Select a calendar:
Filter June Events by Event Type:
Events for June 12, 2025
-
Six Sigma Black BeltThu, Jun 12, 2025 @ 09:00 AM - 05:00 PM
Executive Education
Conferences, Lectures, & Seminars
Speaker: IISE Faculty, IISE Faculty
Talk Title: Six Sigma Black Belt
Abstract: USC Viterbi School of Engineering's Six Sigma Black Belt program, offered in partnership with the Institute of Industrial and Systems Engineers, enables professionals to learn how to integrate principles of business, statistics, and engineering to achieve tangible results. Learn the advanced problem-solving skills you need to implement the principles, practices, and techniques of our Six Sigma Black Belt course in order to maximize performance and cost reductions in your organization. During this three-week practitioner course, you will learn how to measure a process, analyze the results, develop process improvements, and quantify the resulting savings. You will be required to complete a project demonstrating mastery of appropriate analytical methods and pass an examination to earn Six Sigma Black Belt Certification. This practitioner course for Six Sigma implementation provides extensive coverage of the Six Sigma process, as well as intensive exposure to the key analytical tools associated with Six Sigma, including project management, team skills, cost analysis, FMEA, basic statistics, inferential statistics, sampling, goodness of fit testing, regression and correlation analysis, reliability, design of experiments, statistical process control, measurement systems analysis, and simulation. Computer applications are emphasized.
Host: USC Viterbi Corporate and Professional Programs
More Info: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-black-belt/
Audiences: Six Sigma Black Belt Students
Contact: VASE Executive Education
Event Link: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-black-belt/
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. -
Pre-SPARK seminar
Thu, Jun 12, 2025 @ 12:30 PM - 01:30 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Daria Mochly-Rosen, Professor of Chemical & Systems Biology @ Stanford Cellular/Molecular Engineering of Pharmaceuticals
Talk Title: SPARKing Translation at Stanford: 19 Years of Experience (2006- )
Host: Eun Ji Chung
Location: Michelson Center for Convergent Bioscience (MCB) - 101
Audiences: Everyone Is Invited
Contact: Yi Huang
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. -
PhD Dissertation Defense - Xisen Jin
Thu, Jun 12, 2025 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Towards Continual Learning of Language Models in the Wild
Date and Time: Thursday, June 12th, 2025 | 1:00p - 3:00p
Location: RTH 306
Committee Members: Xiang Ren (Chair), Jesse Thomason, Mahdi Soltanolkotabi
Abstract: Language language models (LLMs/LMs) have become foundations of many artificial intelligence (AI) applications, and greatly benefited users in seeking information and completing tasks. Alongside the success of LLMs, there is an increasing need to promptly update these models for new application domains, new factual knowledge, and mitigating harmful behaviors. The large-scale models and the complicated data distributions have introduced unforeseen challenges in earlier study of continual learning; at the same time, new paradigms of building models, e.g., fine-tuning open-source models, have become prevalent. These new challenges and resources create a context of continual learning of language models, which we term continual learning in the wild, that differentiates the problem from the past study.
The thesis focuses on identifying and addressing the emerging challenges in continual learning of language models. In the first part of the thesis, I propose training and evaluation protocols representative of two different goals of continual learning. I create two datasets, namely a domain-incremental research paper stream and a chronologically-ordered tweet stream, alongside downstream datasets to test model capability. In addition, I extensively evaluate existing or new continual learning algorithms for the setup and identify that knowledge distillation from past model checkpoints stands out as an effective continual learning algorithm.
In the second part of the thesis, I propose to study how merging weights of existing models can achieve the goal of fusing knowledge of multiple models without access to original training data. I propose a novel model merging algorithm, RegMean, which is simple to implement, computationally efficient, and outperforms baseline merging algorithms significantly.
In the remaining part of the thesis, I introduce my work on analyzing patterns of upstream knowledge forgetting in continual learning. I interpret significant patterns of forgetting in upstream data that arise when fine-tuning LLMs. The analysis demonstrates that accurate predictions about forgetting can be made using embedding similarity models, or matrix completion from a small set of observed occurrences of forgetting. I further illustrate how predicting forgetting can lead to the development of simple and effective continual learning algorithms.Location: Ronald Tutor Hall of Engineering (RTH) - 306
Audiences: Everyone Is Invited
Contact: Xisen Jin
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.
