Select a calendar:
Filter December Events by Event Type:
SUNMONTUEWEDTHUFRISAT
University Calendar
Events for December
-
PhD Thesis Defense - Gautam Salhotra
Tue, Dec 05, 2023 @ 03:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Defense - Gautam Salhotra
Committee Members: Gaurav Sukhatme (chair), Somil Bansal, Daniel Seita
Title: Accelerating Robot Manipulation with demonstrations
Abstract: Robot manipulation of complex objects, such as cloth, is challenging due to difficulties in perceiving and exploring the environment. Pure reinforcement learning (RL) is difficult in this setting, as it requires extensive exploration of the state space, which can be inefficient and dangerous. Demonstrations from humans can alleviate the need for exploration, but collecting good demonstrations can be time-consuming and expensive. Therefore, a good balance between perception, exploration, and imitation is needed to solve manipulation of complex objects.This thesis focuses on dexterous manipulation of complex objects, such as cloth, using images and without assuming full state information during inference. It also aims to achieve efficient learning by reducing interactions with the environment during exploration and reducing the overhead of collecting demonstrations. To achieve these goals, we present i. a learning algorithm that uses a motion planner in the loop, to enable efficient long horizon exploration, ii. A framework for visual manipulation of complex deformable objects using demonstrations from a set of agents with different embodiments. iii. An LfD algorithm for dexterous tasks with rigid objects, such as peg insertion with high precision, using images and a multi-task attention-based architecture.These contributions enable robots to manipulate complex objects efficiently and with high precision, using images alone. This opens up new possibilities for robots to be used in a wider range of applications, such as manufacturing, logistics, and healthcareLocation: Ronald Tutor Hall of Engineering (RTH) - 406
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
-
PhD Thesis Proposal - Nathan Bartley
Wed, Dec 06, 2023 @ 12:00 PM - 01:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Nathan Bartley Committee Members:
Kristina Lerman (chair)
Mike Ananny
Emilio Ferrara
red Morstatter
Barath Raghavan
Title: Content Exposure Bias and Online Social Networks
Abstract: Online social platforms employ personalized feed algorithms to gather and collate messages from accounts users follow. However, the network structure and activity of the followed users distorts content’s perceived popularity prior to personalization. We call this “exposure bias:” our research focuses on quantifying it using diverse metrics, and we evaluate different algorithms that underpin personalized feeds with these metrics. We use empirical X/Twitter data and simulations in a network to assess the influence different feeds have on exposure bias. Furthermore we are working on agent-based model simulations to comprehend the impact of changing feeds, with the ultimate goal of making interventions.
Location: https://usc.zoom.us/j/98609708157?pwd=VWJuMVROL3Z5YVZmWDFWQ2xRRzNOUT09
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/98609708157?pwd=VWJuMVROL3Z5YVZmWDFWQ2xRRzNOUT09
-
PhD Thesis Defense - Tiantian Feng
Mon, Dec 11, 2023 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Defense - Tiantian Feng
Committee Members: Professor Shrikanth Narayanan, Professor Aiichiro Nakano, Professor Kristina Lerman, and Professor Morteza Dehghani (external)
Title: Foundation Model Assisted Privacy-Enhancing Computing in Human-centered Machine Intelligence
Abstract: Human-centered machine intelligence has revolutionized many leading domains, ranging from transportation and healthcare to education and defense, profoundly changing how people live, work, and interact with each other. These systems utilize state-of-the-art machine learning (ML) algorithms to achieve a deeper understanding of human conditions, such as state, trait, and interactions, which provide possibilities to create technologies that increasingly support and enhance human experiences. Despite promises human-centric ML systems deliver, they create critical risks in potentially leaking sensitive information that people might want to keep private. The sensitive information can be individual attributes (e.g., age, gender), states (e.g., health, emotions), or biometric fingerprints. In this thesis, I explore privacy-enhancing computation associated with human-centered ML. My thesis investigates established approaches to preserve privacy in diverse human-centered applications. However, we identify that these approaches are frequently ineffective when encountering low-resource data due to privacy restrictions in sensing, storing, and using such data. Concurrently, the foundation model is a rapidly evolving research field, leading to the success of modern generative AI capable of creating realistic and high-fidelity digital content. These advances in foundation models and generative AI also present opportunities for privacy-enhancing computing as high-quality generated content can serve as training data. This leads us to explore using the foundation model to generate training data to assist low-resource training encountered with sensitive data in human-centered applications. Our extensive experiments demonstrate the potential of the foundation model in assisting low-resource training caused by privacy constraints in obtaining human-centered signals.Location: Ronald Tutor Hall of Engineering (RTH) - 320
Audiences: Everyone Is Invited
Contact: CS Events
-
PhD Thesis Defense - Kexuan Sun
Wed, Dec 13, 2023 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
Committee members:
Prof. Jay Pujara
Prof. Aiichiro Nakano
Prof. Gerard Hoberg
Title: Advances in Understanding and Leveraging structured data for knowledge-intensive tasks
Abstract: Over the past few decades, the Web has evolved into an essential information hub. Among the vast repository of information, structured data, including well-organized tables, charts, and knowledge graphs, distinguishes itself as a valuable source of knowledge. This dissertation investigates techniques for understanding and harnessing such structured data to enhance knowledge-intensive applications. The first part of the dissertation focuses on tabular data. I first investigate approaches for understanding complex table structures by introducing an automated hybrid probabilistic system that identifies sub-structures within tables and their relationships, offering potential benefits for downstream tasks like data integration. I then explore approaches for selecting valuable information to answer questions relying heavily on financial tables. We approach this task by leveraging case-based reasoning, adapting solutions from existing questions to answer new questions effectively. The second part of the dissertation delves into the realm of KGs. I begin by investigating scientific KGs construction and empirically explore techniques that combine inherent graph structures and external entity-associated information. Additionally, I introduce a novel approach for accurately selecting important information from KGs to answer general-domain questions. These advances are necessary to fully exploit multi-source integrated systems that leverage unstructured and structured information together for knowledge delivery.Location: Hughes Aircraft Electrical Engineering Center (EEB) - 203
Audiences: Everyone Is Invited
Contact: CS Events
-
Thesis Proposal (Zihao He)
Wed, Dec 13, 2023 @ 03:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
Committee members:
Kristina Lerman (Chair)
Emilio Ferrara
Jonathan May
Fred Morstatter
Marlon Twyman
Title: Exploring Polarization and Ideological Difference of Online Communities Through Language Models
Abstract: The proliferation of diverse information sources and social platform interactions has led to increased ideological polarization, presenting unique challenges in understanding and quantifying these divides. This thesis tackles the nuanced task of analyzing ideological polarization of online communities through language models. First, I extract contextualized topic embeddings from a pretrained language model, focusing on identifying polarized topics within various information sources. Next, I use a generative language model to probe into the ideological dimensions within social media discourse, specifically examining Twitter conversations around key political figures; this approach uncovers the complexities within user interactions and the formation of opinion clusters. Finally, I investigate the alignment between the affective responses of large language models and human ideologies.Location: Hughes Aircraft Electrical Engineering Center (EEB) - 131A
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/98773410609?pwd=SXQzekVMZjZ6dVhSdWJCRGlrVlFFZz09
