- talks - lists.cs.princeton.edu

Chenghan Zhou will present her MSE talk "Profitable Manipulations of Cryptographic Self-Sortition are Statistically Detectable" on April 25, 2024 in CS 402.
by Gradinfo 16 Apr '24

16 Apr '24

Chenghan Zhou will present her MSE talk "Profitable Manipulations of Cryptographic Self-Sortition are Statistically Detectable" on April 25, 2024 in CS 402. Thesis advisor: Matt Weinberg Thesis reader: Mark Braverman Public seminar time: Apr 25, 2024, 12:30 - 1pm Location: CS402 Thesis Title: Profitable Manipulations of Cryptographic Self-Sortition are Statistically Detectable Abstract: Cryptographic Self-Selection is a common primitive underlying leader-selection for Proof-of-Stake blockchain protocols. The concept was first popularized in Algorand [CM19], who also observed that the protocol might be manipulable. [FHWY22] provide a concrete manipulation that is strictly profitable for a staker of any size (and also prove upper bounds on the gains from manipulation). Separately, [BW23] initiate the study of undetectable profitable manipulations of consensus protocols with a focus on the seminal Selfish Mining strategy [ES14] for Bitcoin’s Proof-of-Work longest-chain protocol. They design a Selfish Mining variant that, for sufficiently large miners, is strictly profitable yet also indistinguishable to an onlooker from routine latency (that is, a sufficiently large profit-maximizing miner could use their strategy to strictly profit over being honest in a way that still appears to the rest of the network as though everyone is honest but experiencing mildly higher latency. This avoids any risk of negatively impacting the value of the underlying cryptocurrency due to attack detection). We investigate the detectability of profitable manipulations of the canonical cryptographic self-selection leader selection protocol introduced in [CM19] and studied in [FHWY22], and establish that every strictly profitable manipulation is statistically detectable. Specifically, we consider an onlooker who sees only the random seed of each round (and does not need to see any other broadcasts by any other players). We show that the distribution of the sequence of random seeds when any player is profitably manipulating the protocol is inconsistent with any distribution that could arise by honest stakers being offline or timing out (for a natural stylized model of honest timeouts).

1 0

Shruthi Santhanam will present her MSE talk "Interpretable 3D Scene Perception, Tracking and Generation" Friday, April 19 at 12:30 PM in Friend 202.
by gradinfo＠cs.princeton.edu 16 Apr '24

16 Apr '24

Shruthi Santhanam will present her MSE talk "Interpretable 3D Scene Perception, Tracking and Generation" Friday, April 19 at 12:30 PM in Friend 202. Advisor: Felix Heide; Reader: Vikram Ramaswamy Abstract: 3D scene understanding is a many-pronged problem that is fundamental to countless real-world applications. These are often deployed in safety-critical situations, meaning that both accuracy and interpretability are crucial. Current methods use non-learned algorithmic approaches, which may be more explainable but often have lower accuracies, or neural networks, which are generally not interpretable. In this thesis, we present two works that tackle different aspects of interpretable 3D scene understanding-perception, generation, and tracking. First, we combine scene perception and generation by reframing 3D object detection as a conditional generative process. Generative methods have shown to be effective learners of empirical priors, and we exploit this property by using a probabilistic diffusion model, conditioned on an input observation, to model each detected object explicitly on a ground plane. Then, we use a diffusion-based neural rendering method to reconstruct the scene, allowing for simultaneous 3D object detection and multi-object scene generation. This closed-loop pipeline gives us interpretability "for free" via the generated ground plane information. Second, we present a new intrinsically interpretable online 3D multi-object tracking method, based on graph attention networks (GAT). Using the tracking-by-detection framework, we use a GAT to perform data association on a track-detection bipartite graph between sequential frames. Furthermore, attention-based scores are used to visualize the GAT's message passing behavior on a model level, as well as explain specific outputs. Along with excellent accuracy across datasets, this method provides much-needed online interpretability to deep learning-based tracking, setting the stage for safe and scalable applications. CS Grad Calendar: https://calendar.google.com/calendar/event?action=TEMPLATE <https://calendar.google.com/calendar/event?action=TEMPLATE&tmeid=MXZyaDA4dW 5rZXFuNDB2NDBpY3NuYjQ3b2sgYWNnMDc5YmxzbzRtczNza2tmZThwa2lyb2dAZw&tmsrc=acg07 9blso4ms3skkfe8pkirog%40group.calendar.google.com> &tmeid=MXZyaDA4dW5rZXFuNDB2NDBpY3NuYjQ3b2sgYWNnMDc5YmxzbzRtczNza2tmZThwa2lyb 2dAZw&tmsrc=acg079blso4ms3skkfe8pkirog%40group.calendar.google.com

1 0

ECE Seminar: Yanjing Li, Monday April 22 at 4:30pm
by Emily C. Lawrence 16 Apr '24

16 Apr '24

Speaker: Yanjing Li, University of Chicago Date: Monday, April 22 Time: 4:30pm Location: B205, EQuad Host: Prof. David Wentzlaff Event link: [ https://ece.princeton.edu/events/how-does-one-bit-flip-corrupt-entire-deep-… | https://ece.princeton.edu/events/how-does-one-bit-flip-corrupt-entire-deep-… ] Title: How does one bit-flip corrupt an entire deep neural network, and what to do about it Abstract: Deep neural networks are increasingly susceptible to hardware failures. The impact of hardware failures on these workloads is severe – even a single bit-flip can corrupt an entire network during both training and inference. The urgency of tackling this challenge, known as the Silent Data Corruption challenge in a broader context, has been widely raised by both the industry and academia. In this talk, I will first present the first in-depth resilience study targeting DNN workloads and hardware failures that occur in the logic portion of deep learning accelerator systems, including a comprehensive characterization of hardware failure effects, along with the fundamental understanding of how hardware failures propagate in hardware devices and interact with the workloads. Next, based on the insights obtained from our study, I will present ultra lightweight yet highly effective techniques to mitigate hardware failures in deep learning accelerator systems. Bio: Yanjing Li is an Assistant Professor in the Department of Computer Science at the University of Chicago. Prior to joining the university, she was a senior research scientist at Intel Labs. Professor Li received her Ph.D. in Electrical Engineering from Stanford University, an M.S. in Mathematical Sciences (with honors) and a B.S. in Electrical and Computer Engineering (with a double major in Computer Science) from Carnegie Mellon University. Professor Li has received various awards, including the NSF CAREER Award, DAC under-40 innovators award, Google research scholar award, Intel Labs Gordy academy award (highest honor in Intel Labs) and several other Intel recognition awards, outstanding dissertation award (European Design and Automation Association), and multiple best paper awards (for example, IEEE VLSI Test Symposium and IEEE International Test Conference). Professor Li’s seminal work on in-field self-test and diagnostics has been adopted by various companies including Intel, Nvdia, Synopsys, TI, and MentorGraphics, and more.

1 0

Princeton Robotics Seminar: Jeannette Bohg (Stanford), Friday @ 11 AM
by Emily C. Lawrence 16 Apr '24

16 Apr '24

Join us this Friday (4/19) for the Robotics Seminar! Speaker: [ https://web.stanford.edu/~bohg/ | Jeannette Bohg ] , Stanford Date: Friday, April 19, 2024 Time: 11am ET Location: Computer Science 105 Event page: [ https://robo.princeton.edu/seminar | https://robo.princeton.edu/seminar ] PhD students and postdocs can [ https://docs.google.com/forms/d/e/1FAIpQLSczj2FTIvPhV_6f0jQpM5XZTJ_c-dp0DfH… | signup to join Jeannette for lunch ] . There will also be a Robotics Social at 4:00 PM in the F-Wing Cafe Area - all are welcome to attend! Title: Enabling Cross-Embodiment Learning Abstract: In this talk, I will investigate the problem of learning manipulation skills across a diverse set of robotic embodiments. Conventionally, manipulation skills are learned separately for every task, environment and robot. However, in domains like Computer Vision and Natural Language Processing we have seen that one of the main contributing factors to generalisable models is large amounts of diverse data. If we were able to have one robot learn a new task even from data recorded with a different robot, then we could already scale up training data to a much larger degree for each robot embodiment. In this talk, I will present a new, large-scale datasets that was put together across multiple industry and academic research labs to make it possible to explore the possibility of cross-embodiment learning in the context of robotic manipulation, alongside experimental results that provide an example of effective cross-robot policies. Given this dataset, I will also present multiple alternative ways to learn cross-embodiment policies. These example approaches will include (1) UniGrasp - a model that allows to synthesise grasps with new hands, (2) XIRL - an approach to automatically discover and learn vision-based reward functions from cross-embodiment demonstration videos and (3) Equivact - an approach that leverages equivariance to learn sensorimotor policies that generalise to scenarios that are traditionally out-of-distribution. Bio: Jeannette Bohg is an Assistant Professor of Computer Science at Stanford University. She was a group leader at the Autonomous Motion Department (AMD) of the MPI for Intelligent Systems until September 2017. Before joining AMD in January 2012, Jeannette Bohg was a PhD student at the Division of Robotics, Perception and Learning (RPL) at KTH in Stockholm. In her thesis, she proposed novel methods towards multi-modal scene understanding for robotic grasping. She also studied at Chalmers in Gothenburg and at the Technical University in Dresden where she received her Master in Art and Technology and her Diploma in Computer Science, respectively. Her research focuses on perception and learning for autonomous robotic manipulation and grasping. She is specifically interested in developing methods that are goal-directed, real-time and multi-modal such that they can provide meaningful feedback for execution and learning. Jeannette Bohg has received several Early Career and Best Paper awards, most notably the 2019 IEEE Robotics and Automation Society Early Career Award and the 2020 Robotics: Science and Systems Early Career Award.

1 0

CSML Seminar: Machine Learning for Structural Biology - TOMORROW at 12:30pm
by Emily C. Lawrence 15 Apr '24

15 Apr '24

Speaker: Ellen Zhong, Assistant Professor, Princeton University, Computer Science Title: Machine Learning for Structural Biology Day: April 16, 2024 Place: CSML, Bendheim House, 26 Prospect Ave, Classroom Room 103 Time: 12:30-1:30 PM Lunch available from 12:00 Host: Tom Griffiths, Director CSML Abstract: Structural biology has been transformed by breakthroughs in deep learning methods for protein structure prediction. In parallel, advances in cryo-electron microscopy (cryo-EM) have produced new opportunities to study the structure and dynamics of proteins and other biomolecular complexes through imaging. In this seminar, I will overview cryoDRGN and related methods that leverage the representation power of deep neural networks for 3D reconstruction of protein structures from cryo-EM images. Extended to real datasets and released as open-source tools, these methods have been used to discover new protein structures and visualize continuous trajectories of protein motion. I will discuss extensions of the method for scalable and robust reconstruction, analysis of the learned generative model, and visualization of dynamic macromolecular machines in situ. Finally, I will discuss how recent advances in machine learning for protein structure prediction (e.g. AlphaFold) can complement methods for cryo-EM structure determination and what key algorithmic challenges remain to realize the next era of structural biology. Bio: Ellen Zhong is an Assistant Professor of Computer Science at Princeton University. She is interested in problems at the intersection of AI and biology. Her research develops machine learning methods for computational and structural biology problems with a focus on protein structure determination with cryo-electron microscopy (cryo-EM). She obtained her Ph.D. from MIT in 2022, advised by Bonnie Berger and Joey Davis, where she developed deep learning algorithms for 3D reconstruction of dynamic protein structures from cryo-EM images. She has interned at DeepMind with John Jumper and the AlphaFold team and previously worked on molecular dynamics algorithms and infrastructure for drug discovery at D. E. Shaw Research. She obtained her B.S. from the University of Virginia where she worked with Michael Shirts on computational methods for studying protein folding. For more information about her research and group, please visit her group website: https://ezlab.princeton.edu/

1 0

Ted Sumers will present his FPO "Grounding Communication in Real-World Action" on Wednesday, April 24, 2024 at 11:00 AM in CS 301
by gradinfo＠cs.princeton.edu 11 Apr '24

11 Apr '24

Ted Sumers will present his FPO "Grounding Communication in Real-World Action" on Wednesday, April 24, 2024 at 11:00 AM in CS 301 Location: CS 301 The members of Ted's committee are as follows: Examiners: Tom Griffiths (Adviser), Ryan Adams, Adele Goldberg Readers: Karthik Narasimhan, Dylan Hadfield-Menell (MIT), Tom Griffiths (Adviser) A copy of his thesis is available upon request. Please email gradinfo(a)cs.princeton.edu <mailto:gradinfo@cs.princeton.edu> if you would like a copy of the thesis. Everyone is invited to attend his talk. Abstract follows below: This dissertation bridges psychology and artificial intelligence (AI) to develop agents capable of learning through communication with humans. The first half establishes a foundation by comparing the efficacy of language and demonstration for transmitting complex concepts. Experiments reveal language's superior ability to convey abstract rules, suggesting its importance for social learning. I then connect computational models of pragmatic language understanding to reinforcement learning settings, grounding a speaker's utility in their listener's decision problem. Behavioral evidence validates this as a model of human language use. Building on these insights, the second half develops AI agents capable of learning from such language. I first extend the computational model to incorporate both commands and teaching. Experiments show this allows an AI listener to robustly infer the human's latent reward function. I then introduce the problem of learning from fully natural language and contribute two novel approaches: utilizing aspect-based sentiment analysis and a inference network learned end-to-end. Behavioral evaluations demonstrate these models successfully learn from interactive human feedback. Together, this dissertation provides a formal computational theory of the cognitive mechanisms supporting human social learning and embeds them in artificial agents. I discuss implications both for large language models and the continued development of AI agents that acquire and use information through genuine dialogue. This work suggests that building machines to learn as humans do - socially and linguistically - is a promising path towards beneficial artificial intelligence.

1 0

Fangyin Wei will present her FPO "Learning to Edit 3D Objects and Scenes" on Monday, April 22, 2024 at 1:30 PM in CS 302
by gradinfo＠cs.princeton.edu 10 Apr '24

10 Apr '24

Fangyin Wei will present her FPO "Learning to Edit 3D Objects and Scenes" on Monday, April 22, 2024 at 1:30 PM in CS 302 Location: CS 302 The members of Fangyin's committee are as follows: Examiners: Szymon Rusinkiewicz (Adviser), Thomas Funkhouser (Adviser), Jia Deng Readers: Felix Heide, Olga Russakovsky A copy of her thesis is available upon request. Please email gradinfo(a)cs.princeton.edu <mailto:gradinfo@cs.princeton.edu> if you would like a copy of the thesis. Everyone is invited to attend her talk. Abstract follows below: 3D editing plays a key role in many fields ranging from AR/VR, industrial and art design, to robotics. However, existing 3D editing tools either (i) demand labor-intensive manual efforts and struggle to scale to many examples, or (ii) use optimization and machine learning but produce unsatisfactory results (e.g., losing details, supporting only coarse editing, etc.). These shortcomings often arise from editing in geometric space rather than structure-aware semantic space, where the latter is the key to automatic 3D editing at scale. While learning a structure-aware space will result in significantly improved efficiency and accuracy, labeled datasets to train 3D editing models don't exist. In this dissertation, we present novel approaches for learning to edit 3D objects and scenes in structure-aware semantic space with noisy or no supervision. We first address how to extract the underlying structure to edit 3D objects, with a focus on editing two critical properties: semantic shape parts and articulations. Our semantic editing method enables specific edits to an object's semantic parameters (e.g., the pose of a person's arm or the length of an airplane's wing), leading to better preservation of input details and improved accuracy compared to previous work. Next, we introduce a 3D annotation-free method that learns to model geometry, articulation, and appearance of articulated objects from color images. The model works on an entire category (as opposed to typical NeRF extensions that only overfit on a single scene) and enables various applications such as few-shot reconstruction and static object animation. It also generalizes to real-world captures. Then, we tackle how to extract structure for scene editing. We present an automatic system that removes clutter (frequently moving objects such as clothes or chairs) from 3D scenes and inpaints the resulting holes with coherent geometry and texture. We address challenges including the lack of well-defined clutter annotations, entangled semantics and geometry, and multi-view inconsistency. In summary, this dissertation demonstrates techniques to exploit the underlying structure of 3D data for editing. Our work opens up new research directions such as leveraging structures from other modalities (e.g., text, images) to empower 3D editing models with stronger semantic understanding.

1 0

Upcoming Princeton Precision Health talks: bioethics, neuroscience, computer vision, environmental effects on disease
by Emily C. Lawrence 10 Apr '24

10 Apr '24

The Princeton Precision Health team has three great seminars coming up in the next two weeks: On Friday, April 12, at 12 pm , we have two bioethicists, Aurelia Sauerbrei from Oxford and Ian Peebles from Princeton University Center for Human Values, presenting talks titled: "A.I. and the Doctor-Patient Relationship: a Bioethics Perspective” and “What’s Wrong With Decision Procedures in Medical Ethics?” Lunch will be provided. On Thursday, April 18, at 10:00 am , Uri Hasson from Psychology and PNI will give a talk, “The First 1000 Days Project: A Novel Framework for Modeling Language Development,” and Olga Russakovsky from Computer Science will present, “The Role of Computer Vision in Understanding Neurodivergence.” Breakfast will be provided. On Friday, April 19, at 12 pm , Jane Burns, MD, the Director of the Kawasaki Disease Clinic and Research Center at UCSD will give a talk about the climate and environmental effects on Kawasaki Disease. Her work has recently been featured in the [ https://www.nytimes.com/2024/02/27/health/kawasaki-disease-cause.html | NY Times ] . Lunch will be provided. We hope to see you at our upcoming seminars! The PPH Team 252 Nassau Street is between Tiger Noodles and the Small World Coffee on Nassau Street. We do not yet have a functional elevator, and getting to our space requires that you climb a flight of stairs. If an accommodation is needed, please do not hesitate to let us know in advance of the event. ************************************ Princeton Precision Health [ http://pph.princeton.edu/ | pph.princeton.edu ] [ mailto:princetonpph@princeton.edu | princetonpph(a)princeton.edu ]

1 0

Kritkorn Karntikoon will present his FPO "Dynamics of Averaging Systems: Convergence and Cyclical Trends" on May 9th, 2024 at 10:30am in CS 402 (and Zoom)
by Gradinfo 10 Apr '24

10 Apr '24

Kritkorn Karntikoon will present his FPO "Handling Data Too Large To Handle: On Multi-pass Streaming and Interactive Coding" on May 9th, 2024 at 10:30am in CS 402 (and Zoom). Title: Dynamics of Averaging Systems: Convergence and Cyclical Trends Examiners: Bernard Chazelle (advisor), Mark Braverman, Matt Weinberg Readers: Robert Tarjan, Huacheng Yu Date and Time: May 9, 2024 at 10.30 AM ET Zoom link: https://princeton.zoom.us/j/98534246633 All are welcome to attend. Abstract: Averaging dynamics drives countless processes in biology, social science, physics, and engineering. Notable examples include opinion dynamics, bird flocking, and synchronization processes. These processes involve agents interacting across a dynamic network by averaging their state variables with those of their neighbors. The dynamics of averaging systems therefore depend on the structure of the underlying network sequences. Under mild conditions, such systems are known to converge to fixed-point attractors but are hard to analyze because of the time-varying nature of networks. The s-energy, a generating function over inter-agent distances, has emerged as a powerful tool to deal with this issue. In this thesis, we refine the analysis of the s-energy by highlighting the impact of network connectivity. This allows us to address an intriguing exponential gap in the convergence rate of averaging systems. We also apply this new s-energy bound to resolve open questions in several areas including bird flocking, where we establish sufficient conditions for the first polynomial bound in bird flocking convergence. Additionally, we investigate the emergence of cyclical trends in opinion dynamics. Modifying the model with a separation rule reveals that the systems either converge to a nonconsensual equilibrium or are attracted to periodic or quasi-periodic orbits. Our analysis includes exploring geometric properties such as dimensionality, periodicity, and conditions for various behaviors.

1 1

Ben Burgess will present his FPO " Reverse Engineering Real World Trusted Systems" on Tuesday, May 7th, 2024 at 2:15pm in CS 105.
by Gradinfo 09 Apr '24

09 Apr '24

Ben Burgess will present his FPO " Reverse Engineering Real World Trusted Systems" on Tuesday, May 7th, 2024 at 2:15pm in CS 105. The members of his committee are as follows: Examiners: Ed Felten (adviser), Arvind Narayanan, and Roya Ensafi (University of Michigan) Readers: Ed Felten, Prateek Mittal, Danny Huang (New York University) All are welcome to attend. Please see below for abstract. In recent years, the adoption of remote proctoring solutions for law schools and bar examshassurged. Yet, the integrity and fairness of these systems have come under scrutiny. Concurrently, post the September 11th attacks, the security of police radio systems, notably Motorola P25 and Harris OpenSky, has emerged as a significant concern. This thesis delves into the issues plaguing these real-world systems and forwards potential remedies. The initial segment of the thesis appraises the integrity and equitability of remote proctoring solutions. An extensive literature review on remote proctoring’s application in law schools and bar exams sets the stage, elucidating both the advantages and limitations of these platforms. The narrative then transitions to the inherent security challenges: threats to exam sanctity posed by students, and the overarching issues of unfairness and systemic discrimination at the institutional level. The subsequent section casts a spotlight on the security dimensions of police radio systems, with an emphasis on Motorola P25 and Harris OpenSky. A meticulous breakdown of these systems’ features, capabilities, and security vulnerabilities ensues. The discourse deepens by investigating real-world deployments of these platforms, capturing the authentic security tribulations encountered by police departments across the United States. Additionally, the repercussions of these security concerns on police efficacy and overall public safety are explored. Drawing from the insights garnered, this thesis recommends a suite of measures to enhance the security and fairness of remote proctoring platforms and fortify the security infrastructure of police radio systems. These encompass the incorporation of advanced encryption methodologies and other security protocols to shield sensitive information. Moreover, the formulation of ethnically diverse datasets and strategies to curtail bias and discrimination in remote proctoring systems are elaborated upon. In essence, this thesis offers a holistic examination of the security and fairness facets of remote proctoring tools and the robustness of police radio systems, culminating in actionable recommendations to ameliorate the identified challenges.

1 0