Select a calendar:
Filter October Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for October 24, 2023
-
PhD Thesis Proposal - Xisen Jin
Tue, Oct 24, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Xisen Jin
Committee Members: Xiang Ren (advisor), Jesse Thomason, Robin Jia, Mahdi Soltanolkotabi, Jieyu Zhao
Title: Building Updatable Language Model Systems in the Wild
Abstract: Building updatable language model systems has become a crucial challenge alongside the progress of large language models. In this thesis proposal, I will present my efforts on creating resources, developing efficient methods, and analyzing learning dynamics in updating language models. I will introduce two of my past works, focused on lifelong pretraining of language models and fusing knowledge of multiple models by merging their weights. I will then introduce my on-going study of analyzing and forecasting examples that will be forgotten by model updates to reduce forgetting that happens during the process of model updates.Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/j/92405014194?pwd=RlpqYzNKejZEQ1J1alhQYjBqN3dNZz09
-
CAIS Webinar: Beyond Datasets – How the Small Decisions We Make Affect The Tools We Build
Tue, Oct 24, 2023 @ 12:00 PM - 01:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nyalleng Moorosi, Senior Researcher at DAIR
Talk Title: Beyond Datasets -“ How the Small Decisions We Make Affect The Tools We Build
Series: CS Colloquium
Abstract: Data and our understanding of correctness and ground truth are a function of our history, culture and our position in society. In this talk, I wish to share with you some of the often nondocumented decisions we make as builders of machine learning tools and how they challenge the theory of building for all
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Nyalleng Moorosi is a senior researcher at DAIR, and her research interests are in understanding how we can build models which center populations often regarded as peripheral.
Register for the Zoom webinar here: https://usc.zoom.us/webinar/register/WN_evMt4EB7S9SVoq0XVzJ1yw
Host: CAIS
More Info: https://usc.zoom.us/webinar/register/WN_evMt4EB7S9SVoq0XVzJ1yw
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/webinar/register/WN_evMt4EB7S9SVoq0XVzJ1yw
-
PhD Thesis Proposal - Ang Li
Tue, Oct 24, 2023 @ 02:00 PM - 03:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Ang Li
Committee Members: T. K. Satish Kumar (chair), Sven Koenig, Aiichiro Nakano, Emilio Ferrara, and John Carlsson
Title: Revisiting FastMap: New Applications
Abstract: FastMap was first introduced in the Data Mining community for generating Euclidean embeddings of complex objects. In this talk, I will first generalize FastMap to generate Euclidean embeddings of graphs in near-linear time: The pairwise Euclidean distances approximate a desired graph-based distance function on the vertices. I will then apply the graph version of FastMap to efficiently solve various graph-theoretic problems of significant interest in AI: including shortest-path computations, facility location, top-K centrality computations, and community detection and block modeling. I will also present a novel learning framework, called FastMapSVM, by combining FastMap and Support Vector Machines. I will then apply FastMapSVM to predict the satisfiability of Constraint Satisfaction Problems and to classify seismograms in Earthquake ScienceLocation: Hughes Aircraft Electrical Engineering Center (EEB) - 110
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/j/92891703811?pwd=MmhNQXJCY3ZhMTRlOGp0aWpBZkRsZz09
-
CS Colloquium: Feng Qian (USC / ECE) - Towards Robust and Resource-efficient Immersive Content Streaming
Tue, Oct 24, 2023 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Feng Qian, USC / ECE
Talk Title: Towards Robust and Resource-efficient Immersive Content Streaming
Series: Computer Science Colloquium
Abstract: Compared to delivering regular 2D videos, streaming immersive content such as 360-degree panoramic videos, volumetric videos, and virtual/mixed reality (VR/MR) content presents distinct challenges due to their intensive network and compute resource consumption. In this talk, I will detail our team's journey over the past five years to boost the robustness, resource efficiency, and user experience of immersive content streaming. Our high-level design principles include adapting to the network & compute resources, integrating viewers' motion patterns, and harnessing the power of AI through edge computing. Backed up with real prototype implementation and field trials, our efforts make it feasible to stream high-quality immersive content to commodity mobile devices such as untethered smartphones and entry-level VR/MR headsets.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Feng Qian is an associate professor in the Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering at the University of Southern California. His research interests cover the broad areas of intelligent mobile systems (including 5G/6G), virtual, augmented, and mixed reality (VR/AR/MR) systems, cross-layer system design & analysis, application & transport layer protocols, and real-world system measurement. He obtained his Ph.D. in Computer Science and Engineering from the University of Michigan. He received multiple awards including the AT&T Key Contributor Award, the Google Faculty Award, two ACM CoNEXT best paper awards (2016, 2018), the NSF CAREER Award, the Trustees Teaching Award, the DASH-IF Excellence Award, the Cisco Research Award, the ACM SIGCOMM Best Student Paper Award (2021), the Google Research Scholar Award, two ACM MobiCom best community paper awards (2022, 2023), and the Okawa Research Grant.
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
