Upcoming CS Seminars

Missed a seminar? No worries! View past seminars via the Northwestern CS Website (northwestern login required).

"Generative AI for Music and Audio"

Abstract

Generative AI has been transforming the way we interact with technology and consume content. In this talk, I will briefly introduce the three main directions of my research centered around generative AI for music and audio: 1) multitrack music generation, 2) assistive music creation tools, and 3) multimodal learning for audio and music. I will then zoom into my recent work on learning text-queried sound separation and text-to-audio synthesis from videos using pretrained language-vision models. Finally, I will close this talk by discussing the challenges and future directions of generative AI for music and audio.

Biography

Hao-Wen (Herman) Dong is a PhD Candidate in Computer Science at University of California San Diego working with Prof. Julian McAuley and Prof. Taylor Berg-Kirkpatrick. Herman’s research aims to empower music and audio creation with machine learning. His long-term goal is to lower the barrier of entry for music composition and democratize audio content creation. He is broadly interested in music generation, audio synthesis, multimodal machine learning and music information retrieval. He has collaborated with researchers at NVIDIA, Adobe, Dolby, Amazon, Sony and Yamaha through internships. Prior to his PhD, he was a research assistant at Academia Sinica working with Prof. Yi-Hsuan Yang. Herman’s research has been recognized by the UChicago and UCSD Rising Stars in Data Science, ICASSP Rising Stars in Signal Processing and UCSD GPSA Interdisciplinary Research Award. His PhD study has been supported by IEEE SPS Scholarship, Taiwan Government Scholarship to Study Abroad, J. Yang Scholarship and UCSD ECE Department Fellowship. For more information, please visit his personal website (https://salu133445.github.io/).

Zoom Link: https://northwestern.zoom.us/j/97908273578?pwd=aUxFZ1Npc3oyNFdrSmQrdHU0QldlZz09 

Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=5cfa8c07-23ca-4992-bfd8-b0b4011de673 

"Tools for Hypothesizing Effects in Analysis and Science"

Abstract

A host of visualization and interactive tools aim to support learning from data to inform decision-making. However, attempts to design for exploratory data analysis and other analytical tasks are frequently based on overly simplified views of statistical workflow. Consequently, users may engage in pattern-finding at the expense of recognizing uncertainty or considering potential sources of heterogeneity and variation in the effects they seek to discover. I will describe how goals like facilitating model checking and supporting rational decision-making have led me and collaborators to develop novel software designs and evaluative frameworks for analysis and visualization tools. For example, rethinking the goals of exploratory data analysis software led us to develop Exploratory Visual Modeling (EVM), a Tableau-style GUI visual analysis tool with built-in statistical modeling support that enables analysts to check their provisional interpretations of data in an exploratory session. Motivated by the heavy reliance on average treatment effects in data-driven science, Causal Quartets depict possible patterns of variation compatible with an average treatment effect at the level of individual units, helping modelers consider the implications of effect heterogeneity for downstream policy decisions. Relatedly, the difficulty of identifying what has been learned about the value of a better visualization from the typical evaluative study informed our development a rational agent framework for benchmarking attainable performance with a data-driven interface. Using our framework, researchers can design better experiments for studying interface performance, and better explain losses in performance they observe.

Biography

Jessica Hullman is Ginni Rometty Associate Professor of Computer Science at Northwestern University. Her research addresses challenges and limitations that arise when people draw inductive inferences from data. Her work has contributed multiple visualization and interaction techniques for improving reasoning under uncertainty from data-driven interfaces, as well as theoretical frameworks for understanding the role of visualization in statistical workflow. Jessica's work has been awarded best paper awards at top visualization and HCI venues, a Microsoft Faculty award and NSF CAREER, Medium, and Small awards as PI, among others.

Zoom Link: https://northwestern.zoom.us/j/97908273578?pwd=aUxFZ1Npc3oyNFdrSmQrdHU0QldlZz09 

Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=c4bec2ac-083e-4ed8-bb93-b0af011b0a8d

"Challenges and Opportunities for MPI in the Post-Exascale Era"

Abstract

Over the past 30 years, MPI (Message Passing Interface) has enabled applications to run on many generations of parallel clusters and supercomputing systems, thereby enabling computation-driven progress in essentially all areas of science and engineering. As we enter the era of exascale systems, MPI continues to be the standard interface that most applications use for internode communication and scaling to the full system. This talk will discuss some of the challenges that were overcome for MPI to reach exascale and explore the challenges that must be overcome for MPI to continue to meet the needs of future post-exascale systems and applications.

Biography

Rajeev Thakur is an Argonne Distinguished Fellow and Deputy Director of the Data Science and Learning Division at Argonne National Laboratory. He received a Ph.D. in Computer Engineering from Syracuse University. His research interests are in high-performance computing, parallel programming models, runtime systems, communication libraries, scalable parallel I/O, and artificial intelligence and machine learning. He was the director of Software Technology for the Exascale Computing Project (ECP) from 2016 to 2017 and continues as the lead for the Programming Models and Runtimes area in ECP Software Technology. He is a member of the MPI Forum that defines the Message Passing Interface (MPI) standard. He is also co-author of the MPICH implementation of MPI and the ROMIO implementation of MPI-IO, which have thousands of users all over the world and form the basis of commercial MPI implementations from Intel, HPE/Cray, IBM, Microsoft, and other vendors. MPICH received an R&D 100 Award in 2005. Rajeev is a co-author of the book “Using Advanced MPI: Modern Features of the Message-Passing Interface” published by MIT Press. He was an associate editor of IEEE Transactions on Parallel and Distributed Systems (2003-2007) and was Technical Program Chair of the SC12 conference. He also served on the Steering Committee of the SC conference series (2015-2018). He is a Fellow of IEEE.

Zoom Link: https://northwestern.zoom.us/j/98742944672?pwd=eUNmd3dabGlyYkxUQThZNjVVRS84QT09

Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=0c762f3e-4358-4c48-ae8c-b0b6012faf7a 

Research Interests/Area
High-performance computing, parallel programming models, runtime systems, communication libraries, scalable parallel I/O, AI/ML

CS Department Events

CSPAC Tuesday Student Seminars

CSPAC is launching a student seminar series within the CS department. It will run on Tuesdays (12-1pm in 3514 with lunch, like the other seminars).  

The goal is to showcase student research in the department, and to give students an opportunity to give broad audience talks. You can find an overview of the format and goals here.

If you are a PhD student and you are interested in presenting, please reach out to (Vaidehi Srinivas, vaidehi@u.northwestern.edu) directly, and we can schedule a week that works for you.  A tentative schedule can be found here.

While the presenters will be PhD students, everyone in the CS department community (faculty, postdocs, students of all levels, etc.) are invited to attend!

What is CSPAC?

We are the CS PhD Advisory Council.  We are a PhD student-led organization, and our mandate is to interface between PhD students and faculty on academic issues.  Some examples of what we do include: identifying issues in the PhD program and providing input to faculty, and organizing events like the CS Open House and this student seminar series.  (Not to be confused with CSSI– the CS Social Initiative, another student-led organization that organizes social events for the department.)

We want to advocate for PhD students in the department, so if there is some way we can support you, please come talk to us.  We welcome PhD students to our weekly meetings on Tuesdays, 5-5:30pm, Mudd 3501 and/or zoom.  We also welcome anonymous concerns/feedback at any time via this form.  Anyone in the community can reach us at cspac@u.northwestern.edu.

Evening with Alisa Liu

IDEAL: New Perspectives on Data Science with Imperfect Data

Other Events & Opportunities

Native American and Indigenous Heritage Month

Become a DTC Project Partner

CS News

NU News