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
Thomas Lord Department of 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
-
DEN@Viterbi - Online Graduate Engineering Virtual Information Session
Tue, Jun 15, 2021 @ 09:00 AM - 10:00 AM
DEN@Viterbi, 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
-
Virtual 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
Contact: Viterbi Admission
-
DEN@Viterbi - Online Graduate Engineering Virtual Information Session
Wed, Jun 16, 2021 @ 06:00 PM - 07:00 PM
DEN@Viterbi, 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
-
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/TwE2m6Z991sLocation: Information Science Institute (ISI) - Virtual Only
WebCast Link: https://youtu.be/TwE2m6Z991s
Audiences: Everyone Is Invited
Contact: Petet Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
Virtual 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
Contact: Viterbi Admission
-
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=Rlg3UUkzTTljVDdQSHpEZ04vWkdPQT09Audiences: Exclusive to Summer Start students
Contact: Juli Legat
-
PhD Defense - Sungyong Seo
Fri, Jun 18, 2021 @ 01:00 PM - 02:30 PM
Thomas Lord Department of 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
-
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 hereAudiences: Exclusive to Summer Start students
Contact: Juli Legat