Select a calendar:
Filter August Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for the 2nd week of August
-
PhD Dissertation Defense - Haowen Li
Mon, Aug 05, 2024 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Controllable Trajectory Generation
Date and Time: Monday, August 5th, 2024: 1:00p -3:00p
Location: Ronald Tutor Hall of Engineering (RTH) - 306
Committee Members: Prof. Cyrus Shahabi (Chair), Prof. Bistra Dilkina, Prof. Marlon Boarnet and Prof. Xiong Li
Abstract: Accessing realistic human movements (aka trajectories) is essential for many application domains, such as urban planning, transportation, and public health (e.g., understanding the spread of an epidemic). However, due to privacy and commercial concerns, real-world trajectories are not readily available, giving rise to an important research area of generating synthetic but realistic trajectories. Traditional rule-based methods rely on predefined heuristics and distributions that fail to capture complicated transition patterns in human mobility. Inspired by the success of deep neural networks (DNN), data-driven methods learn underlying human decision-making mechanisms and generate synthetic trajectories by directly fitting real-world data. Despite this progress, existing approaches lack mechanisms to control the generation process, which prevents the incorporation of prior knowledge and the spatiotemporal specification of certain visits. This lack of control on the generated trajectories greatly limits their practical applicability. In addition, existing studies on trajectory mining applications often project GPS coordinates onto discrete geographical grids and time intervals. However, modeling human movements requires algorithms that can effectively capture inherently complex spatial and temporal dependencies and transforming trajectories into regular grids and time intervals cannot accurately model real-world trajectories with irregular moving patterns. This thesis addresses the above two shortcomings and proposed generation algorithms under various control settings.
In this thesis defense, I will present my work on controllable trajectory generation. I will first provide the motivations and review previous work on implicitly controlled trajectory generation via clustering. Subsequently, I will formally define the Constraint Trajectory Generation problem and our framework that operates within continuous spatiotemporal space, enabling the direct generation of geographical coordinates and the duration of each visit in a trajectory. In conclusion, I will discuss future directions for the development of trajectory generation models
Zoom Link: https://usc.zoom.us/j/98507965284?pwd=Kbx7MCqHVizVGOnTcgxLwQs04qe8Aa.1
Password: 1234Location: Ronald Tutor Hall of Engineering (RTH) - 306
Audiences: Everyone Is Invited
Contact: Haowen Li
Event Link: https://usc.zoom.us/j/98507965284?pwd=Kbx7MCqHVizVGOnTcgxLwQs04qe8Aa.1
-
AI Seminar- Composable Interventions for Language Models
Fri, Aug 09, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Arinbjorn Kolbeinsson, University of Virginia
Talk Title: Composable Interventions for Language Models
Abstract: Virtual zoom link: https://usc.zoom.us/j/7042850182?pwd=OTQ3aW9LUjErTC9iWGRFQUg0LzlOdz09&omn=96405030645Meeting ID: 704 285 0182Meeting password: 832239
Abstract: Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. In practice, multiple interventions must be applied sequentially to the same model, yet we lack standardized ways to study how interventions interact. We fill this gap by introducing composable interventions, a framework to study the effects of using multiple interventions on the same language models, featuring new metrics and a unified codebase. Using our framework, we conduct extensive experiments and compose popular methods from three emerging intervention categories — Knowledge Editing, Model Compression, and Machine Unlearning. Our results from 310 different compositions uncover meaningful interactions: compression hinders editing and unlearning, composing interventions hinges on their order of application, and popular general-purpose metrics are inadequate for assessing composability. Taken together, our findings showcase clear gaps in composability, suggesting a need for new multi-objective interventions. All of our code is public: https://github.com/hartvigsen-group/composable-interventions
Biography: Arinbjörn Kolbeinsson is currently serving as a visiting scholar at the University of Virginia, focusing on responsible and accurate models for health and biomedicine. His recent research explores the editing and efficiency of language models, along with the development of composable intervention techniques. Previously, Arinbjörn was a machine learning scientist at Evidation Health Inc., where he developed innovative methods to predict health outcomes using high-frequency multi-modal data. His work was pivotal in advancing differential privacy, disease modeling, and reinforcement learning for health applications. Arinbjörn completed his Ph.D. in Biostatistics at Imperial College London in 2020, specializing in deep learning for health outcome prediction.
Host: Abel Salinas and Maura Covaci
More Info: https://www.isi.edu/events/5056/composable-interventions-for-language-models/
Webcast: https://usc.zoom.us/j/7042850182?pwd=OTQ3aW9LUjErTC9iWGRFQUg0LzlOdz09&omn=96405030645Location: Information Science Institute (ISI) - Virtual Only
WebCast Link: https://usc.zoom.us/j/7042850182?pwd=OTQ3aW9LUjErTC9iWGRFQUg0LzlOdz09&omn=96405030645
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://www.isi.edu/events/5056/composable-interventions-for-language-models/
