Select a calendar:
Filter February Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for February
-
CS Colloquium: Justin Solomon (MIT) - Navigating, Restructuring and Reshaping Learned Latent Spaces
Mon, Feb 03, 2025 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Justin Solomon, MIT
Talk Title: Navigating, Restructuring and Reshaping Learned Latent Spaces
Abstract: Modern machine learning architectures often embed their inputs into a lower-dimensional latent space before generating a final output. A vast set of empirical results---and some emerging theory---predicts that these lower-dimensional codes often are highly structured, capturing lower-dimensional variation in the data. Based on this observation, in this talk I will describe efforts in my group to develop lightweight algorithms that navigate, restructure, and reshape learned latent spaces. Along the way, I will consider a variety of practical problems in machine learning, including low-rank adaptation of large models, regularization to promote local latent structure, and efficient training/evaluation of generative models. This talk will cover collaborative research with Rickard Gabrielsson, Kimia Nadjahi, Chris Scarvelis, Tal Shnitzer, Mikhail Yurochkin, Jiacheng Zhu, and others.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Justin Solomon is an Associate Professor of Electrical Engineering and Computer Science at MIT. He leads the Geometric Data Processing Group in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), which studies problems at the intersection of geometry, large-scale optimization, and applications.
Host: Yue Wang
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone (USC) is invited
Contact: CS Faculty Affairs
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.
-
CS Colloquium: Amit Sheth (University of South Carolina) - Intelligent, Robust and Trustworthy AI: Managing GenAI Challenges, Next Phase of Hybrid AI Models and Enterprise AI for Mission-Critical Applications
Wed, Feb 19, 2025 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Amit Sheth, University of South Carolina
Talk Title: Intelligent, Robust and Trustworthy AI: Managing GenAI Challenges, Next Phase of Hybrid AI Models and Enterprise AI for Mission-Critical Applications
Abstract: This talk will present my team's current and future research themes. The first theme is the development of Civilized and Human-inspired AI. This encompasses addressing challenges associated with Generative AI (GenAI) and finding ways to mitigate its limitations, such as detecting AI-generated content, combating hallucinations, misinformation, and toxicity, and exploring methods for their reduction. The second theme involves the next phase of post-GenAI strategies aimed at creating robust and trustworthy AI solutions. This includes the development of a new generation of custom, compact, agile and neurosymbolic (CCAN) AI models for a more intelligent, robust and trustworthy AI with support for grounding, alignment, instructability, user-level explainability, attribution, safety, reasoning, planning, analogy and abstraction. Lastly, I will provide a brief demonstration of how these AI models, along with AI copilots and agents, are utilized for complex, enterprise-class, mission-critical decision-making applications in diverse fields such as behavioral and mental health, personalized nutrition, autonomous vehicles and smart manufacturing. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Prof. Amit Sheth (Home Page, LinkedIn, GScholar) is an Educator, Researcher, and Entrepreneur. He is the NCR Chair & Professor of Computer Sc & Engg. He founded the university-wide AI Institute at the University of South Carolina in 2019 which now has ~50 researchers. Earlier, he was the Ohio Eminent Scholar and Exec. Director of Ohio Center of Excellence in Knowledge-enabled Computing and BioHealth Innovation at Wright State University. He is a Fellow of IEEE, AAAI, AAAS, ACM, and AAIA. His major awards include IEEE CS W. Wallace McDowell and IEEE TVSVC Research Innovation awards. He has (co-)founded four companies based on his university research, including the first Semantic Search company in 1999 that pioneered technology similar to what is found today in Google Semantic Search and Knowledge Graph, ezDI, which developed knowledge-infused clinical NLP/NLU, and Cognovi Labs at the intersection of emotion and AI. He is particularly proud of the success of his >>45 Ph.D. advisees and postdocs in academia, industry research, and entrepreneurship.
Host: Emilio Ferrara
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
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. -
CS DISTINGUISHED LECTURE feat. Noah A. Smith, PhD
Fri, Feb 21, 2025 @ 02:00 PM - 04:15 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Noah A. Smith, PhD, Amazon Professor of Machine Learning - Paul G. Allen School of Computer Science & Engineering, University of Washington
Talk Title: OLMo, Tulu, and Friends: Accelerating the Science of Language Modeling
Abstract: Neural language models with billions of parameters and trained on trillions of words are powering the fastest-growing computing applications in history and generating discussion and debate around the world. Yet most scientists cannot study or improve those state-of-the-art models because the organizations deploying them keep their data and machine learning processes secret. I believe that the path to models that are usable by all, at low cost, customizable for areas of critical need like the sciences, and whose capabilities and limitations are made transparent and understandable, is radically open development, with academic and not-for-profit researchers empowered to do reproducible science. In this talk, I’ll share the story of the work our team is doing to radically open up the science of language modeling. We've released multiple iterations of OLMo, a strong language model with fully open pretraining data, including a strong mixture-of-experts model, OLMoE. From these we also built Molmo, an open language-vision model. We’ve also built and released Tülu, a series of models that systematically explore the post-training landscape. All of these come with open-source code and extensive documentation, including new tools for evaluation. Together these artifacts make it possible to explore new scientific questions and democratize control of the future of this fascinating and important technology.
The work I’ll present was led by a large team at the Allen Institute for Artificial Intelligence in Seattle, with collaboration from the Paul G. Allen School at the University of Washington and various kinds of support and coordination from many organizations, including the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University, AMD, CSC - IT Center for Science (Finland), Databricks, Together.ai, and the National AI Research Resource Pilot.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
RSVP Deadline: Tuesday, February 18, 2025
ZOOM: https://usc.zoom.us/j/94658825749?pwd=PSuL9G8Aw9BaR7haIuAfPwIyQ7d7Hq.1
Meeting ID: 946 5882 5749
Passcode: 02212025
Biography: Noah Smith is a computer scientist working in several fields of artificial intelligence research. He recently wrote Language Models: A Guide for the Perplexed, a general-audience tutorial, and he co-directs the OLMo open language modeling effort with Hanna Hajishirzi.
Broadly, his research targets algorithms that process data encoding language, music, and more, to augment human capabilities. He also works on core problems of research methodology like evaluation. You can watch videos of some of his talks, read his papers, and learn about his research groups, Noah’s ARK and AllenNLP. Smith is most proud of his mentoring accomplishments: as of 2024, he has graduated 29 Ph.D. students and mentored 15 postdocs, with 27 alumni now in faculty positions around the world. 20 of his undergraduate/masters mentees have gone on to Ph.D. programs. His group’s alumni have started companies and are technological leaders both inside and outside the tech industry.
Host: Prof. Jieyu Zhao
More Info: https://forms.gle/FDsJM8mjfCw8M6Rk9
Webcast: https://usc.zoom.us/j/94658825749?pwd=PSuL9G8Aw9BaR7haIuAfPwIyQ7d7Hq.1Location: Ginsburg Hall (GCS) - Auditorium (LL1)
WebCast Link: https://usc.zoom.us/j/94658825749?pwd=PSuL9G8Aw9BaR7haIuAfPwIyQ7d7Hq.1
Audiences: Everyone Is Invited
Contact: Thomas Lord Department of Computer Science
Event Link: https://forms.gle/FDsJM8mjfCw8M6Rk9
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. -
CS Colloquium: Angela Zhou (USC / Marshall School of Business) - Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders
Mon, Feb 24, 2025 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Angela Zhou, USC / Marshall School of Business
Talk Title: Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders
Abstract: Offline causal decision making and reinforcement learning is important in domains such as medicine, economics, and e-commerce where online experimentation is costly, dangerous or unethical, and where the true model is unknown. However, most methods assume all covariates used in the behavior policy's action decisions are observed. Though this assumption, sequential ignorability/unconfoundedness, likely does not hold in observational data, most of the data that accounts for selection into treatment may be observed, motivating sensitivity analysis. We study robust policy evaluation and policy optimization in the presence of sequentially-exogenous unobserved confounders under a sensitivity model. We consider the single-timestep and the sequential setting. For the sequential setting, we propose and analyze orthogonalized robust fitted-Q-iteration that uses closed-form solutions of the robust Bellman operator to derive a loss minimization problem for the robust Q function, and adds a bias-correction to quantile estimation. Our algorithm enjoys the computational ease of fitted-Q-iteration and statistical improvements (reduced dependence on quantile estimation error) from orthogonalization. We provide sample complexity bounds, insights, and show effectiveness both in simulations and on real-world longitudinal healthcare data of treating sepsis. In particular, our model of sequential unobserved confounders yields an online Markov decision process, rather than partially observed Markov decision process: we illustrate how this can enable warm-starting optimistic reinforcement learning algorithms with valid robust bounds from observational data. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Angela Zhou is an Assistant Professor in Data Sciences and Operations at the University of Southern California, Marshall School of Business. She received her PhD from Cornell ORIE and completed a postdoctoral fellowship at UC Berkeley / the Simons Institute. She works on data-driven decision making, including the interface of causal inference and machine learning, (offline) reinforcement learning, and equitable social prediction in consequential domains. She was a program co-chair for ACM EAAMO 2022 (a new conference on Equity and Access in Algorithms, Mechanisms and Optimization). Her research interests are in statistical machine learning for data-driven sequential decision making under uncertainty, causal inference, and the interplay of statistics and optimization. Her work has received oral-equivalent or featured designations at machine learning venues (Neurips, TMLR) and has won the INFORMS Data Mining Best Student Paper award, while she has received various designations as a Rising Star in AI, Data Science, and AI Fairness.
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone (USC) is invited
Contact: CS Faculty Affairs
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. -
CS Colloquium: Paul Bogdan (USC / ECE) - Theoretical Foundations of NeuroAI: Challenges and A Gedanken Modeling Framework Motivated by Living Neuronal Networks Dynamics
Wed, Feb 26, 2025 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Paul Bogdan, USC / ECE
Talk Title: Theoretical Foundations of NeuroAI: Challenges and A Gedanken Modeling Framework Motivated by Living Neuronal Networks Dynamics
Abstract: Brains build compact models or discover governing laws of the world from just a few assumptions or noisy and conflicting observations. Biological brains can also predict uncanny events via memory-based analogies even when resources are limited. The ability of biological intelligence to discover, generalize, hierarchically reason and plan, and complete a wide range of unknown heterogeneous tasks calls for a comprehensive understanding of how distributed networks of interactions among neurons, glia, and vascular systems enable animal and human cognition. Such an understanding can serve as a basis for advancing the design of artificial general intelligence (AGI). In this talk, we will discuss the challenges and potential solutions for inferring the theoretical foundations of biological intelligence and NeuroAI which can guide the design of future A(G)I, expanding the limit of human discovery. To infer network structures from very scarce and noisy data, we propose a new mathematical framework capable of learning the emerging causal fractal memory from biological neuronal spiking activity. This framework offers insight into the topological properties of the underlying neuronal networks and helps us predict animal behavior during cognitive tasks. We will also discuss an AI framework for mining the optical imaging of brain activity and reconstructing the weighted multifractal graph generators governing the neuronal networks from very scarce data. This network generator inference framework can reproduce a wide variety of network properties, differentiate varying structures in brain networks and chromosomal interactions, and detect topologically associating domain regions in conformation maps of the human genome. We will discuss how network science-based AI can discover the phase transitions in complex systems and help with designing protein–nanoparticle assemblies. To infer the objectives and rules by which distributed networks of neurons attain intelligent decisions, we discuss an AI framework (multiwavelet-based neural operator) capable of learning, solving, and forecasting sets of coupled governing laws. We thus learn the operator kernel of an unknown partial differential equation (PDE) from noisy scarce data. For time-varying PDEs, this model exhibits 2-10X higher accuracy than state-of-the-art machine learning tools. Inspired by the multifractal formalism for detecting phase transitions in biological neuronal networks, we explore the principles of self-organization in Large Language Models (LLMs). Through the lens of multifractal analysis, we reveal the intricate dynamics of neuron interactions, showing how self-organization facilitates the emergence of complex patterns and intelligence within LLMs.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Paul Bogdan is the Jack Munushian Early Career Chair associate professor in the Ming Hsieh Department of Electrical and Computer Engineering at University of Southern California. He received his Ph.D. degree in Electrical & Computer Engineering at Carnegie Mellon University. His work has been recognized with a number of honors and distinctions, including the 2021 DoD Trusted Artificial Intelligence (TAI) Challenge award, the USC Stevens Center 2021 Technology Advancement Award for the first AI framework for SARS-CoV-2 vaccine design, the 2019 Defense Advanced Research Projects Agency (DARPA) Director’s Fellowship award, the 2018 IEEE CEDA Ernest S. Kuh Early Career Award, the 2017 DARPA Young Faculty Award, the 2017 Okawa Foundation Award, the 2015 National Science Foundation (NSF) CAREER award, the 2012 A.G. Jordan Award from Carnegie Mellon University for an outstanding Ph.D. thesis and service, and several best paper awards. His research interests include cyber-physical systems, new computational cognitive neuroscience tools for deciphering biological intelligence, the quantification of the degree of trustworthiness and self-optimization of AI systems, new machine learning techniques for complex multi-modal data, the control of complex time-varying networks, the modeling and analysis of biological systems and swarms, new control techniques for dynamical systems exhibiting multi-fractal characteristics, performance analysis and design methodologies for heterogeneous manycore systems.
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone (USC) is invited
Contact: CS Faculty Affairs
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.
