS Infrastructure at Scale

    Abstract: Domain Name System (DNS) is a fundamental infrastructure that supports almost all sorts of Internet activities. However, service failures and breach of DNS are not rare, and some even led to the shutdown of large data centers, though DNS was designed under the goals like resiliency from the very beginning. We argue that the root causes are that DNS infrastructure has become too fragmented and its protocols have become much more complex, so new research efforts are needed to harden the DNS infrastructure. In this talk, I'll describe our efforts in this direction. First, I'll talk about two new DNS attacks we identified under the settings of domain revocation and conditional resolution, and their implications. Second, I'll talk about how we measure the operational status of DNS-over-Encryption at a large scale. Finally, I'll conclude the talk with an outlook for DNS-related research.

    This lecture satisfies requirements for CSCI 591: Research Colloquium

    Biography: Zhou Li is an Assistant Professor at UC Irvine, EECS department, leading the Data-driven Security and Privacy Lab. Before joining UC Irvine, he worked as Principal Research Scientist at RSA Labs from 2014 to 2018. His research interests include Domain Name System (DNS), Graph Security analytics, Privacy Enhancement Technologies and Side-channel analysis. He received the NSF CAREER award, Amazon Research Award, Microsoft Security AI award and IRTF Applied Networking Research Prize.

    Host: Weihang Wang

    More Info: https://usc.zoom.us/j/92035174335?pwd=VzhKZ0xjM3A2SzFwOWsyRG1SQWpqUT09

    Location: Seeley G. Mudd Building (SGM) - 124

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/92035174335?pwd=VzhKZ0xjM3A2SzFwOWsyRG1SQWpqUT09