Logo: University of Southern California

Events Calendar



Select a calendar:



Filter June Events by Event Type:



Events for the 3rd week of June

  • PhD Defense - Xusen Yin

    Mon, Jun 14, 2021 @ 01:30 PM - 03:00 PM

    Computer Science

    University Calendar


    PhD Candidate: Xusen Yin
    Date: June 14, 2021
    Time: 1:30-3pm
    Zoom Link:

    https://usc.zoom.us/j/98248745757?pwd=VDcvWHpWT0tLSCs0eldsRjhwVGh3UT09

    Title:
    Generalized Sequential Decision-Making via Language

    Committee: Jon May (Chair), Sven Koenig, Shri Narayanan

    Abstract:

    Many interactive applications, e.g., negotiation, game-playing, personal assistants, and online customer service, require sequential decision-making over natural language communications, a novel but fast-growing domain in Natural Language Processing (NLP).

    Unlike other NLP tasks that deal with single sentences or documents---e.g., question answering, machine translation, and sentiment analysis---sequential decision making requires language understanding and inference over sequences of sentences or documents. Moreover, there is usually no direct training objective for these applications compared to typical machine learning tasks. Thus, these tasks require a search in a decision-making space.

    Deep Reinforcement Learning (RL) is a common choice for these tasks without explicit or direct targets. It ordinarily needs many iterations to get close to an actual target due to the demand of exploration in the tremendous search space induced by near-infinite natural language responses in dialogue. These explorations usually are composed of many random movements, especially in the initial RL training stage.

    However, when placed in an unfamiliar environment, humans know how to solve new problems by applying existing knowledge and skills rather than working randomly. In contrast, computer agents struggle in these new scenarios due to overfitting and lack of common sense.

    Can we generalize sequential decision-making agents to novel, even unrelated tasks under the medium of language? We show how to train agents that take beneficial decision sequences from experience and external knowledge for better generalization than standard RL algorithms, using text-based games as a demo environment. We find out that proper dialogue encoding helps the intent understanding, that turning instance knowledge into universal knowledge helps in-domain generalization, that large language models can provide external knowledge rather than learning everything from scratch. Finally, we show that fine-tuned large language models with decision-making ability from one domain can guide RL algorithms towards better exploration and generalization for cross-domain transfer.

    WebCast Link: https://usc.zoom.us/j/98248745757?pwd=VDcvWHpWT0tLSCs0eldsRjhwVGh3UT09

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal
  • DEN@Viterbi - Online Graduate Engineering Virtual Information Session

    Tue, Jun 15, 2021 @ 09:00 AM - 10:00 AM

    Distance Education Network, Viterbi School of Engineering Graduate Admission

    Workshops & Infosessions


    Join USC Viterbi School of Engineering for a virtual information session via WebEx, providing an introduction to DEN@Viterbi, our top ranked online delivery system. Discover the 40+ graduate engineering and computer science programs available entirely online.

    Attendees will have the opportunity to connect directly with USC Viterbi representatives during the session to discuss the admission process, program details and the benefits of online delivery.

    Register Today!

    WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=e268e282e9c56ed5ad668820dfbbb122f

    Audiences: Everyone Is Invited

    Contact: Corporate & Professional Programs

    OutlookiCal
  • Repeating EventVirtual First-Year Admission Information Session

    Tue, Jun 15, 2021 @ 04:00 PM - 05:00 PM

    Viterbi School of Engineering Undergraduate Admission

    Workshops & Infosessions


    Our virtual information session is a live presentation from a USC Viterbi admission counselor designed for high school students and their family members to learn more about the USC Viterbi undergraduate experience. Our session will cover an overview of our undergraduate engineering programs, the application process, and more on student life. Guests will be able to ask questions and engage in further discussion toward the end of the session.

    Please Register Here!

    Audiences: Everyone Is Invited

    View All Dates

    Contact: Viterbi Admission

    OutlookiCal
  • DEN@Viterbi - Online Graduate Engineering Virtual Information Session

    Wed, Jun 16, 2021 @ 06:00 PM - 07:00 PM

    Distance Education Network, Viterbi School of Engineering Graduate Admission

    Workshops & Infosessions


    Join USC Viterbi School of Engineering for a virtual information session via WebEx, providing an introduction to DEN@Viterbi, our top ranked online delivery system. Discover the 40+ graduate engineering and computer science programs available entirely online.

    Attendees will have the opportunity to connect directly with USC Viterbi representatives during the session to discuss the admission process, program details and the benefits of online delivery.

    Register Today!

    WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=e6f43f126ee97eb27f832778f2dab256e

    Audiences: Everyone Is Invited

    Contact: Corporate & Professional Programs

    OutlookiCal
  • NL Seminar PREFIX TUNING: OPTIMIZING CONTINUOUS PROMPTS FOR GENERATION

    Thu, Jun 17, 2021 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars


    Speaker: Xiang Lisa Li, Stanford Unversity

    Talk Title: PREFIX-TUNING: OPTIMIZING CONTINUOUS PROMPTS FOR GENERATION

    Series: NL Seminar

    Abstract: Fine tuning is the de facto way of leveraging large pre trained language models for downstream tasks. However, fine tuning modifies all the language model parameters and therefore necessitates storing a full copy for each task. In this paper, we propose prefix tuning, a lightweight alternative to fine tuning for natural language generation tasks, which keeps language model parameters frozen and instead optimizes a sequence of continuous task specific vectors, which we call the prefix. Prefix tuning draws inspiration from prompting for language models, allowing subsequent tokens to attend to this prefix as if it were virtual tokens. We apply prefix tuning to GPT 2 for table to text generation and to BART for summarization. We show that by modifying only 0.1 percent of the parameters, prefix tuning obtains comparable performance in the full data setting, outperforms fine tuning in low data settings, and extrapolates better to examples with topics that are unseen during training.

    Biography: Xiang Lisa Li is a first year PhD student in computer science at Stanford University, advised by Percy Liang and Tatsunori Hashimoto. She works on controllable text generation/decoding and efficient adaptation of pre trained language models. Lisa is supported by a Stanford Graduate Fellowship and is the recipient of an EMNLP Best Paper award.





    Host: Jon May and Mozhdeh Gheini

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

    Webcast: https://youtu.be/TwE2m6Z991s

    Location: Information Science Institute (ISI) - Virtual Only

    WebCast Link: https://youtu.be/TwE2m6Z991s

    Audiences: Everyone Is Invited

    Contact: Petet Zamar

    OutlookiCal
  • Repeating EventVirtual First-Year Admission Information Session

    Thu, Jun 17, 2021 @ 04:00 PM - 05:00 PM

    Viterbi School of Engineering Undergraduate Admission

    Workshops & Infosessions


    Our virtual information session is a live presentation from a USC Viterbi admission counselor designed for high school students and their family members to learn more about the USC Viterbi undergraduate experience. Our session will cover an overview of our undergraduate engineering programs, the application process, and more on student life. Guests will be able to ask questions and engage in further discussion toward the end of the session.

    Please Register Here!

    Audiences: Everyone Is Invited

    View All Dates

    Contact: Viterbi Admission

    OutlookiCal
  • Viterbi MS Orientation for Summer Start 2

    Thu, Jun 17, 2021 @ 05:00 PM - 07:00 PM

    Viterbi School of Engineering Masters Programs

    Student Activity


    The New Student Welcome is a mandatory live virtual event to start your first semester with a good foundation and prepare you for success. You will meet the VASE Master's Student Affairs Team, as well as your Academic Department Advisors, and have an opportunity to network with other students.
    Zoom link: https://usc.zoom.us/j/92111976242?pwd=Rlg3UUkzTTljVDdQSHpEZ04vWkdPQT09

    Audiences: Exclusive to Summer Start students

    Contact: Juli Legat

    OutlookiCal
  • PhD Defense - Sungyong Seo

    Fri, Jun 18, 2021 @ 01:00 PM - 02:30 PM

    Computer Science

    University Calendar


    PhD Candidate: Sungyong Seo

    Committee: Prof. Yan Liu (chair), Prof. Xiang Ren, Prof. Antonio Ortega

    Date: June 18th, 2021
    Time: 1:00-2:30pm
    Zoom Link: https://usc.zoom.us/j/7346393285

    Title: Physics-aware Graph Networks for Spatiotemporal Physical Systems

    Abstract:
    While deep neural networks have been successful over a number of applications, it is still challenging to achieve a robust model for physical systems since data-driven learning does not explicitly consider physical knowledge, which should be beneficial for modeling. To leverage domain knowledge for robust learning, I propose various novel methods to incorporate physical knowledge for modeling spatiotemporal observations from physical systems. First, in my talk, I quantify data quality inspired by physical properties of fluids to identify abnormal observations and improve forecasting performance. The second work proposes a regularizer to explicitly impose partial differential equations (PDEs) associated with physical laws to provide an inductive bias in the latent space. The third method focuses on the approximation of spatial derivatives, which are one of the fundamental components of spatiotemporal PDEs. Then, I demonstrate a meta-learning framework to prove that the physics-related quantity is beneficial for fast-adaptation of learnable models on few observations. Finally, I propose spatiotemporal modeling via physics-aware causality, which leverages additional causal information described in PDEs for physical systems. All methods share a common goal: how to integrate physical knowledge with graph networks to model sensor-based physical systems by providing a strong inductive bias.

    WebCast Link: Link: https://usc.zoom.us/j/7346393285

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal
  • Experience Viterbi App Zoom Party

    Fri, Jun 18, 2021 @ 06:00 PM - 07:00 PM

    Viterbi School of Engineering Masters Programs

    Student Activity


    Learn more about the web app and the four success areas, receive insider app tips from current student users, and play an interactive game for a chance to win prizes! Unlock the tools you need for a successful school year. It's an event you won't want to to miss!
    RSVP here

    Audiences: Exclusive to Summer Start students

    Contact: Juli Legat

    OutlookiCal