Logo: University of Southern California

Events Calendar



Select a calendar:



Filter September Events by Event Type:



University Calendar
Events for September

  • PhD Thesis Proposal - Jiao Sun

    Mon, Sep 11, 2023 @ 03:30 PM - 05:30 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Proposal - Jiao Sun

    Committee Members: Xuezhe (Max) Ma (Chair), Nanyun (Violet) Peng, Johnathan May, Cyrus Shahabi, O Leary Dan

    Title: Discovering and Addressing the Pitfalls in Practical Text Generation

    Abstract: Research in language models has advanced at an incredible place, to the point where it is making its way to our daily lives of not only NLP researchers but also outsiders. However, there are some pitfalls that will hurt the utility of generative models and even exclude certain groups from using such models. In this talk, I will do a thorough reality check for each stage of text generation: data, model, and evaluation, and ask three main questions: how will data quality impact the utility of generation? Are we building the right models for the right purpose? How reliable are current evaluation metrics? I will ground these questions by my recent works on investigating the utility of free form rationales, a brand new set up for pun generation and dialect robust evaluation of generated text. In final remarks, I will discuss some future research perspectives on building trustworthy generation systems.

    Location: Ronald Tutor Hall of Engineering (RTH) - 306

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/my/jiaosun

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • DREAM Industry Mentorship speaker series

    Thu, Sep 14, 2023 @ 12:30 PM - 01:30 PM

    USC Viterbi School of Engineering

    University Calendar


    DREAM (Direct Response to Engineers Aspirations from Mentors) is a mentorship initiative which connects students to high profile industry professionals relevant to students dream pitches, an original leadership communication assignment where students create a vision for their future selves, align their careers around purpose, and build character in the context of growth, reinvention, and constant change. Industry mentors serve as moral exemplars as they discuss how professional challenges present opportunities for character and leadership development. Guest speakers and panels feature experienced professionals from a variety of tech and destination companies.

    This event will feature talks with Viterbi M.S. alumni Justene Karimi and Edgar Vargas about how they found career purpose in aerospace and their evolving roles as engineers and managers at Boeing.

    Location: Michelson Center for Convergent Bioscience (MCB) - 102

    Audiences: Everyone Is Invited

    Contact: Elisabeth Arnold Weiss

    Event Link: https://cglink.me/2nB/r391353

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Proposal - Sabyasachee Baruah

    Mon, Sep 18, 2023 @ 02:00 PM - 04:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Proposal - Sabyasachee Baruah

    Committee Members: Shrikanth Narayanan (Chair), Jonathan May, Kristina Lerman, Emilio Ferrara, and Morteza Dehghani

    Title: Character Resolution and Attribution for Narrative Understanding

    Abstract: Narrativity is a mechanism through which human beings try to understand the world. We computationally define it as characters interacting with each other during events that relate in time and space. We propose a computational pipeline for narrative understanding and discuss its character centric aspects, resolution and attribution of characters. We contribute computational models and novel datasets towards these tasks in both the textual and visual domain. We work towards scaling our methods to long and multimodal narratives, and analyze how they portray characters across different attribute types and time.

    Location: Ronald Tutor Hall of Engineering (RTH) - 320

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/97813866730?pwd=dHRBUG1aQjJJTmxsS1d5ajhNMFZCQT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PHD Thesis Proposal (Shushan Arakelyan)

    Tue, Sep 19, 2023 @ 02:00 PM - 03:30 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Thesis proposal committee members:
    Xiang Ren (Chair)
    Nenad Medvidovic
    Weihang Wang
    Jay Kuo
    Mukund Raghothaman

    Abstract:
    Successful deployment of any AI model requires generalization to previously unseen, real-world scenarios. Lack of generalization in models can lead to outcomes ranging from reduced performance to potential legal liabilities. In this thesis, I explore generalization challenges in large language models for code processing. I will discuss three different generalization concerns that language models for code processing can exhibit, and present my progress in building models that can overcome those. 1) I will start by discussing compositional generalization issues, where models must adapt to previously unseen instruction combinations 2) Next I will talk about out-of-domain generalization, and how distribution shifts within single projects or corporations can affect model performance, and how to overcome it. 3) Finally, I will talk about generalization of advanced models to programming languages with fewer resources.

    Location: https://usc.zoom.us/j/7195147935?pwd=SU5oS1MrQUxURC9tSFd2Y3VuUDdoQT09

    Audiences: Everyone Is Invited

    Contact: Asiroh Cham

    Event Link: https://usc.zoom.us/j/7195147935?pwd=SU5oS1MrQUxURC9tSFd2Y3VuUDdoQT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Dissertation Defense - Ali S. Alotaibi

    Wed, Sep 20, 2023 @ 01:00 PM - 03:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Dissertation Defense - Ali S. Alotaibi

    Committee Members: William GJ Halfond (chair), Nenad Medvidovic, Mukund Raghothaman, Gisele Ragusa, and Chao Wang

    Title: Automated Repair of Layout Accessibility Issues in Mobile Applications

    Abstract: An increasing number of people are now dependent on mobile devices to access data and complete essential tasks. For people with disabilities, mobile apps that violate accessibility guidelines can prevent them from carrying out these activities. Layout accessibility issues are among the top accessibility issues in mobile applications. These issues impact the accessibility of mobile apps and make them difficult to use, especially for older people and people with disabilities. Unfortunately, existing techniques are limited in helping developers debug these issues. These techniques are only capable of detecting the issues but cannot help to repair them. Therefore, the repair of layout accessibility issues remains a manual process, which is both labor intensive and error prone.

    Automated repair of layout accessibility issues is complicated by several challenges. First, a repair must account for multiple issues holistically in order to preserve the relative consistency of the original app design. Second, due to the complex relationship between UI components, there is no clear way of identifying the set of elements and properties that need to be modified for a given issue. Third, assuming the relevant views and properties can be identified, the number of possible changes that need to be considered grows exponentially as more elements and properties need to be considered. Finally,
    a change in one element can create cascading changes that lead to further problems in other areas of the UI. Together, these challenges make a seemingly simple repair difficult to achieve. In this dissertation, I present an automated framework for repairing layout accessibility issues in mobile applications. To evaluate the effectiveness of this framework, I instantiated it to repair the different types of layout accessibility issues. I assessed the effectiveness of these instantiations by using them to repair issues detected in real world mobile apps. In addition, I conducted user studies to evaluate the impact of the repairs on the quality of the UIs of mobile apps. The results from these evaluations show that these techniques are effective in improving the accessibility of mobile apps without negatively impacting or distorting the UIs.

    Location: Charles Lee Powell Hall (PHE) - 325

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Dissertation Defense - Setareh Nasihati Gilani

    Tue, Sep 26, 2023 @ 03:00 PM - 05:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Dissertation Defense - Setareh Nasihati Gilani

    Committee Members: David Traum (Chair), Maja Mataric, Peter Kim, Kallirroi Georgila, Mohammad Soleymani

    Title: Understanding and Generating Multimodal Feedback in Human Machine Story Telling

    Abstract: People use feedback, verbal or nonverbal, from their interlocutors to guide their own behavior and alter the flow of conversation. In this thesis, we focus on human machine interactions that involve storytelling and investigate the role of understanding and providing feedback from the machines perspective. We explored the characteristics of stories that machines should use to increase rapport. We developed machine storytellers and listeners that can provide feedback and adapt their stories based on perceived multimodal feedback from their users. Finally, we investigated how machines can use real time predictions based on user feedback to further adapt the dialogue management policies of the system for better overall performance.

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/93206733633

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Proposal - Taoan Huang

    Tue, Sep 26, 2023 @ 03:30 PM - 05:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Proposal - Taoan Huang

    Committee Members: Sven Koenig (co chair), Bistra Dilkina (co chair), Jyotirmoy Deshmukh, Stefanos Nikolaidis, John Carlsson, Peter Stuckey from Monash University

    Title: Improving Decision Makings in Search Algorithms with Machine Learning for Combinatorial Optimizations

    Abstract: Designing algorithms for combinatorial optimization problems (COP) are important and challenging tasks since it concerns a wide range of real world problems, such as vehicle routing, path planning and resource allocation problems. Most COPs are NP hard to solve and many research algorithms have been developed for them in the past few decades. Decision makings such as partitioning or pruning the search space and prioritizing exploration in the search space, are crucial to the efficiency and effectiveness of the search algorithms. Many of those heavily rely on domain expertise and human designed strategies.

    In this thesis, we hypothesize that one can leverage machine learning to improve human designed decision making strategies in different categories of search algorithms for combinatorial optimization problems. We validate the hypothesis on the problems of multiagent path finding and solving mixed integer linear programs, introducing different machine learning techniques to advance a few state of the art optimal and heuristic search algorithms for the two problems.

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/92825821724?pwd=a2RFY0x0QzV0S3hqYmkxakJvQUpYZz09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Thesis Proposal - Alan Romano

    Thu, Sep 28, 2023 @ 09:30 AM - 11:00 AM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Proposal - Alan Romano

    Committee Members: Weihang Wang (chair), William Halfond, Nenad Medvidovic, Pierluigi Nuzzo, Chao Wang

    Title: WAF: A Multi Purpose Static Program Analysis Framework for WebAssembly

    Abstract: WebAssembly is a recent standard for the web that aims to enable high performance web applications that can run at near native speeds. The standard has gained attention in both academia and industry for its ability to speed up existing user facing web applications. However, we have encountered several limitations in the static program analysis tools of the current WebAssembly ecosystem. We find that current program optimizations applied on WebAssembly modules may lead to diminished performance. We also identify a lack of tools that help developers understand WebAssembly modules through robust binary decompilation. Finally, we find a gap in the ability to analyze cross language WebAssembly applications across the two languages they are typically implemented in, i.e., WebAssembly and JavaScript.

    In this thesis, we present a novel WebAssembly Analysis Framework, or WAF. WAF is a static program analysis framework for WebAssembly modules that consists of multiple intermediate representations. Inspired by frameworks made for Java, the core of our framework lies in our three intermediate representations that each model the WebAssembly module at a different semantic level. This structure enables WAF to serve in multiple use cases, including program optimizations, binary decompilation, cross language program analysis, and malware detection. We aim to show that our framework can improve static program analysis in the areas that the WebAssembly ecosystem is lacking

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/98399405992?pwd=ME1ENk9QL2V1bmdXZld2K0psV2p6Zz09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Dissertation Defense - David Millard

    Fri, Sep 29, 2023 @ 03:00 PM - 05:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Dissertation Defense - David Millard

    Committee Members: Gaurav Sukhatme (chair), Lars Lindemann, Somil Bansal

    Title: Augmented Simulation Techniques for Robotic Manipulation

    Abstract: The development and application of capable robot manipulators require advances in world modeling and simulation. This thesis provides a comprehensive overview of our work in simulation methodologies, covering diverse physical phenomena and target applications, and with augmented structures that make associated computation tractable. First, we present work in rigid body dynamics with contact, augmented for fast computation of first and second order derivatives and probability distributions, and present applications to parameter estimation and control. We then present work in soft object modeling and control, first by using differentiable solid mechanics for constrained parameter estimation and then by machine learning based predictive control. Finally, we present work on GPU accelerated parallel Discrete Element Methods DEM and their applicability to the challenges of robotic sampling and excavation. To demonstrate the translational utility of this work, we present results from several methodologies from real data or on real hardware

    Location: Ronald Tutor Hall of Engineering (RTH) - 105

    Audiences: Everyone Is Invited

    Contact: Melissa Ochoa

    Event Link: https://usc.zoom.us/j/97228913263?pwd=aitNWjk3VjlmcnBEcmlERURDY1kwUT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File