Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for April
-
The Bekey Distinguished Lecture & Munushian Distinguished Lecture Present: Gordon Bell, Microsoft Researcher Emeritus
Mon, Apr 01, 2024 @ 03:30 PM - 04:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Gordon Bell, Microsoft Researcher Emeritus
Talk Title: Bell's Law of Computer Classes. Why We Have All Kinds of Computers
Abstract: In 1951, a person could walk inside a computer and by 2010 a single computer (or “cluster’) with millions of processors has expanded to building size. Alternatively, computers are “walking” inside of us. These ends illustrate the vast dynamic range in computing power, size, cost, etc. for early 21st century computer classes. A computer class is a set of computers in a particular price range with unique or similar programming environments (e.g. Linux, OS/360, Palm, Symbian, Windows) that support a variety of applications that communicate with people and/or other systems. A new computer class forms roughly each decade establishing a new industry. A class may be the consequence and combination of a new platform with a new programming environment, a new network, and new interface with people and/or other information processing systems. Bell’s Law accounts for the formation, evolution, and death of computer classes based on logic technology evolution beginning with the invention of the computer and the computer industry in the first generation, vacuum tube computers (1950-1960), second generation, transistor computers (1958-1970), through the invention and evolutions of the third generation TTL and ECL bipolar Integrated Circuits (1965-1985), and the fourth generation bipolar, MOS and CMOS ICs enabling the microprocessor, (1971) represents a “break point” in the theory because it eliminated the other early, more slowly evolving technologies. Moore’s Law (Moore 1965, revised in 1975) is an observation about integrated circuit evolution. In summary, Moore’s Law and Bell’s effectively predict the ensuing fifty years of the computer. This lecture satisfies requirements for CSCI 591: Research Colloquium. To register visit: https://docs.google.com/forms/d/e/1FAIpQLSe6If3BkOATE8onTmrYZNSr0pzWF47TedNKMrwnukr0Ue_k8w/viewform
Biography: Gordon Bell is a Microsoft Researcher Emeritus He spent 23 years at Digital Equipment Corporation as Vice President of R&D, responsible for the first mini- and time-sharing computers and DEC's VAX, with a 6 year sabbatical at Carnegie Mellon. In 1987, as NSF's first, Ass't Director for Computing (CISE), he led the National Research and Education Network panel that became the Internet. In 1987 he established the Gordon Bell Prize to recognize the extraordinary efforts to exploit modern highly parallel computers. Bell maintains three interests: computers: their evolution and use, technology-based startup companies, and lifelogging. He is a member or Fellow of the American Academy of Arts and Sciences, Association of Computing Machinery, Institute of Electrical and Electronic Engineers, the National Academy of Engineering, National Academy of Science, the Australia Academy of Technological Sciences and Engineering and received The 1991 National Medal of Technology. He is a founding trustee of the Computer History Museum, Mountain View, CA. and lives in San Francisco. http://gordonbell.azurewebsites.net
Host: Cyrus Shahabi
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: CS Events
-
CS Colloquium: Jane E. - Artistic Vision: Interactive Computational Guidance for Developing Expertise
Tue, Apr 02, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jane E., UC San Diego
Talk Title: Artistic Vision: Interactive Computational Guidance for Developing Expertise
Series: Computer Science Colloquium
Abstract: Computer scientists have long worked towards the vision of human-AI collaboration for augmenting human capabilities and intellect. My work contributes to this vision by asking: How can computational tools not only help a user complete a task, but also help them develop their own domain expertise while doing so?
I investigate this question by designing new interactive tools for domains of artistic creativity. My work is inspired by the fact that expert artists have trained their eyes to “see” in ways that embed their expert domain knowledge—in this case, core artistic concepts. As instructors, experts have also designed approaches to intentionally communicate their vision to their students. My work designs creativity tools that leverage these expert structures to help novices develop this expert-like "artistic vision"—specifically through providing guidance to scaffold their design processes. In this talk, I will demonstrate my approach for designing tools that embed such guidance for photography and visual design that embed the underlying design principles. I will show that these tools are able to scaffold novices’ to be more aware of these artistic concepts during their creative process.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Jane E is Postdoctoral Fellow at The Design Lab at UCSD under the guidance of mentors Steven Dow and Haijun Xia. She earned her PhD in Computer Science from Stanford University, where she was co-advised by James Landay and Pat Hanrahan. Her research lies at the intersection of human-computer interaction and computer graphics with a focus on designing computational guidance to support novices in developing their own creative expertise. Her work takes inspiration from cognitive science and education theory to design computational tools that scaffold novices’ creative processes. Jane is grateful to have been selected as a Rising Star in EECS and to have been supported by a Microsoft Research Dissertation Grant, Hasso Plattner Institute’s Design Thinking Research Program, Brown Institute for Media Innovation, and UCSD CSE’s Postdoctoral Fellowship Program. She previously worked on the Microsoft Photos app as a software engineer after receiving her BSE from Princeton University. For more information, see her website: ejane.me
Host: Souti Chattopadhyay
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Sai Praneeth Karimireddy - Building Planetary-Scale Collaborative Intelligence
Wed, Apr 03, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Sai Praneeth Karimireddy, University of California, Berkeley
Talk Title: Building Planetary-Scale Collaborative Intelligence
Abstract: Today, access to high-quality data has become the key bottleneck to deploying machine learning. Often, the data that is most valuable is locked away in inaccessible silos due to unfavorable incentives and ethical or legal restrictions. This is starkly evident in health care, where such barriers have led to highly biased and underperforming tools. Using my collaborations with Doctors Without Borders and the Cancer Registry of Norway as case studies, I will describe how collaborative learning systems, such as federated learning, provide a natural solution; they can remove barriers to data sharing by respecting the privacy and interests of the data providers. Yet for these systems to truly succeed, three fundamental challenges must be confronted: These systems need to 1) be efficient and scale to massive networks, 2) manage the divergent goals of the participants, and 3) provide resilient training and trustworthy predictions. I will discuss how tools from optimization, statistics, and economics can be leveraged to address these challenges. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Sai Praneeth Karimireddy is a postdoctoral researcher at the University of California, Berkeley with Mike I. Jordan. Karimireddy obtained his undergraduate degree from the Indian Institute of Technology Delhi and his PhD at the Swiss Federal Institute of Technology Lausanne (EPFL) with Martin Jaggi. His research builds large-scale machine learning systems for equitable and collaborative intelligence and designs novel algorithms that can robustly and privately learn over distributed data (i.e., edge, federated, and decentralized learning). His work has seen widespread real-world adoption through close collaborations with public health organizations (e.g., Doctors Without Borders, the Red Cross, the Cancer Registry of Norway) and with industries such as Meta, Google, OpenAI, and Owkin. Karimireddy's research has been recognized by the EPFL Patrick Denantes Memorial Prize for the best computer science thesis, the Dimitris N. Chorafas Foundation Award for exceptional applied research, an EPFL thesis distinction award, a Swiss National Science Foundation fellowship, and best paper awards at the International Workshop on Federated Learning for User Privacy and Data Confidentiality at ICML 2021 and the International Workshop on Federated Learning: Recent Advances and New Challenges at NeurIPS 2022.
Host: Jiapeng Zhang / Mahdi Soltanolkotabi
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Jason Wu - Computational Understanding of User Interfaces
Thu, Apr 04, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jason Wu, CMU
Talk Title: Computational Understanding of User Interfaces
Series: Computer Science Colloquium
Abstract: A grand challenge in human-computer interaction (HCI) is constructing user interfaces (UIs) that make computers useful for all users across all contexts. Today, most UIs are manually designed for a rigid set of assumptions and are unable to dynamically accommodate the diversity of user abilities, usage contexts, or computing technologies. The goal of my research is to build a machine that can understand and operate any UI then dynamically convert it into a new personalized, context-dependent representation. In this talk, I focus on three areas that define this approach for enhancing human-computer interaction. First, I describe approaches for understanding user ability and context embodied by a recommendation system that recommends device settings (e.g., accessibility features) based on sensed usage behaviors and user interaction logs. Next, I introduce several machine learning models that reliably understand the semantics (content and functionality) of any graphical UI from its visual appearance, unlocking new possibilities for many existing systems such as assistive technology, software testing, and UI automation. Finally, I present systems that incorporate both user and UI understanding to synthesize improved interfaces using a novel fine-tuned large language model (LLM) for UI generation. Improved machine understanding of UIs has the potential to redefine how we use computers in the future and drive advances in many fields such as HCI, machine learning and software engineering.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Jason Wu is a PhD candidate in the HCI Institute at Carnegie Mellon University advised by Jeffrey Bigham. In his research, Jason builds data-driven and computational systems that understand, manipulate, and synthesize user interfaces to maximize the usability and accessibility of computers . His research has been published in top venues for human-computer interaction, user interface technology, accessibility, and machine learning, where he has received several best paper awards (CHI 2021, W4A 2021) and honorable mention awards (CHI 2020, CHI 2023). His work has also been recognized outside of academic conferences by a Fast Company Innovation by Design Student Finalist Award, press coverage in major outlets such as TechCrunch and AppleInsider, and by the FCC Chair Awards for Advancements in Accessibility. Jason is a recipient of the NSF Graduate Research Fellowship and selected as a Heidelberg Laureate Forum Young Researcher.
Host: Souti Chattopadhyay
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
PhD Defense - Jared Coleman
Thu, Apr 04, 2024 @ 10:00 AM - 11:30 AM
Thomas Lord Department of Computer Science
University Calendar
PhD Defense: Jared Coleman
Title: Dispersed Computing for Dynamic Environments Committee: Bhaskar Krishnamachari (Chair), Konstantinos Psounis, Jyotirmoy Deshmukh
Abstract: Scheduling a distributed application modeled as a directed acyclic task graph over a set of networked compute nodes is a fundamental problem in distributed computing and thus has received substantial scholarly attention. Most existing solutions, however, fall short of accommodating the dynamic and stochastic nature of modern dispersed computing systems (e.g., IoT, edge, and robotic systems) where applications and compute networks have stricter and less stable resource constraints. In this dissertation, we identify problems and propose solutions that address this gap and advance the current state-of-the-art in task scheduling.Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: Everyone Is Invited
Contact: Asiroh Cham
-
CS Colloquium: Xuhai Orson Xu - How Do We Get There?: Toward Intelligent Behavior Intervention
Mon, Apr 08, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Xuhai Orson Xu, MIT
Talk Title: How Do We Get There?: Toward Intelligent Behavior Intervention
Abstract: As the intelligence of everyday smart devices continues to evolve, they can already monitor basic health behaviors such as physical activities and heart rates. The vision of an intelligent behavior change intervention pipeline for health -- combining behavior modeling & interaction design -- seems to be within reach. How do we get there?In this talk, I will introduce a comprehensive intervention pipeline that bridges behavior science theory-driven designs and generalizable behavior models. I will also introduce my efforts on passive sensing datasets, human-centered algorithms, and a benchmark platform that drives the community toward more robust and deployable intervention systems for health and well-being. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Xuhai "Orson" Xu is a postdoc at MIT EECS. He received his PhD at the University of Washington. Specializing in human-computer interaction, applied machine learning, and health, Xu develops intelligent behavior intervention systems to promote human health and well-being. His research covers two aspects -- 1) building deployable human-centered behavior models and 2) designing interactive user experiences -- to establish a complete system to improve end-users' well-being. Moreover, his research also goes beyond end-users and supports health experts by designing new human-AI collaboration paradigms in clinical settings. Xu has earned several awards, including 9 Best Paper, Best Paper Honorable Mention, and Best Artifact awards. His research has been covered by media outlets such as the Washington Post and ACM News. He was recognized as the Outstanding Student Award Winner at UbiComp 2022, the 2023 UW Distinguished Dissertation Award, and the 2024 Innovation and Technology Award at the Western Association of Graduate Schools.
Host: Stefanos Nikolaidis
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Niloufar Salehi - Designing Reliable Human-AI Interactions: Translating Languages and Matching Students
Tue, Apr 09, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Niloufar Salehi, UC Berkeley
Talk Title: Designing Reliable Human-AI Interactions: Translating Languages and Matching Students
Abstract: How can users trust an AI system that fails in unpredictable ways? Machine learning models, while powerful, can produce unpredictable results. This uncertainty becomes even more pronounced in areas where verification is challenging, such as in machine translation, and where reliance depends on adherence to community values, such as student assignment algorithms. Providing users with guidance on when to rely on a system is challenging because models can create a wide range of outputs (e.g. text), error boundaries are highly stochastic, and automated explanations themselves may be incorrect. In this talk, I will first focus on the case of health-care communication to share approaches to improving the reliability of ML-based systems by guiding users to gauge reliability and recover from potential errors. Next, I will focus on the case of student assignment algorithms to examine modeling assumptions and perceptions of fairness in AI systems. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Niloufar Salehi is an assistant professor in the School of Information at UC, Berkeley where she is a member of Berkeley AI Research (BAIR). She studies human-computer interaction, with her research spanning education to healthcare to restorative justice. Her research interests are social computing, human-centered AI, and more broadly, human-computer interaction (HCI). Her work has been published and received awards in premier venues including ACM CHI, CSCW, and EMNLP and has been covered in VentureBeat, Wired, and the Guardian. She is a W. T. Grant Foundation scholar for her work on promoting equity in student assignment algorithms. She received her PhD in computer science from Stanford University in 2018.
Host: Souti Chattopadhyay
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
Computer Science General Faculty Meeting
Wed, Apr 10, 2024 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Invited Faculty Only
Contact: Assistant to CS Chair
-
CAIS Seminar: Nowcasting Temporal Trends Using Indirect Surveys
Wed, Apr 10, 2024 @ 02:30 PM - 03:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Ajitesh Srivastava, USC CAIS Associate Director & Research Assistant Professor of Electrical and Computer Engineering
Talk Title: CAIS Seminar: Nowcasting Temporal Trends Using Indirect Surveys
Abstract: Indirect surveys, in which respondents provide information about other people they know, have been proposed for estimating (nowcasting) the size of a hidden population where privacy is important or the hidden population is hard to reach. Examples include estimating casualties in an earthquake, conditions among female sex workers, and the prevalence of drug use and infectious diseases. The Network Scaleup Method (NSUM) is the classical approach to developing estimates from indirect surveys, but it was designed for one-shot surveys. Further, it requires certain assumptions and asking for or estimating the number of individuals in each respondent’s network. In recent years, surveys have been increasingly deployed online and can collect data continuously (e.g., COVID-19 surveys on Facebook during much of the pandemic). Conventional NSUM can be applied to these scenarios by analyzing the data independently at each point in time, but this misses the opportunity of leveraging the temporal dimension. We propose to use the responses from indirect surveys collected over time and develop analytical tools (i) to prove that indirect surveys can provide better estimates for the trends of the hidden population over time, as compared to direct surveys and (ii) to identify appropriate temporal aggregations to improve the estimates. We demonstrate through extensive simulations that our approach outperforms traditional NSUM and direct surveying methods. We also empirically demonstrate the superiority of our approach on a real indirect survey dataset of COVID-19 cases.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
RSVP/Register for the Zoom webinar here: https://usc.zoom.us/webinar/register/WN_LkSI20EOQPm5npI_d8w5HA
Biography: Dr. Ajitesh Srivastava is a USC CAIS associate director and Research Assistant Professor of Electrical and Computer Engineering. He earned his PhD in computer science from USC. Dr. Srivastava’s research interests include social networks, algorithms, parallel computing, and machine learning applied to social good, crime, smart grids, and computer architecture.
Host: CAIS
More Info: https://cais.usc.edu/events/nowcasting-temporal-trends-using-indirect-surveys/
Webcast: https://usc.zoom.us/webinar/register/WN_LkSI20EOQPm5npI_d8w5HALocation: HYBRID: CPA 156 & Zoom
WebCast Link: https://usc.zoom.us/webinar/register/WN_LkSI20EOQPm5npI_d8w5HA
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://cais.usc.edu/events/nowcasting-temporal-trends-using-indirect-surveys/
-
CS Colloquium: Z. Morley Mao - Staying Ahead of the Arms Race in Cybersecurity: Realizing Effective Attack Prevention, Detection, and Mitigation for Legacy and Future Networked Systems.
Thu, Apr 11, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Z. Morley Mao, University of Michigan
Talk Title: Staying Ahead of the Arms Race in Cybersecurity: Realizing Effective Attack Prevention, Detection, and Mitigation for Legacy and Future Networked Systems.
Abstract: The landscape of cybersecurity is a dynamic arena, characterized by an ongoing arms race between malicious actors exploiting vulnerabilities and defenders striving to safeguard systems against potential devastation. With the increasing integration of cyberphysical systems like autonomous vehicles and AI/ML technologies into our daily lives, the reactive nature of our security measures poses significant risks. In this talk, I will articulate a forward-looking vision for cybersecurity research. Drawing upon the collective efforts of my team, I will delve into innovative approaches aimed at addressingsecurity challenges across diverse fronts. From enhancing the resilience of the time-honored DNS system to fortifying the security of ubiquitous mobile platforms, and extending to safeguarding ML-based systems within the burgeoning realms of IoT and autonomous vehicles, our focus is proactive. Our strategy entails the construction of inherently secure systems designed to systematically eliminate vulnerabilities. We advocate for the integration of formalisms derived from disciplines such as programming languages, coupled with the provision of robust security guarantees within the very fabric of the platform architecture. Through this proactive paradigm shift, we endeavor to usher in a new era of cybersecurity resilience and reliability. This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Z. Morley Mao is a Professor at the University of Michigan, having completed her Ph.D. at UC Berkeley on robust Internet routing protocol design and effective network measurement techniques to uncover network properties with security and performance implications. She is an ACM and IEEE Fellow, a recipient of the Sloan Fellowship, the NSF CAREER Award, the ARMY YIP Award, and an IBM Faculty Award. Her other honors include the Morris Wellman Faculty Development Professor, EECS Achievement Award, College of Engineering George J. Huebner Research Excellence Award at University of Michigan. Her recent research focus encompasses adversarial machine learning, AV security, and next generation wireless networks.
Host: Harsha V. Madhyastha
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
Robotics as an Eco-Effective Contingency for Weakened Ecosystems?
Thu, Apr 11, 2024 @ 10:00 AM - 11:30 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Prof. Thomas Schmickl , Professor - Institute of Biology at the University of Graz, Austria
Talk Title: Robotics as an Eco-Effective Contingency for Weakened Ecosystems?
Abstract: Our planet is on the brink of the 6th mass extinction, as our ecosystems are rapidly losing both diversity and biomass. As intra- and inter-specific interaction networks weaken, ecosystems become increasingly unstable, setting off on a downward trajectory along a deadly spiral. In my keynote, I will explore how robotic systems can play a crucial role in supporting ecosystems and communities. I will show three levels of agency how a „tech for good“ approach might be helpful to fight ecosystem decay: Monitoring, intervention and restoration. By mitigating ecosystem decay, robots may buy us precious time to address the root causes of environmental crises. I will show innovative systems that we’ve developed over recent years — the initial strides toward going beyond mere animal-interaction systems by establishing eco-effective robotics.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Thomas Schmickl (https://www.thomasschmickl.eu) is full professor at the Institute of Biology at the University of Graz, Austria. There he also supervises the Artificial Life Lab (https://alife.uni-graz.at), which he founded in 2007 after returning from a HHMI visiting professorship in the USA. In 2012, he was appointed the Basler Chair of Excellence at the East Tennessee State University (ETSU). His research focuses on the biology of social insects and on ecological modeling, as well as on bio-inspired engineering including swarm-, modular-, hormone-, and evolutionary- robotics. He was/is a partner in the EU-funded projects I- Swarm, Symbrion, Replicator, FloraRobotica, RoboRoyale and serves as the leading scientist and consortium coordinator of the EU grants CoCoRo, ASSISIbf, subCULTron, Atempgrad and Hiveopolis. His research seeks to improve the current state-of-the-art in robotics to allow robotic agents to be more like animals or plants, by being more adaptive, resilient, and flexible. Living organisms are parts of his targeted bio-hybrid robotic systems, with the goal to form sustainable organism-technology symbioses. In 2018, he founded the Field of Excellence COLIBRI (Complexity of Life in Basic Research & Innovation, https://colibri.uni-graz.at) at University of Graz, a network of full professors researching complexity with a focus on living systems, joining forces across various disciplines.
Host: Prof. Wei-Min Shen, Associate Professor of Computer Science Practice
Location: Henry Salvatori Computer Science Center (SAL) - 126
Audiences: Everyone Is Invited
Contact: Thomas Lord Department of Computer Science
-
CS Colloquium: TBA
Tue, Apr 16, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: TBA, TBA
Talk Title: TBA
Series: Computer Science Colloquium
Abstract: TBA
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: TBA
Host: Ruishan Liu
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Julia Len - Designing secure-by-default cryptography for computer systems
Wed, Apr 17, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Julia Len, Cornell University
Talk Title: Designing secure-by-default cryptography for computer systems
Series: Computer Science Colloquium
Abstract: Designing cryptography that protects against all the threats seen in deployment can be surprisingly hard to do. This frequently translates into mitigations which offload important security decisions onto practitioners or even end users. The end result is subtle vulnerabilities in our most important cryptographic protocols. In this talk, I will present an overview of my work in two major areas on designing cryptography for real-world applications that targets security by default: (1) symmetric encryption and (2) key transparency for end-to-end encrypted systems. I will describe my approach of understanding real-world threats to provide robust, principled defenses with strong assurance against these threats in practice. My work includes introducing a new class of attacks exploiting symmetric encryption in applications, developing new theory to act as guidance in building better schemes, and designing practical cryptographic protocols. This work has seen impact through updates in popular encryption tools and IETF draft standards and through the development of protocols under consideration for deployment.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Julia Len is a Ph.D. candidate at Cornell University where she is advised by Thomas Ristenpart and is based in New York City at Cornell Tech. Her research interests are broadly in the areas of applied cryptography and computer security. Julia has been named a 2023 Rising Star in EECS and has received the NSF Graduate Research Fellowship. She has also worked at Zoom and Microsoft on cryptographic protocol designs which are being considered for deployment in their video calling products.
Host: Jiapeng Zhang / Konstantinos Psounis
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
Computer Science General Faculty Meeting
Wed, Apr 17, 2024 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Invited Faculty Only
Contact: Assistant to CS Chair
-
Thomas Lord Department of Computer Science: Distinguished Lecture Series feat. Dr. Mohit Bansal
Thu, Apr 18, 2024 @ 02:00 PM - 04:15 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Mohit Bansal, John R. & Louise S. Parker Distinguished Professor, UNC Chapel Hill
Talk Title: Multimodal Generative LLMs: Unification, Interpretability, Evaluation
Abstract: In this talk, I will present our journey of large-scale multimodal pretrained (generative) models across various modalities (text, images, videos, audio, layouts, etc.) and enhancing their important aspects such as unification (for generalizability, shared knowledge, and efficiency), interpretable programming/planning (for controllability and faithfulness), and evaluation (of fine-grained skills, faithfulness, and social biases). We will start by discussing early cross-modal vision-and-language pretraining models (LXMERT). We will then look at early unified models (VL-T5) to combine several multimodal tasks (such as visual QA, referring expression comprehension, visual entailment, visual commonsense reasoning, captioning, and multimodal translation) by treating all tasks as text generation. We will next look at recent, progressively more unified models (with joint objectives and architecture, as well as newer unified modalities during encoding and decoding) such as textless video-audio transformers (TVLT), vision-text-layout transformers for universal document processing (UDOP), and interactive, interleaved, composable any-to-any text-audio-image-video multimodal generation (CoDi, CoDi-2). Second, we will discuss interpretable and controllable multimodal generation (to improve faithfulness) via LLM-based planning and programming, such as layout-controllable image generation via visual programming (VPGen), consistent multi-scene video generation via LLM-guided planning (VideoDirectorGPT), open-domain, open-platform diagram generation (DiagrammerGPT), and LLM-based adaptive environment generation for training embodied agents (EnvGen). I will conclude with important faithfulness and bias evaluation aspects of multimodal generation models, based on fine-grained skill and social bias evaluation (DALL-Eval), interpretable and explainable visual programs (VPEval), as well as reliable fine-grained evaluation via Davidsonian semantics based scene graphs (DSG).
Please RSVP by Monday, April 15, 2024 (5:00 p.m., PST): https://forms.gle/shymnJc87y5fHFJaA
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Dr. Mohit Bansal is the John R. & Louise S. Parker Distinguished Professor and the Director of the MURGe-Lab (UNC-NLP Group) in the Computer Science department at UNC Chapel Hill. He received his PhD from UC Berkeley in 2013 and his BTech from IIT Kanpur in 2008. His research expertise is in natural language processing and multimodal machine learning, with a particular focus on multimodal generative models, grounded and embodied semantics, faithful language generation, and interpretable, efficient, and generalizable deep learning. He is a recipient of IIT Kanpur Young Alumnus Award, DARPA Director's Fellowship, NSF CAREER Award, Google Focused Research Award, Microsoft Investigator Fellowship, Army Young Investigator Award (YIP), DARPA Young Faculty Award (YFA), and outstanding paper awards at ACL, CVPR, EACL, COLING, and CoNLL. He has been a keynote speaker for the AACL 2023, CoNLL 2023, and INLG 2022 conferences. His service includes EMNLP and CoNLL Program Co-Chair, and ACL Executive Committee, ACM Doctoral Dissertation Award Committee, ACL Americas Sponsorship Co-Chair, and Associate/Action Editor for TACL, CL, IEEE/ACM TASLP, and CSL journals. Webpage: https://www.cs.unc.edu/~mbansal/
Host: USC Thomas Lord Department of Computer Science
More Info: https://forms.gle/shymnJc87y5fHFJaA
Location: Seeley G. Mudd Building (SGM) - 124
Audiences: Everyone Is Invited
Contact: Thomas Lord Department of Computer Science
Event Link: https://forms.gle/shymnJc87y5fHFJaA
-
ShowCAIS Symposium 2024
Fri, Apr 19, 2024 @ 08:45 AM - 04:15 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Bistra Dilkina, Eric Rice, and Phebe Vayanos, USC CAIS Co-Directors
Talk Title: ShowCAIS Symposium 2024
Abstract: ShowCAIS is the USC Center for AI in Society's annual symposium highlighting research by USC students, faculty, and alumni. The event provides an opportunity for scholars and experts from all disciplines to share their findings around AI for social good.
WEBSITE: https://sites.google.com/usc.edu/showcais-2024/
EVENTBRITE REGISTRATION: https://www.eventbrite.com/e/showcais-2024-tickets-850982841587
Host: USC Center for AI in Society
More Info: https://www.eventbrite.com/e/showcais-2024-tickets-850982841587
Location: Michelson Center for Convergent Bioscience (MCB) - 101 & 102
Audiences: Everyone Is Invited
Contact: Thomas Lord Department of Computer Science
Event Link: https://www.eventbrite.com/e/showcais-2024-tickets-850982841587
-
PhD Thesis Proposal - Qinyuan Ye
Mon, Apr 22, 2024 @ 10:00 AM - 11:30 AM
Thomas Lord Department of Computer Science
University Calendar
Title: Cross-Task Generalization Abilities of Large Language Models
Committee Members: Xiang Ren (Chair), Robin Jia, Swabha Swayamdipta, Jesse Thomason, Morteza Dehghani
Date & Time: Monday, April 22, 10am-11:30am\
Location: SAL 213
Abstract: Humans can learn a new language task efficiently with only a few examples, by leveraging their knowledge and experience obtained when learning prior tasks. Enabling similar cross-task generalization abilities in NLP systems is fundamental for achieving the goal of general intelligence and enabling broader and more scalable adoption of language technology in future applications. In this thesis proposal, I will present my work on (1) benchmarking cross-task generalization abilities with diverse NLP tasks; (2) developing new model architecture for improving cross-task generalization abilities; (3) analyzing and predicting the generalization landscape of current state-of-the-art large language models. Additionally, I will outline future research directions, along with preliminary thoughts on addressing them.
Zoom Link: https://usc.zoom.us/j/93269270403?pwd=NVNmN085bm5SWXNnNGErcXczeVkxdz09Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Qinyuan Ye
Event Link: https://usc.zoom.us/j/93269270403?pwd=NVNmN085bm5SWXNnNGErcXczeVkxdz09
-
PhD Defense- Tiancheng Jin
Mon, Apr 22, 2024 @ 04:00 PM - 05:30 PM
Thomas Lord Department of Computer Science
Student Activity
PhD Defense- Tiancheng Jin
Title: Robust and Adaptive Online Reinforcement Learning
Committee: Haipeng Luo (Chair), Rahul Jain, Vatsal Sharron
Abstract: Reinforcement learning (RL) is a machine learning (ML) technique on learning to make optimal sequential decisions via interactions with an environment. In recent years, RL achieved great success in many artificial intelligence tasks, and has been widely regarded as one of the keys towards Artificial General Intelligence (AGI). However, most RL models are trained on simulators, and suffer from the reality gap: a mismatch between simulated and real-world performance. Moreover, recent work has shown that RL models are especially vulnerable to adversarial attacks. This motivates the research on improving the robustness of RL, that is, the ability of ensuring worst-case guarantees.
On the other hand, it is not favorable to be too conservative/pessimistic and sacrifice too much performance while the environment is not difficult to deal with.In other words, adaptivity --- the capability of automatically adapting to the maliciousness of the environment, is especially desirable to RL algorithms: they should not only target worst-case guarantee, but also pursue instance optimality and achieve better performance against benign environments.
In this thesis, we focus on designing practical, robust and adaptive reinforcement algorithms.
Specifically, we take inspiration from the online learning literature, and consider interacting with a sequence of Markov Decision Processes (MDPs), which captures the nature of changing environment. We hope that the techniques and insight developed in this thesis could shed light on improving existing deep RL algorithms for future applications.Location: Kaprielian Hall (KAP) - 141
Audiences: Everyone Is Invited
Contact: Tiancheng Jin
-
Computer Science General Faculty Meeting
Tue, Apr 23, 2024 @ 12:00 AM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: TBD
Audiences: Invited Faculty Only
Contact: Assistant to CS Chair
-
PhD Dissertation Defense - Arka Sadhu
Tue, Apr 23, 2024 @ 02:00 PM - 03:30 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Grounding Language in Images and Videos
Location: SAL 213
Time: 2 pm on April 23, 2024
Committee Members: Ram Nevatia (Chair), Xiang Ren, Toby Mintz
Abstract: My thesis investigates the problem of grounding language in images and videos -- the task of associating linguistic symbols to perceptual experiences and actions -- which is fundamental to developing multi-modal models that can understand and jointly reason over images, videos, and text. The overarching goal of my dissertation is to bridge the gap between language and vision as a means to a ``deeper understanding'' of images and videos to allow developing models capable of reasoning over longer-time horizons such as hour-long movies, or a collection of images, or even multiple videos. In this thesis, I will introduce the various vision-language tasks developed during my Ph.D. which include grounding unseen words, spatiotemporal localization of entities in a video, video question-answering, and visual semantic role labeling in videos, reasoning across more than one image or a video, and finally, weakly-supervised open-vocabulary object detection. For each of these tasks, I will further discuss the development of corresponding datasets, evaluation protocols, and model frameworks. These tasks aim to investigate a particular phenomenon inherent in image or video understanding in isolation, develop corresponding datasets and model frameworks, and outline evaluation protocols robust to data priors.
The resulting models can be used for other downstream tasks like obtaining common-sense knowledge graphs from instructional videos or drive end-user applications like Retrieval, Question Answering, and Captioning.
Zoom Link: https://usc.zoom.us/j/94652316277?pwd=QTdqcklJMjg2UE03ZVZHbmFvWU9nQT09Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Arka Sadhu
-
PhD Thesis Defense - Pei Zhou
Wed, Apr 24, 2024 @ 02:00 AM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Defense - Pei Zhou
Committee Members: Xiang Ren (Chair), Jay Pujara (Co-Chair), Toby Mintz, Jieyu Zhao
Title: Common Ground Reasoning for Communicative Agents
Abstract: Effective communication requires reasoning to reach mutual beliefs and knowledge among participants, a process called grounding. Large language model (LLM)-powered conversational AIs have displayed impressive capabilities, showing the potential of building AI agents that can interact with humans and the world smoothly. However, challenges remain unsolved for AI models to become capable communicative agents including understanding implicit intents and reaching goals. My PhD thesis outlines my research aiming to tackle these challenges by teaching models to reason to build common ground to become better communicators. Specifically, I focus on 1) enhancing conversational models with common sense knowledge; 2) modeling theory-of-mind capabilities to build goal-driven dialogue agents; and 3) eliciting metacognition by planning reasoning strategies for diverse scenarios. I will also discuss future directions including life-long self-learning with evolving common ground for personalization, interactive super-alignment to supervise models stronger than us, and measuring and improving safety to deploy agents in the wild.
Venue: RTH 306 and Zoom https://usc.zoom.us/j/2065614640
Date: 04/24/2024, 2-4PMLocation: Ronald Tutor Hall of Engineering (RTH) -
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/2065614640
-
PhD Thesis Proposal - Navid Hashemi
Thu, Apr 25, 2024 @ 10:30 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Verification and Synthesis of Controllers for Temporal Logic Objectives Using Neuro-Symbolic Methods
Committee Members: Jyotirmoy Deshmukh (Chair), Guarav Sukhatme, Chao Wang, Pierlggi Nuzzo, Lars Lindemann, Georgios Fainekos (External Member)
Date & Time: Thursday, April 25th, 10:30am - 12:00pm
Abstract: As the field of autonomy is embracing the use of neural networks for perception and control, Signal Temporal Logic (STL) has emerged as a popular formalism for specifying the task objectives and safety properties of such autonomous cyber-physical systems (ACPS). There are two important open problems in this research area: (1) how can we effectively train neural controllers in such ACPS applications, when the state dimensionality is high and when the task objectives are specified over long time horizons, and (2) how can we verify if the closed-loop system with a given neural controller satisfies given STL objectives. We review completed work in which we show how discrete-time STL (DT-STL) specifications lend themselves to a smooth neuro-symbolic encoding that enables the use of gradient-based methods for control design. We also show how a type of neuro-symbolic encoding of DT-STL specifications can be combined with neural network verification tools to provide deterministic guarantees. We also review how neural network encoding of the environment dynamics can help us combine statistical verification techniques with formal techniques for reachability analysis. We will then propose several directions that we will pursue in the future: (1) We will investigate if our neuro-symbolic encoding approach can extend to other temporal logics, especially those used for specifying properties of perception algorithms (such as Spatio-Temporal Perception Logic or STPL). Our idea is to use a neuro-symbolic encoding of STPL to improve the quality of outputs produced by perception algorithms. (2) We will investigate how control policies generated by our existing algorithms can be made robust to distribution shifts through online and offline techniques. (3) Finally, we will propose scaling our synthesis approaches to higher-dimensional observation spaces and longer horzon tasks. We conclude with the timeline to finish proposed work and write the dissertation.Location: Ronald Tutor Hall of Engineering (RTH) - 306
Audiences: Everyone Is Invited
Contact: Felante' Charlemagne
-
Phd Dissertation Defence - Haidong Zhu
Thu, Apr 25, 2024 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Shape-Assisted Multimodal Person Re-Identification
Committee Members: Ram Nevatia (Chair), Ulrich Neumann, Antonio Ortega
Date & Time: Thursday, April 25th, 12:00pm - 2:00pm
Abstract: Recognizing an individual's identity across non-overlapping images or videos, known as person re-identification, is a fundamental yet challenging task for biometric analysis. This task involves extracting and distinguishing unique features such as appearance, gait, and body shape to accurately identify individuals. Different from other representations, 3-D shape complements the body information with external human body shape prior and enhances the appearance captured in the 2-D images. Although 3-D body shape offers invaluable external shape-related information that 2-D images lack, existing body shape representations often fall short in accuracy or demand extensive image data, which is unavailable for re-identification tasks. We explore various biometric representations for comprehensive whole-body person re-identification, with a particular emphasis on leveraging 3-D body shape. We focus on enhancing the detail and few-shot learning capabilities of 3-D shape representations through the application of implicit functions and generalizable Neural Radiance Fields (NeRF). Moreover, we propose the use of 3-D body shape for alignment and supervision during training, aiming to advance the accuracy and efficiency of person re-identification techniques.Location: Hughes Aircraft Electrical Engineering Center (EEB) - 110
Audiences: Everyone Is Invited
Contact: Haidong Zhu
-
PhD Dissertation Defense - Zhaoheng Zheng
Thu, Apr 25, 2024 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Incorporating Large-Scale Vision-Language Corpora in Visual Understanding
Committee Members: Ram Nevatia (Chair), Mohammad Soleymani, Keith Jenkins
Date and Time: Thursday, April 25th, 2:00pm - 4:00pm
Abstract: As key mediators of human perception, vision and language corpora act as critical roles in the development of modern Artificial Intelligence (AI). The size of vision-language corpora has scaled up rapidly in recent years, from thousands to billions, enabling the creation of large foundation models. However, as an emerging concept, there are a series of problems yet to be explored.
We start with a study of compositional learning from pre-VLM times to the post-VLM era. We introduce a representation blending approach that creates robust features for compositional image classification and a two-stream architecture that tackles the entanglement in the feature space of the object-attribute detection problem with novel object-attribute pairs. We further design an adaptation approach to leverage CLIP encoders for compositional image classification.
The second part covers a variety of methods built with multimodal transformer models. For image retrieval, we propose a framework that assembles multimodal inputs into sequences with which a multimodal transformer encoder can be fine-tuned. The pre-training of vision-language models (VLMs) is also explored. Specifically, we introduce a fractional intermediate tower that improves the feature expressibility of dual-tower vision-language models. We further design a unified pipeline that allows a VLM to learn from not only vision-language corpora but unimodal visual and linguistic data.
Lastly, we study how to leverage the knowledge of Large Language Models (LLMs) for low-shot image classification, in a data- and computation-efficient way.
Zoom Link: https://usc.zoom.us/j/96814169370?pwd=NkhSYWFKNCsya0lyaUFBVlVDQkI3Zz09Location: Hughes Aircraft Electrical Engineering Center (EEB) - 110
Audiences: Everyone Is Invited
Contact: Zhaoheng Zheng
Event Link: https://usc.zoom.us/j/96814169370?pwd=NkhSYWFKNCsya0lyaUFBVlVDQkI3Zz09
-
PhD Dissertation Defense - Alan Romano
Tue, Apr 30, 2024 @ 09:30 AM - 11:30 AM
Thomas Lord Department of Computer Science
University Calendar
Title: Static Program Analyses for WebAssembly
Committee Members: Weihang Wang (Chair), Chao Wang, and Pierluigi Nuzzo
Date/Time: Tuesday, April 30th, 9:30am - 11:30am
Abstract: WebAssembly is a recent standard for the web that aims to enable high-performance web applications that can run at near-native speeds. The standard has gained attention in both academia and industry for its ability to speed up existing user-facing web applications. Due to its well-defined and sound design, many static program analysis techniques have been developed to accomplish various purposes of WebAssembly analysis. However, we identify gaps in the static program analysis tools of the current WebAssembly ecosystem. We find that current program optimizations applied on WebAssembly modules may lead to diminished performance. We also identify a lack of tools that help developers understand WebAssembly modules through robust binary decompilation. Finally, we find a gap in the ability to analyze cross-language WebAssembly applications across the two languages they are typically implemented in, i.e., WebAssembly and JavaScript.
In this thesis, we present a novel WebAssembly Analysis Framework, or WAF . WAF is a static program analysis framework for WebAssembly modules that consists of multiple intermediate representations. Inspired by frameworks made for Java, the core of our framework lies in our three intermediate representations that each model the WebAssembly module at a different semantic level. This structure enables WAF to serve in multiple use cases, including program optimizations, binary decompilation, cross-language program analysis, and malware detection. We aim to show that our framework can improve static program analysis in the areas that the WebAssembly ecosystem is lacking.Location: Henry Salvatori Computer Science Center (SAL) - 322
Audiences: Everyone Is Invited
Contact: Alan Romano
