Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for March 27, 2025
-
AME Special Seminar
Thu, Mar 27, 2025 @ 10:00 AM - 11:00 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Vickie Webster-Wood, Carnegie Mellon University
Talk Title: Biomimetic, Biohybrid, and Biodegradable: Robots for a sustainable future
Abstract: In the last century it was common to envision robots of the future as shining metal structures with rigid and halting motion. This imagery is in sharp contrast to the fluid and organic motion of living organisms that inhabit our natural world. As robotics has advanced, animals are often turned to for inspiration. However, the adaptability, complex control, and advanced learning capabilities observed in animals are not yet fully understood, and therefore have not been fully captured by current robotic systems. Furthermore, many of the mechanical properties and physical capabilities seen in animals have yet to be achieved in robotic platforms. In this talk, I will share efforts from my group in Biomimetic, Biohybrid, and Biodegradable robotics. By using neuromechanical models and bioinspired robots as tools for basic research we are developing new models of how animals achieve multifunctional, adaptable behaviors. Building on our understanding of animal systems and living tissues, our research in biohybrid robotics is enabling new approaches toward the creation of autonomous biodegradable living robots. Finally, by using farmable plant-based materials, we can now create robotic components that are fully degradable in natural environments. These robotic systems have future applications as sustainable platforms for medicine, search and rescue, and environmental monitoring of sensitive environments.
Biography: Vickie Webster-Wood is an Associate Professor in the Department of Mechanical Engineering at Carnegie Mellon University with courtesy appointments in the Department of Biomedical Engineering, the McGowan Institute of Regenerative Medicine, and the Robotics Institute. She is the director of the C.M.U. Biohybrid and Organic Robotics Group and has a long-term research goal to develop completely organic, biodegradable, autonomous robots. Research in the C.M.U. B.O.R.G. brings together bio-inspired robotics, tissue engineering, and computational neuroscience to study and model neuromuscular control and translate findings to the creation of renewable robotic devices. Dr. Webster-Wood completed her postdoc at Case Western Reserve University in the Tissue Fabrication and Mechanobiology Lab under the direction of Dr. Ozan Akkus. During her postdoc, Dr. Webster-Wood was supported by the T32 Training Grant in Musculoskeletal Research. She received her Ph.D. in Mechanical Engineering from the same institution as an N.S.F. Graduate Research Fellow in the Biologically Inspired Robotics Lab, during which time she was co-advised by Drs. Roger Quinn, Ozan Akkus, and Hillel Chiel. She received the NSF CAREER Award in 2021 and leads the SSymBioTIC MURI on Integrated Biohybrid Actuators team. She is also a co-PI of the N.S.F. NeuroNex Network on Communication, Coordination, and Control in Neuromechanical Systems (C3NS), and has received additional funding from the NSF Foundational Research in Robotics Program, a PITA grant from the Commonwealth of Pennsylvania, Department of Community and Economic Development, as well as funding from the PA Manufacturing Initiative, and the Manufacturing Futures Initiative.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Location: Olin Hall of Engineering (OHE) - 406
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar-MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
Thu, Mar 27, 2025 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Julie Kallini, Stanford University
Talk Title: MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
Abstract: 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 via ZOOM: https://usc.zoom.us/j/92986255795?pwd=mbJqNRr6isZBQ9mn643fgalO5gksDs.1 Meeting ID: 929 8625 5795 Passcode: 804448. Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level models like ByT5 attempt to address these concerns, they have not gained widespread adoption—processing raw byte streams without tokenization results in significantly longer sequence lengths, making training and inference inefficient. This work introduces MrT5 (MergeT5), a more efficient variant of ByT5 that integrates a token deletion mechanism in its encoder to dynamically shorten the input sequence length. After processing through a fixed number of encoder layers, a learned delete gate determines which tokens are to be removed and which are to be retained for subsequent layers. MrT5 effectively "merges" critical information from deleted tokens into a more compact sequence, leveraging contextual information from the remaining tokens. In continued pre-training experiments, we find that MrT5 can achieve significant gains in inference runtime with minimal effect on performance, as measured by bits-per-byte. Additionally, with multilingual training, MrT5 adapts to the orthographic characteristics of each language, learning language-specific compression rates. Furthermore, MrT5 shows comparable accuracy to ByT5 on downstream evaluations such as XNLI, TyDi QA, and character-level tasks while reducing sequence lengths by up to 75%. Our approach presents a solution to the practical limitations of existing byte-level models.
Biography: Julie Kallini is a second-year Ph.D. student in Computer Science at Stanford University, advised by Christopher Potts and Dan Jurafsky. Her research focuses on natural language processing (NLP), with an emphasis on computational linguistics/cognitive science, tokenization, and model architecture. Her paper, "Mission: Impossible Language Models," won Best Paper Award at ACL 2024. Her work is supported by the NSF Graduate Research Fellowship, the Stanford School of Engineering Graduate Fellowship, and the Stanford EDGE Fellowship.Before starting her Ph.D., Julie was a software engineer at Meta, where she worked on machine learning for advertisements. Julie graduated summa cum laude from Princeton University with a B.S.E. in Computer Science and a minor in Linguistics.
Host: Jonathan May and Katy Felkner
More Info: https://usc.zoom.us/j/92986255795?pwd=mbJqNRr6isZBQ9mn643fgalO5gksDs.1
Webcast: https://www.youtube.com/watch?v=vWyi1_DXvqALocation: Information Science Institute (ISI) - Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=vWyi1_DXvqA
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://usc.zoom.us/j/92986255795?pwd=mbJqNRr6isZBQ9mn643fgalO5gksDs.1
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
