News & EventsDepartment Events & Announcements
Events
-
Apr19
EVENT DETAILS
less
Friday / CS Seminar
April 19th / 12:00 PM
In Person / Mudd 3514Speaker
Dan Fu, Stanford UniversityTalk Title
Hardware-Aware Efficient Primitives for Machine LearningAbstract
Efficiency is increasingly tied to quality to machine learning, with more efficient training algorithms leading to more powerful models. However, today's most popular machine learning models are built on asymptotically inefficient primitives. For example, attention in Transformers scales quadratically in the input size, while MLPs scale quadratically in model dimension. In this talk, I discuss my work on improving the efficiency of the core primitives in machine learning, with an emphasis on hardware-aware algorithms and long-context applications. First, I focus on replacing attention with gated state space models (SSMs) and convolutions, which scale sub-quadratically in context length. I describe the H3 (Hungry Hungry Hippos) architecture, a gated SSM architecture that matches Transformers in quality up to 3B parameters and achieves 2.4x faster inference. Second, I focus on developing hardware-aware algorithms for SSMs and convolutions. I describe FlashFFTConv, a fast algorithm for computing SSMs and convolutions on GPU by optimizing the Fast Fourier Transform (FFT). FlashFFTConv yields up to 7x speedup and 5x memory savings, even over vendor solutions from Nvidia. Third, I will briefly touch on how these same techniques can also be used to develop sub-quadratic scaling in the model dimension. I will describe Monarch Mixer, which uses a generalization of the FFT to achieve sub-quadratic scaling in both sequence length and model dimension. Throughout the talk, I will give examples of how these ideas are beginning to take hold, with gated SSMs and their variants now leading to state-of-the-art performance in long-context language models, embedding models, and DNA foundation models.Biography
Dan Fu is a PhD student in the Computer Science Department at Stanford University, where he is co-advised by Christopher Ré and Kayvon Fatahalian. His research interests are at the intersection of systems and machine learning. Recently, he has focused on developing algorithms and architectures to make machine learning more efficient, especially for enabling longer-context applications. His research has appeared as oral and spotlight presentations at NeurIPS, ICML, and ICLR, and he has received the best student paper runner up at UAI. Dan has also been supported by an NDSEG fellowship.Research Area/Interests
machine learning, systemsTIME Friday, April 19, 2024 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
May2
EVENT DETAILSmore info
less
With the explosion of AI platforms, what is the future of work? Will we need “humans in the loop”? Although these platforms are still in the early stages, implications are broadly significant. In this dialogue, we bring together researchers with distinct perspectives to discuss approaches for designing a desirable future of work for everyone. Tackling questions related to ethics, governance, and competition, this dialog will highlight the role of thoughtful design in achieving the vision of a desirable future of work for everyone.
TIME Thursday, May 2, 2024 at 4:00 PM - 5:15 PM
CONTACT Madison Deyo Madison.Deyo@northwestern.edu EMAIL
CALENDAR Center for Human-Computer Interaction + Design (HCI+D)
-
May8
EVENT DETAILS
lessWednesday / CS Distinguished Lecture
May 8th / 12:00 PM
Hybrid / Mudd 3514Speaker
Monica Lam, Stanford UniversityTalk Title
Trustworthy Conversational Chatbots for Your Data with Generative AIAbstract
The rapid growth of Large Language Models (LLMs), such as ChatGPT, has both inspired and alarmed knowledge workers. LLM-based chatbots generating false information and hallucinating have garnered widespread attention, raising questions about the reliability of LLMs as chatbots and virtual assistants.The Stanford Open Virtual Assistant Lab has created an open-source Knowledge Engine, powered by an LLM, that can provide a reliable conversational chatbot to any structured or unstructured data. It can also assist writers by drafting full-length Wikipedia-like articles from scratch with breadth and depth. Public demos created with our Knowledge Engine include: WikiChat grounded in Wikipedia, Yelpbot grounded in Yelp, the STORM writing assistant grounded in the Internet, and Noora, a coach for people with Autism Spectrum Disorder (https://oval.cs.stanford.edu).
Biography
Dr. Monica Lam is the Kleiner Perkins, Mayfield, Sequoia Capital Professor in the School of Engineering at Stanford, in the Departments of Computer Science and, by courtesy, Electrical Engineering. She is the Faculty Director of the Stanford Open Virtual Assistant Laboratory and a faculty member of the Natural Language Processing Group at Stanford. She received a B.Sc. from University of British Columbia and a Ph.D. from Carnegie Mellon University.Prof. Lam is a member of the National Academy of Engineering and an ACM Fellow. She has received numerous best paper awards, and has published over 150 papers in areas including natural language processing, machine learning, compilers, computer architecture, operating systems, high-performance computing, and HCI. She co-authored the “Dragon Book”, the definitive text on compiler technology. She was on the founding team of Tensilica, the first startup in configurable processor cores. Prof. Lam's research on privacy-preserving virtual assistants earned Popular Science's Best of What's New Award in Security in 2019.
Research Area/Interests
Natural language processing; programming languagesZoom
TBATIME Wednesday, May 8, 2024 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
May8
EVENT DETAILSmore info
lessThe Center for Scientific Studies in the Arts is a collaboration between the Art Institute of Chicago and materials science-related departments at Northwestern University to pursue objects-based and objects-inspired scientific research. Materials research benefits ongoing work in conservation, archaeology, art history, and curatorial scholarship.
Learn how the Center uses materials research to care for art objects in sustainable, innovative ways with Maria Kokkori, Senior Scientist in the Center for Scientific Studies in the Arts. She will be in conversation with Corey Byrnes, Northwestern Associate Professor of Chinese Culture and co-founder/co-director of the Environmental Humanities Workshop in Kaplan Humanities Center.
This event is presented by the McCormick School of Engineering and Applied Science in conjunction with exhibition Actions for the Earth: Art, Care & Ecology.
TIME Wednesday, May 8, 2024 at 6:00 PM - 7:30 PM
LOCATION Block Museum of Art, Mary and Leigh map it
CONTACT Block Museum of Art block-museum@northwestern.edu EMAIL
CALENDAR Block Museum of Art
-
May10
EVENT DETAILS
lessFriday / CS Distinguished Lecture
May 10th / 12:00 PM
Hybrid / Mudd 3514Speaker
Shafi Goldwasser; Simons Institute for the Theory of Computing, University of California BerkeleyTalk Title
Trust, Backdoor Vulnerabilities and Possible MitigationsAbstract
Cryptographic tools and models enable to trust the use of technology platforms controlled by worst case computationally bounded adversaries. In this talk I will use cryptographic modeling and tools to view trust dilemmas in various phases of the machine learning pipelines. We will touch on privacy in the training stage, verification of properties of
machine learning models, and the possibility of achieving robustness in presence of backdoors.Biography
Shafi Goldwasser is Director of the Simons Institute for the Theory of Computing, and Professor of Electrical Engineering and Computer Science at the University of California Berkeley. Goldwasser is also the RSA Professor (post tenure) of Electrical Engineering and Computer Science at MIT and Professor Emeritus of Computer Science and Applied Mathematics at the Weizmann Institute of Science, Israel. Goldwasser holds a B.S. Applied Mathematics from Carnegie Mellon University (1979), and M.S. and Ph.D. in Computer Science from the University of California Berkeley (1984).
Goldwasser's contributions include the introduction of probabilistic encryption, interactive zero knowledge protocols, elliptic curve primality testings, hardness of approximation proofs for combinatorial problems, combinatorial property testing, and pseudo deterministic algorithms.
Goldwasser was the recipient of the ACM Turing Award in 2012, the Gödel Prize in 1993 and in 2001, the ACM Grace Murray Hopper Award in 1996, the RSA Award in Mathematics in 1998, the ACM Athena Award for Women in Computer Science in 2008, the Benjamin Franklin Medal in 2010, the IEEE Emanuel R. Piore Award in 2011, the Simons Foundation Investigator Award in 2012, and the BBVA Foundation Frontiers of Knowledge Award in 2018. Goldwasser is a member of the NAS, NAE, AAAS, the Russian Academy of Science, the Israeli Academy of Science, the London Royal Mathematical Society and a Foreign Member of the Royal Society. Goldwasser holds honorary degrees from Ben Gurion University, Bar Ilan University, Carnegie Mellon University, Haifa University, University of Oxford, and the University of Waterloo, and has received the UC Berkeley Distinguished Alumnus Award and the Barnard College Medal of Distinction.
Research Area/Interests
Cryptography, Complexity, Probabilistic AlgorithmsZoom: https://northwestern.zoom.us/j/99797040711?pwd=OWtvMGE1TU0rNmdkUEtqb2IrNmJEUT09
TIME Friday, May 10, 2024 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
May29
EVENT DETAILS
lessWednesday / CS Distinguished Lecture
May 29th / 12:00 PM
Hybrid / Mudd 3514Speaker
Ken ReganTalk Title
TBAAbstract
TBABiography
TBA
Research Area/Interests
TBAZoom: TBA
TIME Wednesday, May 29, 2024 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
May30
EVENT DETAILS
lessTBA
TIME Thursday, May 30, 2024 at 9:00 AM - 11:00 AM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
May30
EVENT DETAILS
lessTBA
TIME Thursday, May 30, 2024 at 3:00 PM - 5:00 PM
LOCATION TBA, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Jun10
EVENT DETAILSmore info
lessMcCormick School of Engineering PhD Hooding and Master’s Degree Recognition Ceremony
TIME Monday, June 10, 2024 at 9:00 AM - 11:00 AM
LOCATION Welsh-Ryan Arena
CONTACT Amy Pokrass amy.pokrass@northwestern.edu EMAIL
CALENDAR McCormick School of Engineering and Applied Science
-
Jun10
TIME Monday, June 10, 2024 at 2:00 PM - 4:00 PM
LOCATION Welsh-Ryan Arena
CONTACT Amy Pokrass amy.pokrass@northwestern.edu EMAIL
CALENDAR McCormick School of Engineering and Applied Science
-
Aug14
EVENT DETAILSmore info
lessInnovation in Quantum Pedagogy, Application, and its Relation to Culture (IQ-PARC), funded by the Department of Defense — National Defense Education Program, is extending an invitation to underrepresented students nationwide (including military-connected students) to participate in a summer school focused on quantum technologies, to be held at Northwestern University. Join us for presentations by faculty and industry partners introducing quantum technologies, cutting-edge research areas, and related job opportunities particularly in the areas of national security.
This effort aims to foster an inclusive environment that encourages participation from all corners of the academic community. Successful applicants will receive up to $1,000 USD to cover travel and lodging expenses in Evanston, IL.
Priority application deadline: May 15, 2024.
Decisions will be sent by June 15, 2024.
TIME Wednesday, August 14, 2024
LOCATION Ford Motor Company Engineering Design Center map it
CONTACT Dongyang Li lidongyang@northwestern.edu EMAIL
CALENDAR McCormick School of Engineering and Applied Science