Select a calendar:
Filter December Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for the 2nd week of December
-
PhD Dissertation Defense - Haiwei Chen
Mon, Dec 09, 2024 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Designing Neural Networks from the Perspective of Spatial Reasoning
Date: December 9, 2024
Time: 2:00 pm - 4:00 pm
Location: GFS 104
Committee: Yajie Zhao (Chair), Ramakant Nevatia, and Andrew Nealen
Abstract: All visual data, from image to CAD models, live in a 2D or 3D spatial domain. In order to understand and model the visual data, spatial reasoning has always been fundamental to computer vision algorithms. Naturally, the practice has been widely extended to the use of artificial neural networks built for visual analysis. The basic building blocks of a neural network - operators and representations - are means to learn spatial relationships and therefore are built with spatial properties. In this thesis, we present the designs of ``spatial-aware'' neural operators and representations in different application contexts, with a unique focus on how these design choices affect the spatial properties of the neural networks in a way that is beneficial for the tasks at hand. The first topic explored is the equivariance property, where a SE(3) equivariant convolutional network is designed for 3D pose estimation and scene registration. In this chapter, we show that the equivariant property of a convolutional neural network can be practically extended to higher dimensional space and proved highly effective for applications that are not only sensitive to translation, but also 3D rotations. The second topic explored is learning neural operators that approximate spatially continuous function in a pattern synthesis application context. In this chapter, we explore novel representations of periodic encoding and a continuous latent space for a generative network that is able to synthesize diverse, high-quality and continuous 2D and 3D patterns. The unique formulation allows the generative model to be at least 10 times faster and more memory efficient compared to previous efforts, and marked one of the earliest attempts to adopt the implicit network to the generative setting. The third topic explored is spatial awareness with regard to incomplete images, where a generative network model for image inpainting is designed based on restricting its receptive field. Combined with the generative transformer and the discrete latent codes, this novel paradigm demonstrates the effectiveness of separating analysis and synthesis in challenging image inpainting scenarios, as the resulted network model achieves state-of-the-art performance in both diversity and quality, when completing partial images with free-form holes occupying as large as 70\% of the image. I believe that the topics covered have contributed to a better understanding of neural operator and representation designs for both discriminative and generative learning in computer vision, from a perspective of identifying the effective ways of spatial reasoning for the targeted visual applications.Location: Grace Ford Salvatori Hall Of Letters, Arts & Sciences (GFS) - 104
Audiences: Everyone Is Invited
Contact: Ellecia Williams
-
World models beyond autoregressive next state prediction
Mon, Dec 09, 2024 @ 03:00 PM - 04:00 PM
Ming Hsieh Department of Electrical and Computer Engineering, Thomas Lord Department of Computer Science, USC School of Advanced Computing
Conferences, Lectures, & Seminars
Speaker: Abhishek Gupta, Ph.D., Assistant Professor of Computer Science and Engineering, Paul G. Allen School at the University of Washington
Talk Title: World models beyond autoregressive next state prediction
Series: CSC@USC/CommNetS-MHI Seminar Series
Abstract: Learned models of system dynamics provide an appealing way of predicting the future outcomes in a system, enabling downstream usage for planning or off-policy evaluation in applications such as robotics. However, the prevalent paradigm of autoregressive, next-state prediction in learning dynamics models is challenging to scale to environments with high dimensional observations and long horizons. In this talk, I will present alternative techniques for model learning that go beyond directly predicting next states. Firstly, we will discuss a reconstruction-free class of models that go beyond next-observation prediction by learning the evolution of task-directed latent representations for high dimensional observation spaces. We will then show how this can be generalized to learning a new class of models that avoid autoregressive prediction altogether by directly modeling long-term cumulative outcomes, while remaining task agnostic. In doing so, this talk will propose alternative ways of thinking about model learning that retain the benefits of transferability and efficiency from model-based RL, while going beyond next-state prediction.
Biography: Abhishek Gupta is an assistant professor of computer science and engineering at the Paul G. Allen School at the University of Washington. Prior to joining University of Washington, he was a post-doctoral scholar at MIT, collaborating with Russ Tedrake and Pulkit Agarwal. He completed his Ph.D. at UC Berkeley working with Pieter Abbeel and Sergey Levine, building systems that can leverage reinforcement learning algorithms to solve robotics problems. He is interested in research directions that enable directly performing reinforcement learning directly in the real world — reward supervision in reinforcement learning, large scale real world data collection, learning from demonstrations, and multi-task reinforcement learning. He has also spent time at Google Brain. He is a recipient of the NDSEG and NSF graduate research fellowships, and several of his works have been presented as spotlight presentations at top-tier machine learning and robotics conferences.
Host: Erdem Biyik
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Erdem Biyik
-
MHI - Physics Joint Seminar Series - Daniel Sank, Tuesday, December 10th at 2pm in EEB 248 & Zoom
Tue, Dec 10, 2024 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Daniel Sank, Quantum AI, Google
Talk Title: Fast and Orderly Decoherence: A Systems Engineering View of Superconducting Qubit Readout and Reset
Series: MHI Physics Joint Seminar Series
Abstract: This presentation is a systems engineer's look at the superconducting qubit system, with focus on the two parts where we need fast and orderly decoherence: readout and reset. We introduce the basic theory of operation of the transmon qubit with focus on readout and reset and discuss the constraints placed by these operations on the off-chip physical apparatus, including package, wiring, cryostat, and the control electronics. Then, we give an in-depth tour of the mechanism, known as Measurement Induced State Transitions (MIST), through which the readout process kicks the qubit out of the computational subspace and into so-called "leakage states" which are poisonous for quantum error correction. Finally, we bring everything together to show how we design devices to respect the constraints introduced by readout and reset while still performing with sufficient speed and accuracy to support quantum error correction.
Host: Quntao Zhuang, Eli Levinson-Falk, Jonathan Habif, Daniel Lidar, Kelly Luo, Todd Brun, Tony Levi, Stephan Haas
More Info: https://usc.zoom.us/j/92584409725
More Information: Daniel Sank -Dec 10.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
Event Link: https://usc.zoom.us/j/92584409725
-
Computer Science General Faculty Meeting
Wed, Dec 11, 2024 @ 12:00 AM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
*DATE UPDATED*
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty and staff only. Event details emailed directly to attendees.Location: Ginsburg Hall (GCS) - 107
Audiences: Invited Faculty Only
Contact: Julia Mittenberg-Beirao
-
PhD Thesis Proposal - Lee Kezar
Wed, Dec 11, 2024 @ 03:00 PM - 04:30 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Phonological Inductive Biases for Computationally Modeling American Sign Language
Date and Time: Tuesday, December 11 - 3:00pm - 4:30pm
Location: GFS 109
Committee: Jesse Thomason (chair), Laurent Itti, Jonathan May, Mike Ananny, Zed Sehyr
Abstract: Sign languages are used by millions of people internationally, yet language technologies commonly do not include them because there are insufficient data to train large neural models. In this presentation, I address to what extent linguistic priors, especially theories of phonology and lexical semantics, can help neural models learn American Sign Language from limited data. We show that learning to recognize phonological features (the location, movement, and configuration of the hands) in video data is a versatile and effective approach for ASL recognition and comprehension. Concretely, we show that phonological and semantic "knowledge infusion" can (a) increase sign recognition accuracy by 30%, (b) enable few- and zero-shot sign understanding, and (c) reduce sensitivity to signer demographics. Proposed work will address longstanding research questions in phonology (such as the number of movement phonemes) and apply our methods to ASL-to-English translation.Location: Grace Ford Salvatori Hall Of Letters, Arts & Sciences (GFS) - 109
Audiences: Everyone Is Invited
Contact: Lee Kezar
-
NL Seminar-Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
Thu, Dec 12, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Becca Dorn, USC/ISI
Talk Title: Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
Series: NL Seminar
Abstract: REMINDER: Meeting hosts only admit on-line guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom. If you’re an outside visitor, please inform us at (nlg-seminar-host(at)isi.edu) to make us aware of your attendance so we can admit you. Specify if you will attend remotely or in person at least one business day prior to the event. Provide your: full name, job title and professional affiliation and arrive at least 10 minutes before the seminar begins. If you do not have access to the 6th Floor for in-person attendance, please check in at the 10th floor main reception desk to register as a visitor and someone will escort you to the conference room location. Join Zoom Meeting https://usc.zoom.us/j/98709918457?pwd=sVnp7kgGtL42MLRYEPaGjofzrjJFHL.1 Meeting ID: 987 0991 8457 Passcode: 592675 Content moderation on social media platforms shapes the dynamics of online discourse, influencing whose voices are amplified and whose are suppressed. Recent studies have raised concerns about the fairness of content moderation practices, particularly for aggressively flagging posts from transgender and non-binary individuals as toxic. In this study, we investigate the presence of bias in harmful speech classification of gender-queer dialect online, focusing specifically on the treatment of reclaimed slurs. We introduce a novel dataset, QueerReclaimLex, based on 109 curated templates exemplifying non-derogatory uses of LGBTQ+ slurs. Dataset instances are scored by gender-queer annotators for potential harm depending on additional context about speaker identity. We systematically evaluate the performance of five off-the-shelf language models in assessing the harm of these texts and explore the effectiveness of chain-of-thought prompting to teach large language models (LLMs) to leverage author identity context. We reveal a tendency for these models to inaccurately flag texts authored by gender-queer individuals as harmful. Strikingly, across all LLMs the performance is poorest for texts that show signs of being written by individuals targeted by the featured slur (F1 ≤ 0.24). We highlight an urgent need for fairness and inclusivity in content moderation systems. By uncovering these biases, this work aims to inform the development of more equitable content moderation practices and contribute to the creation of inclusive online spaces for all users.
Biography: Rebecca Dorn is a PhD candidate at the University of Southern California's Information Science Institute where they are co-advised by Kristina Lerman and Fred Morstatter. Previously, they earned their B.S. in Computer Science at UC Santa Cruz, advised by Lise Getoor. Their research focuses on the intersection between AI fairness, natural language processing and computational social science. Lately, their focus has surrounded how NLP systems treat dialects of historically marginalized communities.
If speaker approves to be recorded for this NL Seminar talk, it will be posted on the USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI. Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/ For more information on the NL Seminar series and upcoming talks, please visit: https://www.isi.edu/research-groups-nlg/nlg-seminars/
Host: Jonathan May and Katy Felkner
More Info: https://www.isi.edu/research-groups-nlg/nlg-seminars/
Webcast: https://usc.zoom.us/j/98709918457?pwd=sVnp7kgGtL42MLRYEPaGjofzrjJFHL.1Location: Information Science Institute (ISI) - Conf Rm#689
WebCast Link: https://usc.zoom.us/j/98709918457?pwd=sVnp7kgGtL42MLRYEPaGjofzrjJFHL.1
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://www.isi.edu/research-groups-nlg/nlg-seminars/
-
MHI - Physics Joint Seminar Series - Karan Mehta, Friday, December 13th at 2pm in SSL 202
Fri, Dec 13, 2024 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Karan Mehta, Electrical and Computer Engineering, Cornell University
Talk Title: Enhanced Trapped-Ion Quantum Control with Integrated Photonics
Series: MHI Physics Joint Seminar Series
Abstract: Practical quantum information processing requires significant advances over current systems in error and robustness of basic operations, and in scale. Despite the fundamental promise of trapped atomic ion qubits, the optics required pose a major challenge in scaling. Interfacing low-noise atomic qubits with scalable integrated photonics [1] offers a route to scale, enabling extensibility while simultaneously lending robustness to noise in sensitive quantum operations [2]. Beyond scaling, though, such techniques further allow generation of optical field profiles enabling improvements to coherent and incoherent processes [3]. I will discuss modeling work from our group predicting substantially increased cooling rates as well as motional mode bandwidths for ground-state laser cooling in structured light fields [4], routes to quantum logic leveraging related ideas, and early results from recent foundry-fabricated trap devices with fully integrated delivery to realize these schemes. I will also touch on challenges and opportunities for novel photonic materials and devices motivated by atomic quantum systems. [1] K.K. Mehta, C.D. Bruzewicz, R. McConnell, R.J. Ram, J.M. Sage, and J. Chiaverini. "Integrated optical addressing of an ion qubit." Nature Nanotechnology 11, 1066-1070 (2016). [2] K.K. Mehta, C. Zhang, M. Malinowski, T.-L. Nguyen, M. Stadler, and J.P. Home. "Integrated optical multi-ion quantum logic." Nature 586, 533-537 (2020). [3] A. Ricci Vasquez, et al. "Control of an atomic quadrupole transition in a phase-stable standing wave." PRL 130, 133201 (2023). [4] Z. Xing and K.K. Mehta. "Trapped-ion laser cooling in structured light fields." arXiv: 2411.08844 (2024).
Biography: Karan Mehta received BS. Degrees from UCLA in Electrical Engineering and Physics in 2010 and completed his PhD in Electrical Engineering and Computer Science at MIT in 2017, with the support of a DOE Science Graduate Fellowship. From 2017 to 2021 he was an ETH Postdoctoral Fellow and subsequently senior scientist at ETH Zurich. He joined Cornell ECE in January of 2022 where he leads the Photonics and Quantum Electronics group. He is recipient of an NSF CAREER award and a Sloan Research Fellowship in Physics.
Host: Quntao Zhuang, Eli Levinson-Falk, Jonathan Habif, Daniel Lidar, Kelly Luo, Todd Brun, Tony Levi, Stephan Haas
More Information: Karan Mehta -Dec. 13.pdf
Location: Seaver Science Library (SSL) - 202
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
