February 2025 - talks - lists.cs.princeton.edu

CS Colloquium speakers: week of February 26
by Emily C. Lawrence 06 Mar '25

06 Mar '25

CS Colloquium speakers Speaker: Jialin Ding, Amazon Web Services Date: Monday, February 26 Time: 12:30pm EST Location: CS 105 Host: Wyatt Lloyd Event page: https://www.cs.princeton.edu/events/26578 Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_10z_l8MYRr21ZOuPqA8Odw Title: Instance-Optimization: Rethinking Database Design for the Next 1000X Abstract: Modern database systems aim to support a large class of different use cases while simultaneously achieving high performance. However, as a result of their generality, databases often achieve adequate performance for the average use case but do not achieve the best performance for any individual use case. In this talk, I will describe my work on designing databases that use machine learning and optimization techniques to automatically achieve performance much closer to the optimal for each individual use case. In particular, I will present my work on instance-optimized database storage layouts, in which the co-design of data structures and optimization policies improves query performance in analytic databases by orders of magnitude. I will highlight how these instance-optimized data layouts address various challenges posed by real-world database workloads and how I implemented and deployed them in production within Amazon Redshift, a widely-used commercial database system. Bio: Jialin Ding is an Applied Scientist at AWS. Before that, he received his PhD in computer science from MIT, advised by Tim Kraska. He works broadly on applying machine learning and optimization techniques to improve data management systems, with a focus on building databases that automatically self-optimize to achieve high performance for any specific application. His work has appeared in top conferences such as SIGMOD, VLDB, and CIDR, and has been recognized by a Meta Research PhD Fellowship. To learn more about Jialin’s work, please visit [ https://jialinding.github.io/ | https://jialinding.github.io/ ] . CSML/CS/PSY Colloquium Speaker: Brenden Lake, New York University Date: Tuesday, February 27 Time: 12:30pm EST Location: CS 105 Host: Tom Griffiths Event page: https://csml.princeton.edu/events/csmlpsycs-seminar Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_aUfLfVQFSIqV2RDSYu4big Title: Towards more human-like learning in machines: Bridging the data and generalization gaps Abstract: There is an enormous data gap between how AI systems and children learn: The best LLMs now learn language from text with a word count in the trillions, whereas it would take a child roughly 100K years to reach those numbers through speech (Frank, 2023, "Bridging the data gap"). There is also a clear generalization gap: whereas machines struggle with systematic generalization, children can excel. For instance, once a child learns how to "skip," they immediately know how to "skip twice" or "skip around the room with their hands up" due to their compositional skills. In this talk, I'll describe two case studies in addressing these gaps. 1) The data gap: We train deep neural networks from scratch (using DINO, CLIP, etc.), not on large-scale data from the web, but through the eyes and ears of a single child. Using head-mounted video recordings from a child as training data (<200 hours of video slices over 26 months), we show how deep neural networks can perform challenging visual tasks, acquire many word-referent mappings, generalize to novel visual referents, and achieve multi-modal alignment. Our results demonstrate how today's AI models are capable of learning key aspects of children's early knowledge from realistic input. 2) The generalization gap: Can neural networks capture human-like systematic generalization? We address a 35-year-old debate catalyzed by Fodor and Pylyshyn's classic article, which argued that standard neural networks are not viable models of the mind because they lack systematic compositionality -- the algebraic ability to understand and produce novel combinations from known components. We'll show how neural networks can achieve human-like systematic generalization when trained through meta-learning for compositionality (MLC), a new method for optimizing the compositional skills of neural networks through practice. With MLC, neural networks can match human performance and solve several machine learning benchmarks. Given these findings, we'll discuss the paths forward for building machines that learn, generalize, and interact in more human-like ways based on more natural input. Related articles: Vong, W. K., Wang, W., Orhan, A. E., and Lake, B. M (2024). Grounded language acquisition through the eyes and ears of a single child. Science, 383, 504-511. Orhan, A. E., and Lake, B. M. (in press). Learning high-level visual representations from a child’s perspective without strong inductive biases. Nature Machine Intelligence. Lake, B. M. and Baroni, M. (2023). Human-like systematic generalization through a meta-learning neural network. Nature, 623, 115-121. Bio: Brenden M. Lake is an Assistant Professor of Data Science and Psychology at New York University. He received his M.S. and B.S. in Symbolic Systems from Stanford University in 2009, and his Ph.D. in Cognitive Science from MIT in 2014. He was a postdoctoral Data Science Fellow at NYU from 2014-2017. Brenden is a recipient of the Robert J. Glushko Prize for Outstanding Doctoral Dissertation in Cognitive Science and the MIT Technology Review 35 Innovators Under 35. His research was also selected by Scientific American as one of the 10 most important advances of 2016. Brenden's research focuses on computational problems that are easier for people than they are for machines, such as learning new concepts from just a few examples, learning by asking questions, learning by generating new goals, and learning by producing novel combinations of known components. CS Colloquium Speaker: Eric Mitchell, Stanford University Date: Thursday, February 29 Time: 12:30pm EST Location: CS 105 Host: Karthik Narasimhan Event page: https://www.cs.princeton.edu/events/26587 Register for live-stream online here: TBA Talk info TBA

1 8

CS Colloquium Speaker: Yuke Zhu - TODAY at 12:30pm
by Emily C. Lawrence 27 Feb '25

27 Feb '25

CS Colloquium Speaker Speaker: Yuke Zhu, University of Texas, Austin Date: Thursday, February 27 Time: 12:30pm EST Location: CS 105 Host: Jia Deng Event page: https://www.cs.princeton.edu/events/pathway-generalist-robot-autonomy-data-… Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_p4RA6oDFTiCVquo7_GGJdg Title: Pathway to Generalist Robot Autonomy — A Data-Centric Approach Abstract: In an era of rapid AI progress, leveraging accelerated computing and big data has unlocked new possibilities to develop general-purpose AI models. As AI systems like ChatGPT showcase remarkable performance in the digital realm, we are compelled to ask: Can we achieve similar breakthroughs in the physical world — to create generalist robots capable of performing everyday tasks? In this talk, I will present my data-centric research principles and methodologies for building general-purpose robot autonomy in open-world environments. I will discuss my recent work on building compositional robot autonomy stacks with diverse data sources. I will also present a human-in-the-loop framework for trustworthy robot deployment and continual learning. Combining these advances with cutting-edge developments in humanoid robotics, I will outline a roadmap toward the next generation of autonomous robots. Bio: Yuke Zhu is an Assistant Professor in the Computer Science Department of UT-Austin, where he directs the Robot Perception and Learning (RPL) Lab. He also co-leads the Generalist Embodied Agent Research (GEAR) lab at NVIDIA Research, which builds foundation models for embodied agents in virtual and physical worlds, particularly for humanoid robots. He focuses on developing intelligent algorithms for generalist robots and embodied agents to reason about and interact with the real world. His research spans robotics, computer vision, and machine learning. He received his Master's and Ph.D. degrees from Stanford University. His work has won various awards and nominations, including the Best Conference Paper Award in ICRA 2019, 2024, the Outstanding Learning Paper Award at ICRA 2022, and the Outstanding Paper Award at NeurIPS 2022. He received the NSF CAREER Award and faculty awards from Amazon, JP Morgan, and Sony Research.

1 0

Please join us TODAY for AI² Startup Founders Series Livestream Event Featuring Rocky Yu from AGI House. AGI House: “Founding Story and Mission”
by Emily C. Lawrence 26 Feb '25

26 Feb '25

Please join us TODAY for AI² Startup Founders Series Livestream event featuring Rocky Yu from [ https://agihouse.org/ | AGI House ] . AGI House: “Founding Story and Mission” Wednesday, February 26th, 2025, 4:30PM EST [ https://princeton.zoom.us/j/91744912750#success | Zoom Webinar Link ] [ https://www.youtube.com/@princetonai2 | YouTube channel ] [ https://invent.ai.princeton.edu/events | AI² Events ] [ https://invent.ai.princeton.edu/about/get-involved | AI² Mailing List ] AI for Accelerating Invention [ https://invent.ai.princeton.edu/about/get-involved | Get Involved ] We are rapidly developing AI for Accelerated Invention activities and programs. Sign up for the mailing list and reach out to us with your questions.

1 0

AI² Research Talk Series - TODAY - “Understanding Last Layer Retraining Methods for Fair Classification: Theory and Algorithms” with Lalitha Sankar
by Emily C. Lawrence 25 Feb '25

25 Feb '25

Please join us: AI² Research Talk Series Tuesday, February 25th, 2025 Lunch at 12:15 p.m., seminar starts at 12:30 p.m. Robertson Hall, 002 “Understanding Last Layer Retraining Methods for Fair Classification: Theory and Algorithms” Lilitha Sankar, professor in the School of Electrical, Computer and Energy Engineering at Arizona State University [ https://invent.ai.princeton.edu/events | AI² Events ] [ https://invent.ai.princeton.edu/about/get-involved | AI² Mailing List ] [ https://invent.ai.princeton.edu/about/get-involved | Get Involved ] We are rapidly developing AI for Accelerated Invention activities and programs. Sign up for the mailing list and reach out to us with your questions.

1 0

CS Colloquium Speaker: Zhen Dong - TODAY at 12:30pm
by Emily C. Lawrence 25 Feb '25

25 Feb '25

CS Colloquium Speaker Speaker: Zhen Dong, University of California, Berkeley Date: Tuesday, February 25 Time: 12:30pm EST Location: CS 105 Host: Kai Li Event page: https://www.cs.princeton.edu/events/make-ai-more-accessible-and-run-faster Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_yrwYu8XfT2-UxV-2RVKGvg Title: Make AI More Accessible and Run Faster Abstract: LLMs and diffusion models have achieved great success in recent years. However, many AI models, particularly those with state-of-the-art performance, have a high computational cost and memory footprint. This impedes the development of pervasive AI in scenarios lacking sufficient computational resources (e.g., IoT devices, lunar rovers), requiring ultra-fast inference (e.g., AI4Science), or demanding real-time interaction under constrained computation (e.g., AR/VR, Embodied AI). Model compression (quantization, pruning, distillation, etc) and hardware-software co-design are promising approaches to achieving Efficient AI, which makes AI more accessible and run faster. In this talk, I will first introduce my work on 1) mixed-precision quantization based on Hessian analysis (HAWQv1v2, ZeroQ, Q-BERT) and 2) hardware-software co-design (HAWQv3, CoDeNet, HAO). Then I will talk about my ongoing and future works in the era of LLMs and GenAI, including SqueezeLLM, Q-Diffusion, efficient AI agent systems, advanced CoT distillation, efficient deep thinking for OpenAI-o1 and Deepseek-R1, etc. My research vision is that efficient AI is becoming indispensable both at the edge where increasingly powerful sensors with diverse modalities generate huge volumes of local data, and in the cloud where reducing costs is essential to bridge the speed gap between inference scaling laws and Moore’s law for hardware. Bio: Dr. Zhen Dong is currently a Postdoc at UC Berkeley. He obtained his Ph.D. from Berkeley AI Research advised by Prof. Kurt Keutzer. Before Berkeley, Zhen received B.E. from Peking University. Zhen’s research focuses on efficient AI, model compression, hardware-software co-design, and AI systems. Zhen has received Berkeley University Fellowship and SenseTime Scholarship. Zhen has published over 10 papers as the first or co-first author at top AI conferences. He won the best paper award at AAAI Practical-DL workshop, and Zhen is also a winner of the DAC 2024 PhD forum and CVPR 2024 doctoral consortium.

1 0

Divya Raghunathan will present her FPO "Layered Abstractions for Network Verification and Performance Analysis" on February 24, 2025 at 3pm in CS 302 (and Zoom)
by Gradinfo 20 Feb '25

20 Feb '25

BQ_BEGIN Divya Raghunathan will present her FPO "Layered Abstractions for Network Verification and Performance Analysis" on February 24, 2025 at 3pm in CS 302 and Zoom. Zoom link: Here is the zoom link: [ https://princeton.zoom.us/j/97963140078 | https://princeton.zoom.us/j/97963140078 ] Her committee is as follows: Examiners: Aarti Gupta (Adviser), Zachary Kincaid, and Mae Milano Readers: David Walker and Maria Apostolaki Title: "Formal Methods for Networks: Verification, Compilation, and Performance Analysis" Abstract: The scale and complexity of computer networks make their correct operation and analysis challenging. Networks are difficult to configure correctly: router configuration bugs are common, and often cause severe outages or security breaches. Network management tasks (e.g., ensuring compliance with service-level agreements) are challenging, given the diversity of network traffic and limited monitoring information. Formal verification provides tools to improve network reliability, but large network sizes and the vast space of network environments make scalable verification challenging, especially for approaches using Satisfiability Modulo Theories (SMT). Abstractions can improve verification scalability by simplifying the system being verified. Abstractions that over-approximate system behavior enable sound verification that never misses property violations, but could report spurious violations (false positives). Designing effective abstractions that enable scalable verification but rarely report false positives is challenging. This thesis introduces novel abstractions and verification methods for network control plane verification and network performance analysis. Our abstract verification procedures are effective (low false positive rate) and significantly improve verification scalability over state-of-the-art. Our network control plane verifier, ACORN, checks routing-related properties like reachability given network router configurations. ACORN leverages our novel Nondeterministic Routing Choice (NRC) abstractions to simplify the network control plane. We prove that the NRC abstractions are sound for verification, i.e., never miss property violations. With our NRC abstractions, ACORN successfully verifies reachability for up to 28000 routers (in a FatTree topology) within an hour, while state-of-the-art tools do not scale beyond a few thousand routers. Our network performance analysis approach, QuASI, answers performance queries (e.g., burst occurrence) under given measurements. QuASI's first layer, QuASI-approx, uses three novelties: our enqueue-rate abstraction, our reduction over abstract packet traces, and an efficient matrix-based consistency check. We prove QuASI-approx will never incorrectly report a query is unsatisfiable. QuASI's second layer uses SMT constraints to model switch behavior under measurements, leveraging the enqueue-rate abstraction to speed up verification without loss of precision for supported queries. QuASI answers queries up to six orders of magnitude faster than an existing performance analysis tool. BQ_END

1 0

Join us TODAY for AI² Startup Founders Series Livestream event featuring Rocky Yu from AGI House
by Emily C. Lawrence 19 Feb '25

19 Feb '25

Please join us TODAY for AI² Startup Founders Series Livestream event featuring Rocky Yu from [ https://agihouse.org/ | AGI House ] . AGI House: “Founding Story and Mission” Wednesday, February 19th, 2025, 4:30PM EST [ https://www.youtube.com/@PrincetonAI2 | https://www.youtube.com/@PrincetonAI2 ] AGI House is a premier hub for AI innovation located in San Francisco, bringing together leading researchers, industry pioneers, and visionary founders to advance Artificial General Intelligence. Through its AGI Transformation event series, hackathons, exclusive gatherings, and guest speaker sessions featuring AI leaders such as Jeff Dean and Sam Altman, AGI House fosters a world-class community driving AI progress. AGI House operates a venture fund and fellowship program, investing in some of the most promising GenAI startups, including early rounds of Voyage AI and Pika. Rocky Yu is the founder and CEO of [ https://agihouse.org/ | AGI House(Link is external) ] , a factory designed to build AI startups. He founded several companies in Silicon Valley, including Piki Inc, a platform for AI/AR storytelling, and 35CFund. He launched most recently AGI House Ventures. Join the AI for Accelerating Invention mailing list to receive updates about upcoming events and opportunities: [ https://princeton.us13.list-manage.com/subscribe?u=844cda4548afd4e4c6dd5e1b… | link ] .

1 0

DeCenter Seminar - Elaine Shi TODAY at 3:30pm
by Emily C. Lawrence 19 Feb '25

19 Feb '25

TODAY, Wednesday, February 19th, at 3:30 PM , the DeCenter Seminar Series continues with Elaine Shi , a professor of Computer Science and Electrical & Computer Engineering at Carnegie Mellon University. She is interested in cryptography, game theory, algorithms, and the foundations of blockchains. She will present a seminar titled "Decentralized Mechanism Design: Cryptography Meets Game Theory." The event will take place in the Computer Science Building Room 105 . Abstract: In classical auction design, we take it for granted that the auctioneer is trusted and always implements the auction’s rules honestly. This assumption, however, no longer holds in modern auctions based on blockchains, or those mediated by third-party platforms such as Google. For example, in blockchain-based auctions, the consensus nodes that partly serve as the auctioneer are incentivized to deviate from honest behavior if profitable. Third-party auction platforms such as Google have also been involved in high-profile anti-trust lawsuits for manipulating their auctions. In this talk, I will describe our recent work on decentralized mechanism design, where we aim to build a new scientific foundation for emerging auctions that are not backed by a trusted auctioneer. I will characterize the mathematical landscape of decentralized mechanism design, by showing several infeasibility and feasibility results. I will also highlight how cryptography can play an essential role for bypassing impossibility results in decentralized mechanism design, leading to a new class of auctions that not only incentivize bidders to act honestly, but also incentivize the auctioneer to play by the book. Bio: Elaine Shi is a Professor at CMU. Prior to joining CMU, she was an assistant professor in UMD and an associate professor in Cornell. Her research interests include cryptography, security, algorithms, game theory, and foundations of blockchains. Elaine’s work has successfully transitioned cryptography and privacy algorithms from on-paper theory to large-scale real-world deployment. For example, her Oblivious RAM algorithm now serves as the backbone of Signal’s private contact discovery service and has also been implemented by Meta. Her differential privacy algorithm has been improved and implemented by companies such as Google and JP Morgan and is a core to Google’s Spanish Gboard. Elaine is a Packard Fellow, a Sloan Fellow, and an ACM Fellow. She has also received several awards such as an ONR YIP award, the NSF CAREER award, and various best paper awards such as the CCS Test of Time award, the NSA Best Scientific Cybersecurity paper, Top Picks in Hardware and Embedded Security, ASPLOS best paper, and others. We hope to see you there!

1 0

Indu Panigrahi will present "Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations" on Thurs. February 27, 2025 at 12:30pm in CS 402.
by Gradinfo 18 Feb '25

18 Feb '25

Indu Panigrahi will present "Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations" on Thurs. February 27, 2025 at 12:30pm in CS 402. Adviser: Parastoo Abtahi; Reader: Ruth Fong * Date : Thursday, February 27th, 2025 * Time : 12:30pm * Location : CS 402 * Title : Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations * Abstract : Explanations for computer vision models are important tools for interpreting how the underlying models work. However, they have traditionally been presented in static formats, which pose challenges for users, including information overload, a gap between semantic and pixel-level information, and limited opportunities for exploration. We investigate interactivity as a mechanism for tackling these issues in three common explanation types: heatmap-based, concept-based, and prototype-based explanations. We conducted a study (N=24), using a bird identification task, involving participants with diverse technical and domain expertise. We found that while interactivity enhances user control, facilitates how users interpret information, and allows users to expand their understanding of the model and explanation, it also introduces new challenges. To address these, we provide design recommendations for interactive computer vision explanations, including carefully selected default views, constrained output spaces, and optionality. * Additional note : Please try to email Indu at [ mailto:indup@princeton.edu | indup(a)princeton.edu ] beforehand if you plan on attending so that we can have a rough headcount.

1 0

Ilya Chugunov will present his FPO "Neural Field Representations of Mobile Computational Photography" on Friday, February 21, 2025 at 2:00 PM in CS 302.
by CS Grad Department 11 Feb '25

11 Feb '25

Ilya Chugunov will present his FPO " Neural Field Representations of Mobile Computational Photography " on Friday, February 21, 2025 at 2:00 PM in CS 302 . Location: CS 302 The members of Ilya ’s committee are as follows: Examiners: Felix Heide (Adviser), Szymon Rusinkiewicz , Jia Deng Readers: Adam Finkelstein , Ellen Zhong A copy of his thesis is available upon request. Please email gradinfo(a)cs.princeton.edu if you would like a copy of the thesis. Everyone is invited to attend his talk. Abstract follows below: Over the past two decades, mobile imaging has experienced a profound transformation, with cell phones rapidly eclipsing all other forms of digital photography in popularity. Today’s cell phones are equipped with a diverse range of imaging technologies– laser depth ranging, multi-focal camera arrays, and split-pixel sensors alongside non-visual sensors such as gyroscopes, accelerometers, and magnetometers. This, combined with on-board integrated chips for image and signal processing, makes the cell phone a versatile pocket-sized computational imaging platform. Parallel to this, we have seen in recent years how neural fields– small neural networks trained to map continuous spatial input coordinates to output signals– enable the reconstruction of complex scenes without explicit data representations such as pixel arrays or point clouds. In this thesis, I demonstrate how carefully designed neural field models can compactly represent complex geometry and lighting effects. Enabling applications such as depth estimation, layer separation, and image stitching directly from collected in-the-wild mobile photography data. These methods outperform state-of-the-art approaches without relying on complex pre-processing steps, labeled ground truth data, or machine learning priors. Instead, they leverage well constructed, self-regularized models that tackle challenging inverse problems through stochastic gradient descent, fitting directly to raw measurements from a smartphone.

1 0