Description:

Monday / CS Seminar
February 17th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Ainesh Bakshi

Talk Title
Understanding Quantum Systems via the Algorithmic Lens

Abstract
Quantum mechanics is one of our most profound and successful theoretical frameworks for understanding the physical world. It continues to drive remarkable technological and theoretical breakthroughs, spanning computing, coding theory, cryptography, material science, and chemistry. In this talk, I will describe how the algorithmic lens has been pivotal in rigorously analyzing such quantum systems and revealed deeper structural properties that were previously inaccessible through traditional approaches.

Biography
Ainesh Bakshi is a Postdoctoral Fellow jointly appointed in the Mathematics and Computer Science departments at MIT. Prior to that, he obtained his PhD in Computer Science at CMU. He is broadly interested in theoretical computer science and quantum information. His main research thread revolves around using the algorithmic toolkit, consisting of iterative methods and convex hierarchies, to understand large quantum systems. These results have gained significant attention recently, including two Quanta articles, two QIP Invited Plenaries, a QIP Best Student Paper, and being featured in Quanta Magazine’s “Biggest Breakthroughs in Computer Science 2024.”  He is also interested in extending this algorithmic toolkit and applying it to problems arising in high-dimensional statistics, privacy, metric embeddings, and numerical linear algebra.

Research/Interest Areas
Theoretical Computer Science, Quantum Information
---
Zoom: TBA
Panopto: TBA
Community Connections Topic: Algorithmic Justice League / Dr. Joy Buolamwini

Description:

Wednesday / CS Seminar
February 19th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Dan Adler

Talk Title
Developing Responsible AI Monitoring Technologies for Chronic Care

Abstract
Data from everyday devices are increasingly being repurposed to monitor symptoms of heterogeneous chronic conditions: conditions where symptoms present diversely across individuals, and the devices used for symptom monitoring vary across a population. While these variations may not greatly affect personal tracking applications, they pose challenges towards use in clinical settings. Specifically, how can we develop technologies that accurately identify patient-specific symptoms, and ensure reliable symptom monitoring? How can these tools support patients and their healthcare providers? In this talk, I will discuss my work designing, developing, and evaluating AI-driven symptom monitoring technologies to address these challenges. I will close by presenting my vision for a more responsible approach to develop these technologies – one that is deeply integrated with the needs of patients, healthcare providers, and other key stakeholders within our health system.

Biography
Dan Adler is a PhD Candidate in the College of Computing and Information Science at Cornell University. His research designs, develops, and evaluates novel data-driven technologies and AI models that support healthcare delivery. Dan’s work has been published at top-tier venues in ubiquitous computing (IMWUT), human-computer interaction (CHI, CSCW), and digital health (npj Mental Health Research, BJPsych, JMIR). His research has been highlighted in the national media, cited in government reports, translated into interventions that support patients, and led to patentable systems. He is the recipient of an NSF Graduate Research Fellowship, and was a finalist for the Gaetano Borriello Outstanding Student Award at ACM UbiComp. Dan holds a Bachelor’s in Biomedical Engineering and Applied Mathematics and Statistics from The Johns Hopkins University.

Research/Interest Areas
Human-Computer Interaction; Ubiquitous Computing; Responsible AI/ML; Digital Health
---
Zoom: https://northwestern.zoom.us/j/94583712653?pwd=bJCsurzyfvg4v4LhWU5SjXEaH7RQSB.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=8fb71c59-ec7c-441b-824e-b2820147b70a
Community Connections Topic: Equitable Assessments

Description:

Friday / CS Seminar
February 21st / 12:00 PM
Hybrid / Mudd 3514

Speaker
Sadhika Malladi, Princeton University

Talk Title
Deep Learning Theory in the Age of Generative AI

Abstract
Modern deep learning has achieved remarkable results, but the design of training methodologies largely relies on guess-and-check approaches. Thorough empirical studies of recent massive language models (LMs) is prohibitively expensive, underscoring the need for theoretical insights, but classical ML theory struggles to describe modern training paradigms. I present a novel approach to developing prescriptive theoretical results that can directly translate to improved training methodologies for LMs. My research has yielded actionable improvements in model training across the LM development pipeline — for example, my theory motivates the design of MeZO, a fine-tuning algorithm that reduces memory usage by up to 12x and halves the number of GPU-hours required. Throughout the talk, to underscore the prescriptiveness of my theoretical insights, I will demonstrate the success of these theory-motivated algorithms on novel empirical settings published after the theory.

Biography
Sadhika Malladi is a final-year PhD student in Computer Science at Princeton University advised by Sanjeev Arora. Her research advances deep learning theory to capture modern-day training settings, yielding practical training improvements and meaningful insights into model behavior. She has co-organized multiple workshops, including Mathematical and Empirical Understanding of Foundation Models at ICLR 2024 and Mathematics for Modern Machine Learning (M3L) at NeurIPS 2024. She was named a 2025 Siebel Scholar.

Research/Interest Areas
machine learning, theoretical machine learning, natural language processing, optimization
---
Zoom: https://northwestern.zoom.us/j/93472031147?pwd=EMcOSUapzdfxmWaIUX6EheUDmztCU3.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=f8cd1b02-aca0-4bc9-b475-b2820164a63f
Community Connections Topic: Implicit Bias in Technology

Description:

Monday / CS Seminar
February 24th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Wenqi Jiang, ETH Zurich

Talk Title
Vector-Centric Machine Learning Systems: A Cross-Stack Approach

Abstract
"Despite the recent popularity of large language models (LLMs), the transformer neural network invented eight years ago has remained largely unchanged. It prompts the question of whether machine leanring (ML) systems research is solely about improving hardware and software for tensor operations. In this talk, I will argue that the future of machine learning systems extends far beyond model acceleration. Using the increasingly popular retrieval-augmented generation (RAG) paradigm as an example, I will show that the growing complexity of ML systems demands a deeply collaborative effort spanning data management, systems, computer architecture, and ML.

I will present RAGO and Chameleon, two pioneering works in this field. RAGO is the first systematic performance study of retrieval-augmented generation. It uncovers the intricate interactions between vector data systems and models, revealing drastically different performance characteristics across various RAG workloads. To navigate this complex landscape, RAGO introduces a system optimization framework to explore optimal system configurations for arbitrary RAG algorithms. Building on these insights, I will introduce Chameleon, the first heterogeneous accelerator system for RAG. Chameleon combines LLM and retrieval accelerators within a disaggregated architecture. The heterogeneity ensures efficient serving of both LLM inference and retrievals, while the disaggregation enables independent scaling of different system components to accommodate diverse RAG workload requirements. I will conclude the talk by emphasizing the necessity of cross-stack co-design for future ML systems and the abundant of opporutnities ahead of us."

Biography
Wenqi Jiang is a final-year PhD student at ETH Zurich, advised by Gustavo Alonso and Torsten Hoefler. He aims to enable more efficient, next-generation machine learning systems. Rather than focusing on a single layer in the computing stack, Wenqi's research spans the intersections of data management, computer systems, and computer architecture. His work has driven advancements in several areas, including retrieval-augmented generation (RAG), vector search, and recommender systems. These contributions have earned him recognition as one of the ML and Systems Rising Stars, as well as the AMD HACC Outstanding Researcher Award.

Research/Interest Areas
Data management, computer systems, and computer architecture.
---
Zoom: https://northwestern.zoom.us/j/98746799161?pwd=8tJL888y1j8GrawbwOrTXKT7S9GQA4.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=cd3b91de-4058-478b-8d42-b28901171354
Community Connections Topic: Black Women in Computing

Description:

Wednesday / CS Seminar
February 26th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Tianyu Gao, Princeton University

Talk Title
Enabling Language Models to Process Information at Scale

Abstract
Language models (LMs) are highly effective at understanding and generating text, holding immense potential as intuitive, personalized interfaces for accessing information. Expanding their ability to gather and synthesize large volumes of information will further unlock transformative applications, ranging from generative search engines to AI literature assistants. In this talk, I will present my research on advancing LMs for information processing at scale. (1) I will present my evaluation framework for LM-based information-seeking systems, emphasizing the importance of providing citations for verifying the model-generated answers. Our evaluation highlights shortcomings in LMs’ abilities to reliably process long-form texts (e.g., dozens of webpages), which I address by developing state-of-the-art long-context LMs that outperform leading industry efforts while using a small fraction of the computational budget. (2) I will then introduce my foundational work on using contrastive learning to produce performant text embeddings, which form the cornerstone of effective and scalable search. (3) In addition to building systems that can process large-scale information, I will discuss my contributions to creating efficient pre-training and adaptation methods for LMs, which enable scalable deployment of LM-powered applications across diverse settings. Finally, I will share my vision for the next generation of autonomous information processing systems and outline the foundational challenges that must be addressed to realize this vision.

Biography
Tianyu Gao is a fifth-year PhD student in the Department of Computer Science at Princeton University, advised by Danqi Chen. His research focuses on developing principled methods for training and adapting language models, many of which have been widely adopted across academia and industry. Driven by transformative applications, such as using language models as information-seeking tools, his work also advances robust evaluation and fosters a deeper understanding to guide the future development of language models. He led the first workshop on long-context foundation models at ICML 2024. He won an outstanding paper award at ACL 2022 and received an IBM PhD Fellowship in 2023. Before Princeton, he received his BEng from Tsinghua University in 2020. 

Research/Interest Areas
Natural language processing, language models
---
Zoom: https://northwestern.zoom.us/j/91611540710?pwd=7yBeDMdu6jAcoK2wFQj9Pal31bxk6K.1
Panopto: https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=c651c906-f33f-48e5-87f1-b2890117aac0
Community Connections Topic: Supporting First Generation Students