- talks - lists.cs.princeton.edu

CS Colloquium speaker Feras Saad: TODAY at 12:30pm
by Emily C. Lawrence 04 Apr '22

04 Apr '22

Speaker: Feras Saad, Massachusetts Institute of Technology Date: Thursday, March 31, 2022 Time: 12:30pm EST Location: CS 105 Host: Ryan Adams Event page: https://www.cs.princeton.edu/events/26183 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Scalable Structure Learning and Inference via Probabilistic Programming Abstract: Probabilistic programming supports probabilistic modeling, learning, and inference by representing sophisticated probabilistic models as computer programs in new programming languages. This talk presents efficient probabilistic programming-based techniques that address two fundamental challenges in scaling and automating structure learning and inference over complex data. First, I will describe scalable structure learning methods that make it possible to automatically synthesize probabilistic programs in an online setting by performing Bayesian inference over hierarchies of flexibly structured symbolic program representations, for discovering models of time series data, tabular data, and relational data. Second, I will present fast compilers and symbolic analyses that compute exact answers to a broad range of inference queries about these learned programs, which lets us extract interpretable patterns and make accurate predictions in real time. I will demonstrate how these techniques deliver state-of-the-art performance in terms of runtime, accuracy, robustness, and programmability by drawing on several examples from real-world applications, which include adapting to extreme novelty in economic time series, online forecasting of flu rates given sparse multivariate observations, discovering stochastic motion models of zebrafish hunting, and verifying the fairness of machine learning classifiers. Bio: Feras Saad is a PhD candidate in Computer Science at MIT working at the intersection of programming languages, probabilistic machine learning, and computational statistics. His research is accompanied with a collection of popular open-source probabilistic programming systems used by collaborators at Intel, Takeda, Liberty Mutual, IBM, and the Bill & Melinda Gates Foundation for practical applications of structure learning and probabilistic inference. Feras' MEng thesis on probabilistic programming and data science has been recognized with the 1st Place Computer Science Thesis Award at MIT.

1 1

Sunny Cui will present her MSE Talk "Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories" on Friday, April 8th, 2022 11am via Zoom.
by Nicki Mahler 01 Apr '22

01 Apr '22

Sunny Cui will present her MSE Talk " Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories" on Friday, April 8th, 2022 11am via Zoom. Zoom link: https://princeton.zoom.us/j/93221657583?pwd=VHVacWZKS3lQNkNCcUNWU2hnbUlldz09 Committee members: Barbara Engelhardt (adviser), Ben Raphael (reader) All are welcome to attend. Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories Gaussian processes (GPs) are a versatile nonparametric model for nonlinear regression and have been widely used to study spatiotemporal phenomena. However, standard GPs offer limited interpretability and generalizability for datasets with naturally occurring hierarchies. With large-scale, rapidly-updating electronic health record (EHR) data, we want to study patient trajectories across diverse patient cohorts while preserving patient subgroup structure. In this work, we partition our cohort of over 2000 COVID-19 patients by sex and ethnicity. We develop and apply a hierarchical Gaussian process and a mixture of experts (MOE) hierarchical GP model to fit patient trajectories on clinical markers of disease progression. A case study for albumin, an effective predictor of COVID-19 patient outcomes, highlights the predictive performance of these models. These hierarchical spatiotemporal models of EHR data bring us a step closer toward our goal of building flexible approaches to capture patient data that can be used in real-time systems.

1 0

CS Colloquium Series: week of April 4-8
by Emily C. Lawrence 01 Apr '22

01 Apr '22

Here is the full list of CS Colloquium talks for next week. All talks will be recorded. ~~~~~ CS Colloquium Speaker Speaker: Tej Chajed, Massachusetts Institute of Technology Date: Monday, April 4, 2022 Time: 12:30pm EST Location: CS 105 Host: Amit Levy Event page: https://www.cs.princeton.edu/events/26180 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Formal verification of a concurrent file system Abstract: Bugs in systems software like file systems, databases, and operating systems can have serious consequences, ranging from security vulnerabilities to data loss, and these bugs affect all the applications built on top. Systems verification is a promising approach to improve the reliability of our computing infrastructure, since it can eliminate whole classes of bugs through machine-checked proofs that show a system always meets its specification. In this talk, I’ll present a line of work culminating in a verified, concurrent file system called DaisyNFS. The file system comes with a proof that shows operations appear to execute correctly and atomically (that is, all-or-nothing), even if the computer crashes and when processing concurrent operations. I’ll describe how a combination of design and verification techniques make it possible to carry out the proof for an efficient implementation. Bio: Tej Chajed is a final-year PhD student at MIT advised by Frans Kaashoek and Nickolai Zeldovich. His research is on systems verification, ranging from developing new foundations through designing and verifying high-performance systems. Before MIT, he completed his undergraduate degree in Electrical Engineering and Computer Science at UIUC. His work has been in part supported by an NSF graduate research fellowship. ~~~~~ CS Colloquium Speaker Speaker: Alex Lombardi, Massachusetts Institute of Technology Date: Tuesday, April 5, 2022 Time: 12:30pm EST Location: CS 105 Host: Ran Raz Event page: https://www.cs.princeton.edu/events/26181 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Foundations of Cryptographic Proof Systems Abstract: One of computer science's greatest insights has been in understanding the power and versatility of *proofs*, which were revolutionized in the 1980s to utilize *interaction* as well as other resources such as randomization and computational hardness. Today, they form the backbone of both theoretical and practical cryptography and are simultaneously the source of deep connections to areas such as complexity theory, game theory, and quantum computation. In this talk, I will discuss general-purpose tools, techniques, and abstractions for two key aspects of cryptographic proof systems that have been poorly understood for decades: 1) Can we remove interaction from interactive proofs? Already in the 1980s, Fiat and Shamir proposed a heuristic *but unproven* methodology for removing interaction from interactive proofs, which is now ubiquitous and essential for practical applications. However, it remained open for over 30 years to prove the security of this transformation in essentially any setting of interest. My work on the Fiat-Shamir transform has led to resolutions to many long-standing open problems, including (i) building non-interactive zero knowledge proof systems based on lattice cryptography, (ii) establishing the existence of highly efficient and succinct non-interactive proof systems, and (iii) demonstrating that foundational protocols from the 80s fail to compose in parallel. 2) Are classical interactive protocols secure against quantum computers? At its heart, the problem of analyzing and ruling out quantum attacks on cryptographic protocols is the issue of “rewinding.” The inability to rewind a quantum attack stems from the no-cloning theorem, a fundamental property of quantum information. As a result, very few classical protocols were known to be secure against quantum attacks. In a recent work, I showed how to overcome these difficulties and settle many foundational questions on post-quantum cryptographic proof systems. Our main technique is showing how to efficiently extract certain pieces of (classical) information from a quantum attacker without disturbing its internal state. Bio: Alex Lombardi is a graduate student at MIT advised by Vinod Vaikuntanathan. He is the recipient of an MIT Presidential fellowship, an NDSEG fellowship, and a Charles M. Vest NAE Grand Challenges fellowship. He is broadly interested in cryptography and theoretical computer science with a focus on cryptographic proof systems and post-quantum security. ~~~~~ CS Colloquium Speaker Speaker: Natasha Jaques, Google Brain / University of California, Berkeley Date: Thursday, April 7, 2022 Time: 12:30pm EST Location: CS 105 Host: Karthik Narasimhan Event page: https://www.cs.princeton.edu/events/26182 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Social Reinforcement Learning Abstract: Social learning helps humans and animals rapidly adapt to new circumstances, coordinate with others, and drives the emergence of complex learned behaviors. What if it could do the same for AI? This talk describes how Social Reinforcement Learning in multi-agent and human-AI interactions can address fundamental issues in AI such as learning and generalization, while improving social abilities like coordination. I propose a unified method for improving coordination and communication based on causal social influence. I then demonstrate that multi-agent training can be a useful tool for improving learning and generalization. I present PAIRED, in which an adversary learns to construct training environments to maximize regret between a pair of learners, leading to the generation of a complex curriculum of environments. Agents trained with PAIRED generalize more than 20x better to unknown test environments. Ultimately, the goal of my research is to create intelligent agents that can assist humans with everyday tasks; this means leveraging social learning to interact effectively with humans. I show that learning from human social and affective cues scales more effectively than learning from manual feedback. However, it depends on accurate recognition of such cues. Therefore I discuss how to dramatically enhance the accuracy of affect detection models using personalized multi-task learning to account for inter-individual variability. Together, this work argues that Social RL is a valuable approach for developing more general, sophisticated, and cooperative AI, which is ultimately better able to serve human needs. Bio: Natasha Jaques holds a joint position as a Senior Research Scientist at Google Brain and Visiting Postdoctoral Scholar at UC Berkeley. Her research focuses on Social Reinforcement Learning in multi-agent and human-AI interactions. Natasha completed her PhD at MIT, where her thesis received the Outstanding PhD Dissertation Award from the Association for the Advancement of Affective Computing. Her work has also received Best Demo at NeurIPS, an honourable mention for Best Paper at ICML, Best of Collection in the IEEE Transactions on Affective Computing, and Best Paper at the NeurIPS workshops on ML for Healthcare and Cooperative AI. She has interned at DeepMind, Google Brain, and was an OpenAI Scholars mentor. Her work has been featured in Science Magazine, Quartz, IEEE Spectrum, MIT Technology Review, Boston Magazine, and on CBC radio. Natasha earned her Masters degree from the University of British Columbia, and undergraduate degrees in Computer Science and Psychology from the University of Regina.

1 0

Dora Zhao will present her MSE Talk “Understanding Teenage Perceptions and Configurations of Privacy on Instagram.” on Wednesday, April 6 at 4pm via Zoom.
by Nicki Mahler 30 Mar '22

30 Mar '22

Dora Zhao will present her MSE Talk “Understanding Teenage Perceptions and Configurations of Privacy on Instagram.” on Wednesday, April 6 at 4pm via Zoom. Zoom link: [ https://princeton.zoom.us/j/4036501701 | https://princeton.zoom.us/j/4036501701 ] The members of her committee is as follows: Andrés Monroy-Hernández (adviser), Janet Vertesi As teenage use of social media platform continues to proliferate, so do concerns about teenage privacy and safety online. Prior work has established that privacy on networked publics, such as social media, is complex, requiring users to navigate not only the technical affordances on the platform but also interpersonal relationships and social norms. We investigate how teenagers think about privacy on the popular image-sharing platform, Instagram. We draw on interviews with 12 teenagers (ages 13-18) and an online survey to gain a better understanding how the teenagers configure privacy on the popular image-sharing platform Instagram and why they make these privacy decisions. Finally, based on our findings, we provide design and policy recommendations towards the design of better privacy controls for promoting teenage safety online.

1 0

Robotics Seminar: Michelle Yuen TODAY at 10:45am
by Emily C. Lawrence 30 Mar '22

30 Mar '22

ROBOTICS SEMINAR Speaker: Michelle Yuen Title: Soft robots enabled by functional materials Day: Wednesday, March 30, 2022 Time: 10:45-11:45am Location: Friend Center Convocation Room (FC113) Host: Naveen Verma Abstract: Soft robots have the potential to extend the capabilities currently demonstrated within the field of robotics. By utilizing primarily soft materials in their construction, soft robots are inherently safe to operate around humans, can handle delicate tasks without advanced controls, and are robust to shocks and impacts during deployment. While proof-of-concept devices have been demonstrated successfully, there remains a need for widely applicable, reliable soft robotic components. In this talk, I will present my work on enabling technologies for soft robotic systems and, more broadly, deformable electromechanical systems. Specifically, I will discuss 1) high-deformation strain sensors for state reconstruction and closed-loop control of soft robots, 2) responsive structures enabled by variable-stiffness materials that can switch reversibly from flexible to stiff, and 3) stretchable electronics fabricated using room-temperature liquid metals. These devices rely upon functional materials – materials that have a useful, intrinsic property (e.g., conductivity, thermal-responsiveness) – that can be leveraged for robotic needs. Throughout this talk, I will be highlighting the need for co-developed design, materials selection, and manufacturing processes to produce reliable devices that can be fabricated at scale. The work presented in this talk illustrates a path toward building deformable electromechanical systems that are adaptable and versatile by leveraging functional multi-material systems. Bio: Michelle C. Yuen is a postdoctoral fellow at Harvard University in the School of Engineering and Applied Sciences at the Harvard Microrobotics Lab. She received her Ph.D. in Mechanical Engineering from Purdue University in 2018, following a B.S. in Biological Systems Engineering from University of California, Davis in 2013. During her Ph.D. studies, she worked on the design, materials, and manufacturing methods for soft robotic components and systems, and was awarded an NSF Graduate Research Fellowship. She was then awarded a Research Associateship from the National Academies of Science, Engineering, and Medicine to work on next-generation stretchable electronic devices at the Air Force Research Laboratory. Currently, her work leverages her expertise in soft materials manipulation to discovering advanced adhesion strategies for wet, rough surfaces toward applications in marine mammal tagging.

1 0

CS Colloquium speaker Sai Swaminathan: TODAY at 12:30pm
by Emily C. Lawrence 29 Mar '22

29 Mar '22

Speaker: Sai Swaminathan, Carnegie Mellon University Date: Tuesday, March 29, 2022 Time: 12:30pm EST Location: CS 105 Hosts: Andrés Monroy-Hernández & Adam Finkelstein Event page: https://www.cs.princeton.edu/events/26184 This talk will be live-streamed for the Princeton University community at https://mediacentrallive.princeton.edu/ *Note, this live-stream is only available to Princeton netID holders. Title: Computational Infrastructure Materials for the Networked & Interactive Built Environment Abstract: From roads to roofs, homes to high-rises, my inspiration is the promise of building cyber-physical infrastructure for human interaction and enabling smart city applications. Unfortunately, there are several challenges in achieving this vision due to the end of Moore's law, Dennard scaling, and our limited views on how computing systems are manufactured. To date, device manufacturing has focused primarily on miniaturization—packing the most functionality into the smallest form factor—despite our physical infrastructure being much larger in scale. We need to think creatively, design devices in new form factors (made in structural forms like walls, tables, facades, etc.) and materials of various kinds (those with extreme mechanical strength) that make up our built environments. There remain several challenges at the nexus of device power, form factor, and scale for designing our cyber-physical infrastructure. This talk will introduce "computational infrastructure materials" that enable us to build energy-efficient sensing, actuation, and communication in the networked physical infrastructure (e.g., buildings, sidewalks) forms. Specifically, I will talk about how to enable our infrastructure materials (e.g., concrete, wood, composites) to do computation: (1) as they bear large amounts of forces (~4000 lbs) (2) enable battery-free sensing and activity recognition in long distances (~70km), (3) actuate large-structures in response to user interaction and (4) enable battery-free wireless communication. Taken together, these capabilities in infrastructure materials enable a range of applications in the built environment, such as digital buildings, accessibility, and ultimately towards creating sustainable and resilient cyber-physical infrastructure for human interaction. I will conclude by discussing open problems and challenges for this emerging research area. Bio: Sai Swaminathan is a Ph.D. Candidate at the Human-Computer Interaction Institute in the School of Computer Science of Carnegie Mellon University. He is advised by Scott Hudson in the DevLab. He works at the intersection of Human-Computer Interaction, Ubiquitous Computing, and Computational Materials. He has published award-winning work at top-tier HCI venues, including ACM CHI, IMWUT (UbiComp), UIST, and CSCW. His work has also been featured in news outlets such as the New Scientist, Makezine, and HacksterIO. He has worked at numerous research institutions such as the Manufacturing Science group at Oakridge National Lab (ORNL), Microsoft Research, INRIA, and Xerox Research. You can find out more about him at www.saiganesh.net

1 0

Charlie Murphy will present his Pre FPO "Relational Verification via Weak Simulation" on Thursday April 7th, 2022 at 2pm in CS 402 and Zoom.
by Nicki Mahler 28 Mar '22

28 Mar '22

Charlie Murphy will present his Pre FPO "Relational Verification via Weak Simulation" on Thursday April 7th, 2022 at 2pm in CS 402 and Zoom. Zoom link: https://princeton.zoom.us/j/93257853666 His committee is as follows: Aarti Gupta (Reader) Dave Walker (Examiner) Lennart Beringer (Reader) Wyatt Lloyd (Examiner) Zak Kincaid (Advisor) All are welcome to attend. Title: Relational Verification via Weak Simulation Abstract: Distributed systems are notoriously hard to get right, even when based on existing protocols. The system implementor needs to worry about faulty nodes, asynchronous and delayed or dropped messages, and global correctness properties. Given this complexity, distributed systems are an attractive target for formal verification; however, direct verification of distributed systems is extremely expensive. As such, there is very little work on formally reasoning about distributed systems. Instead, there has been more work on formally verifying distributed protocols, but there is still a gap between the distributed system and a distributed protocol it is based on. In this talk, I propose formally verifying that a distributed system correctly implements a distributed protocol. By formally connecting a distributed system to a protocol, the system inherits the correctness properties of the protocol. This strategy is not new: it’s the method of executable specifications. Executable specifications have long been considered in formally verifying distributed systems; however, existing techniques are unable to handle systems and protocols with infinite state. I propose Contextual Simulation, a relational Hoare logic based on weak simulation for specifying a system implements a protocol. I provide a sound but incomplete set of inference rules for reasoning about contextual simulations. I conclude by presenting simulation synthesis, a semi-algorithm to automatically prove or refute contextual simulations. Simulation synthesis is based on the game semantics of weak simulation (an infinite state infinite duration game). The simulation game is solved by iteratively solving longer finite duration games. When the algorithm terminates, it does so with a winning strategy that (depending on the winning player) either proves or refutes the input contextual simulation.

1 0

Robotics Seminar: Patrick Slade, TODAY at 10:45am
by Emily C. Lawrence 28 Mar '22

28 Mar '22

ROBOTICS SEMINAR Speaker: Patrick Slade Title: Improving Health with Human-Centered Robotics Day: Monday, March 28, 2022 Time: 10:45-11:45am Location: Room E219 EQuad Host: Anirudha Majumdar Abstract: Globally, billions of people face mobility challenges like obesity, age-related diseases, and physical limitations which negatively impact health. Wearable devices that merge robotics, biomechanics, and human-centered AI can enable people to overcome these challenges. We will discuss key ideas for building intelligent assistive devices with several case studies. 1) A simple wearable system worn on one leg that accurately calculates calories expended during exercise, with three-fold lower error than a smartwatch. 2) A portable exoskeleton that personalizes assistance during real-world walking, which reduces walking effort (equivalent to removing an 18-pound backpack) and increases walking speed (by 9%) compared to normal shoes. 3) A robotic cane that improves navigation and increases walking speed by 20% for people with impaired vision. These projects focus on developing technology that is low-cost and easily reproducible to work towards tools for underserved populations. We will also explore how wearable monitoring and assistive devices will impact personal health in the future. Bio: Patrick Slade received his Ph.D. in Mechanical Engineering from Stanford in 2021 and is now a Distinguished Postdoctoral Scholar in Bioengineering as part of the Stanford Human Performance Alliance. His research combines robotics, biomechanics, and human-centered AI to build intelligent health models and assistive devices. He explores how we can safely and effectively integrate human-robot systems so people can live healthier and more independent lives. His work focuses on solutions that are open-source and low-cost to make care accessible for underserved populations. Patrick was an NSF Graduate Research Fellow, named a Forbes 30 under 30 in healthcare, and has published in journals like Science Robotics and Nature Communications.

1 0

CS Colloquium speaker Rowan Zellers: TODAY at 12:30pm
by Emily C. Lawrence 28 Mar '22

28 Mar '22

Speaker: Rowan Zellers, University of Washington Date: Monday, March 28, 2022 Time: 12:30pm EST Location: CS 105 Host: Danqi Chen Event page: https://www.cs.princeton.edu/events/26178 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Grounding Language by Seeing, Hearing, and Interacting Abstract: As humans, our understanding of language is grounded in a rich mental model about “how the world works” – that we learn through perception and interaction. We use this understanding to reason beyond what we literally observe or read, imagining how situations might unfold in the world. Machines today struggle at this kind of reasoning, which limits how they can communicate with humans. In my talk, I will discuss three lines of work to bridge this gap between machines and humans. I will first discuss how we might measure grounded understanding. I will introduce a suite of approaches for constructing benchmarks, using machines in the loop to filter out spurious biases. Next, I will introduce PIGLeT: a model that learns physical commonsense understanding by interacting with the world through simulation, using this knowledge to ground language. From an English-language description of an event, PIGLeT can anticipate how the world state might change – outperforming text-only models that are orders of magnitude larger. Finally, I will introduce MERLOT, which learns about situations in the world by watching millions of YouTube videos with transcribed speech. Through training objectives inspired by the developmental psychology idea of multimodal reentry, MERLOT learns to jointly reason over language, vision, and sound. Together, these directions suggest a path forward for building machines that learn language rooted in the world. Bio: Rowan Zellers is a final year PhD candidate at the University of Washington in Computer Science & Engineering, advised by Yejin Choi and Ali Farhadi. His research focuses on enabling machines to understand language, vision, sound, and the world beyond these modalities. He has been recognized through an NSF Graduate Fellowship and a NeurIPS 2021 outstanding paper award. His work has appeared in several media outlets, including Wired, the Washington Post, and the New York Times. In the past, he graduated from Harvey Mudd College with a B.S. in Computer Science & Mathematics, and has interned at the Allen Institute for AI.

1 0

CS Colloquium Series: week of March 21-25
by Emily C. Lawrence 25 Mar '22

25 Mar '22

Here is the full list of CS Colloquium talks for next week. All talks will be recorded. ~~~~~ Speaker: Xinyun Chen, University of California, Berkeley Date: Monday, March 21, 2022 Time: 12:30pm EST Location: CS 105 Host: Jia Deng Event page: [ https://www.cs.princeton.edu/events/26175 | https://www.cs.princeton.edu/events/26175 ] This talk will be live-streamed at [ https://mediacentrallive.princeton.edu/ | https://mediacentrallive.princeton.edu/ ] Title: Learning-Based Program Synthesis: Learning for Program Synthesis and Program Synthesis for Learning Abstract: With the advancement of modern technologies, programming becomes ubiquitous not only among professional software developers, but also for general computer users. However, gaining programming expertise is time-consuming and challenging. Therefore, program synthesis has many applications, where the computer automatically synthesizes programs from specifications such as natural language descriptions and input-output examples. In this talk, I will present my work on learning-based program synthesis, where I have developed deep learning techniques for various program synthesis problems. Despite the remarkable success of deep neural networks for many domains, including natural language processing and computer vision, existing deep neural networks are still insufficient for handling challenging symbolic reasoning and generalization problems. My learning-based program synthesis research lies in two folds: (1) learning to synthesize programs from potentially ambiguous and complex specifications; and (2) neural-symbolic learning for language understanding. I will first talk about program synthesis applications, where my work demonstrates the applicability of learning-based program synthesizers for production usage. I will then present my work on neural-symbolic frameworks that integrate symbolic components into neural networks, which achieve better reasoning and generalization capabilities. In closing, I will discuss the challenges and opportunities of further improving the complexity and generalizability of learning-based program synthesis for future work. Bio: Xinyun Chen is a Ph.D. candidate at UC Berkeley, working with Prof. Dawn Song. Her research lies at the intersection of deep learning, programming languages, and security. Her recent research focuses on learning-based program synthesis and adversarial machine learning. She received the Facebook Fellowship in 2020, and Rising Stars in Machine Learning in 2021. Her work SpreadsheetCoder for spreadsheet formula prediction was integrated into Google Sheets, and she was part of the AlphaCode team when she interned at DeepMind. ~~~~~ Speaker: Sherry Tongshuang Wu, University of Washington Date: Tuesday, March 22, 2022 Time: 12:30pm EST Location: CS 105 Hosts: Andrés Monroy-Hernández & Adam Finkelstein Event page: [ https://www.cs.princeton.edu/events/26176 | https://www.cs.princeton.edu/events/26176 ] This talk will be live-streamed at [ https://mediacentrallive.princeton.edu/ | https://mediacentrallive.princeton.edu/ ] Title: Interactive AI Model Debugging and Correction Abstract: Research in Artificial Intelligence (AI) has advanced at an incredible pace, to the point where it is making its way into our everyday lives, explicitly and behind the scenes. However, beneath their impressive progress, many AI models hide deficiencies that amplify social biases or even cause fatal accidents. How do we identify, improve, and cope with imperfect models, while still benefiting from their use? I will discuss my work empowering humans to interact with AI models in order to debug and correct them. I will describe both (1) how I help experts run scalable and testable analyses on models in development, and (2) how I help end users collaborate with deployed AI in a transparent and controllable way. In my final remarks, I will discuss my future research perspectives on building human-centered AI through data-centric approaches. Bio: Sherry Tongshuang Wu is a final year Ph.D. Candidate in Computer Science & Engineering at the University of Washington, advised by Jeffrey Heer and Dan Weld. She received her B.Eng in CSE from the Hong Kong University of Science and Technology. Her research lies at the intersection of Human-Computer Interaction (HCI) and Natural Language Processing (NLP), and aims to empower humans to debug and correct AI models interactively, both when the model is under active development, and after it is deployed for end users. Sherry has authored 19 papers in top-tier NLP, HCI and Visualization conferences and journals such as ACL, CHI, TOCHI, TVCG, etc, including a best paper award (top-1) and an honorable mention (top-3). You can find out more about her at https://homes.cs.washington.edu/~wtshuang/.

1 1