- talks - lists.cs.princeton.edu

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

Divya Raghunathan will present her FPO "Layered Abstractions for Network Verification and Performance Analysis" on February 24, 2025 at 3pm in CS 302 (CORRECTION)
by Gradinfo 10 Feb '25

10 Feb '25

CORRECTION: Divya Raghunathan will present her FPO "Layered Abstractions for Network Verification and Performance Analysis" on February 24, 2025 at 3pm in CS 302. 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.

1 0

Divya Raghunathan will present her FPO "Formal Methods for Networks: Verification, Compilation, and Performance Analysis" on February 24, 2025 at 3pm in CS 302.
by Nicki Mahler 10 Feb '25

10 Feb '25

Divya Raghunathan will present her FPO "Formal Methods for Networks: Verification, Compilation, and Performance Analysis" on February 24, 2025 at 3pm in CS 302. 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. (edited) 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.

1 0

Yikai Wu will present his General Exam "Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set" on Wednesday, February 12, 2025 at 1:30 PM in CS 401 and via zoom.
by CS Grad Department 07 Feb '25

07 Feb '25

Yikai Wu will present his General Exam "Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set" on Wednesday, February 12, 2025 at 1:30 PM in CS 401 and via zoom. Zoom Link: https://princeton.zoom.us/j/97198300462 Committee Members: Sanjeev Arora (advisor), Elad Hazan, Pravesh Kothari Abstract: AI methods, especially generative models and reinforcement learning, have recently been applied to combinatorial optimization (CO) problems, especially NP-hard ones. This paper compares such GPU-based methods with classical CPU-based methods on Maximum Independent Set (MIS). Experiments on standard graph families show that AI-based algorithms fail to outperform and, in many cases, to even match the solution quality of classical solvers. The GPU-based methods often perform similarly to the simplest classical heuristic, degree-based greedy. Even when allowing ML-based methods to improve their solutions with post-processing techniques like local search, their performance remains inferior to that of CPU-based solvers. We develop a new mode of analysis to reveal that step-by-step AI methods, e.g. LTFT (which is based on GFlowNets), end up reasoning similarly to classical degree-based greedy approaches. We also find that CPU-based algorithms, notably Kamis, have strong performance on sparse random graphs, which appears to surpass a conjectured upper bound for polynomial algorithms. Reading List: https://docs.google.com/document/d/10wj4bZsLdrMIU402he0aC6HkxVSE_v9ujmnVgzz… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

ECE SEMINAR: Alon Kipnis from Reichman University, Friday, February 7 at 2pm
by Emily C. Lawrence 07 Feb '25

07 Feb '25

ECE SEMINAR Speaker: [ https://www.runi.ac.il/en/faculty/akipnis/ | Alon Kipnis ] , School of Computer Science at Reichman University Title: [ https://ece.princeton.edu/events/information-theoretic-approach-detecting-e… | An Information-Theoretic Approach for Detecting Edits in AI-Generated Text ] Day: Friday, February 7 Time: 2:00 PM Location: Computer Science 105 *Refreshments will be available. Host: Andrea Goldsmith, Dean, School of Engineering and Applied Science Abstract: We propose a method to determine whether a given article was written entirely by a generative language model or perhaps contains edits by a different author, possibly a human. Our process involves multiple tests for the origin of individual sentences or other pieces of text and combining these tests using a method sensitive to alternatives in which non-null effects are few and scattered across the text in unknown locations. Interestingly, this method is also useful for identifying pieces of text suspected to contain edits. We demonstrate the effectiveness of the method in detecting edits through extensive evaluations using real data and provide an information-theoretic analysis of the factors affecting its success. In particular, we discuss optimality properties under a theoretical framework for text editing saying that sentences are generated mainly by the language model, except perhaps for a few sentences that might have originated via a different mechanism. Our analysis raises several interesting research questions at the intersection of information theory and data science. Bio: Alon Kipnis is a Senior Lecturer (Assistant Professor) at the School of Computer Science at Reichman University. He received a PhD in electrical engineering from Stanford University in 2017. Between 2017-2021 he was a postdoctoral research scholar and a lecturer at the Department of Statistics at Stanford, advised by David Donoho. Dr. Kipnis' research combines mathematical statistics, information theory, and data science with applications to the analysis of noisy and sparse data in high dimensions, time-series, and text. He is the recipient of numerous fellowships and awards, including the Koret foundation postdoctoral fellowship, Stanford's electrical engineering department fellowship, and a prize from the Wolf Foundation.

1 1

PPPL Seminar - Sunita Chandrasekaran, January 30, 2:45 PM
by Emily C. Lawrence 29 Jan '25

29 Jan '25

The Princeton Plasma Physics Laboratory's Computational Science Department is pleased to announce. [ https://sites.google.com/d/13WaEf9N_dRV6D56spW_7SebByoF71VQe/p/1u7bBH2T5Z_D… | The Artificial Scientist - Leveraging In-transit Machine Learning for Plasma Simulations ] Presented by: Sunita Chandrasekaran , Associate Professor , University of Delaware Thursday, January 30, 2025, 2:45 PM Richard Hawryluk Conference Room, B31 8, [ https://pppl.zoom.us/j/91058597465?pwd=bLV9xHE4WFbznMBZFh45MJl4jiZ1pg.1 | Zoom ] Host: Shantenu Jha Abstract: With the rapid advancements in the computer architecture space, the migration of legacy applications to new architectures remains a continuous challenge. To effectively navigate this ever-evolving hardware landscape, software and toolchains must evolve in tandem, staying ahead of the curve in terms of architectural innovation. While this synchronization between hardware and software is inherently complex, it is essential for fully harnessing the potential of advanced hardware platforms. In this context, a marriage between HPC and AI is gaining increasing prominence. By effectively orchestrating the workflow of HPC and AI, we can not only accelerate scientific progress but also achieve significant gains in computational efficiency. One promising strategy to further optimize large-scale workflows is to stream simulation data directly into machine learning (ML) frameworks. This approach bypasses traditional file system bottlenecks, allowing for the transformation of data in transit— asynchronously with both the simulation process and model training. This talk will explore these strategies in detail, demonstrating the synergy between hardware innovation and software adaptation. Using real-world scientific applications as case study, Plasma-in-Cell on GPU, i.e. PIConGPU will showcase how these techniques can be applied at scale to drive both scientific and computational advancements. Sponsorship of an event does not constitute institutional endorsement of external speakers or views presented.

1 0

Yun Cheng will present her General Exam "Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?" on Wednesday, January 22, 2025 at 10:00 AM in CS 402 and via zoom.
by CS Grad Department 17 Jan '25

17 Jan '25

Yun Cheng will present her General Exam "Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?" on Wednesday, January 22, 2025 at 10:00 AM in CS 402 and via zoom. Zoom link: https://princeton.zoom.us/j/91346752488 Committee Members: Sanjeev Arora (advisor), Danqi Chen, Benjamin Eysenbach Abstract: While Vision Language Models (VLMs) are impressive in tasks such as visual question answering (VQA) and image captioning, their ability to apply multi-step reasoning to images has lagged, giving rise to perceptions of modality imbalance or brittleness. Towards systematic study of such issues, we introduce a synthetic framework for assessing the ability of VLMs to perform algorithmic visual reasoning (AVR), comprising three tasks: Table Readout, Grid Navigation, and Visual Analogy. Each has two levels of difficulty, SIMPLE and HARD, and even the SIMPLE versions are difficult for frontier VLMs. We seek strategies for training on the SIMPLE version of tasks that improve performance on the corresponding HARD task, i.e., S2H generalization. This synthetic framework, where each task also has a text-only version, allows a quantification of the modality imbalance and how it is impacted by training strategy. Ablations highlight the importance of explicit image-to-text conversion in promoting S2H generalization when using auto-regressive training. We also report results of mechanistic study of this phenomenon, including a measure of gradient alignment that seems to identify training strategies that promote better S2H generalization. Reading List: https://docs.google.com/document/d/1DbFfQZyCJb3HSYLvhy2SZ9voh_IN_6JZXcrFoiy… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

Amaya Kelegedara will present her General Exam "The Impact of Coreset Selection on Bias and Group Robustness" on Friday, January 17, 2025 at 3:00 PM in CS 105 and via zoom.
by CS Grad Department 14 Jan '25

14 Jan '25

Amaya Kelegedara will present her General Exam "The Impact of Coreset Selection on Bias and Group Robustness" on Friday, January 17, 2025 at 3:00 PM in CS 105 and via zoom. Zoom link: https://princeton.zoom.us/j/95739855237 Committee Members: Olga Russakovsky (advisor), Lydia Liu, Ryan Adams Abstract: Coreset selection methods have shown promise in reducing the training data size while maintaining model performance for data-efficient machine learning. However, many real-world datasets contain spurious features and unintended biases, and how coreset selection algorithms could impact the group robustness of their respective downstream models remains unexplored. I will talk about my research project where we conducted the first extensive analysis of the implications of coreset selection on the downstream group-robustness in the presence of spurious correlations. Our findings point to counterintuitive interactions between data bias and data quality, highlighting the importance of evaluating biases and robustness in coreset selection. Reading List: https://docs.google.com/document/d/1SMJIM-L98tOrmW0xY9P0hXqyymvaVyEB33Z71QA… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

Wei Tang will present his FPO "Enabling Large-scale Quantum Computing via Distributed and Hybrid Architectures" on Monday, January 27, 2025 at 10am in CS 302.
by Gradinfo 14 Jan '25

14 Jan '25

Wei Tang will present his FPO "Enabling Large-scale Quantum Computing via Distributed and Hybrid Architectures" on Monday, January 27, 2025 at 10am in CS 302. The members of his committee are as follows: Examiners: Margaret Martonosi (adviser), Jeff Thompson (Princeton ECE), Kai Li Readers: Fred Chong (Univ of Chicago), Amit Levy All are welcome to attend. Abstract follows below. Quantum Computing (QC) is an emerging paradigm that may o!er significant runtime advantages over classical computing by harnessing quantum physics principles to perform computations. Through years of software and hardware developments, QC has achieved notable progress. The theoretical computational advantages of QC over classical computing only manifest themselves as greater e”ciency when handling large and complex applications. Yet, QC encounters significant challenges in scaling and maintaining the precision necessary to fulfill its potential. In simpler or smaller problems, these theoretical advantages might not present a clear benefit over traditional methods. Such complex applications demand large Quantum Processing Units (QPUs). Moreover, in contrast to the exceptionally low error rates of classical computers, current QPUs are much more susceptible to errors. This vulnerability necessitates QPUs that not only support large-scale tasks but also mitigate error accumulation. The dual requirements of size and accuracy put a heavy toll on QC, hindering its adoption in practical scenarios. Conversely, classical computing is characterized by its high precision and reliability across various applications. Nonetheless, it encounters intrinsic limitations in computational complexity for solving complex, real-world challenges. In fact, the best-known classical algorithms for many important real-world problems remain intractable as the size of the problems increases. Despite decades of semiconductor technology advancements, the miniaturization of chip components to enhance their processing capacity is approaching its physical boundaries. This development poses a challenge to classical computing’s ability to keep pace with increasing computational demands, highlighting the need for innovative paradigms such as QC. This dissertation tackles the challenges of scaling up QC by distributing quantum algorithms across quantum and classical resources. The distributed hybrid approach carries two main benefits. First, it significantly reduces the quantum resource requirements compared to an exclusively quantum setup. Second, it achieves potentially faster runtimes than those attainable on purely classical platforms. This dissertation pioneers the field of Distributed Hybrid QC (DHQC) and develops the first end-to-end DHQC toolchain. By integrating with cutting-edge classical computing methods, this dissertation further enhances the scalability of DHQC systems. Additionally, this dissertation also contributes to the evolution of QC compiler design, optimizing QPU performance towards practical applications.

1 0

Tyler Zhu will present his General Exam "Unifying Specialized Visual Encoders for Video Language Models" on Tuesday, January 14, 2025 at 10:00 AM in CS 402 and via zoom.
by CS Grad Department 09 Jan '25

09 Jan '25

Tyler Zhu will present his General Exam " Unifying Specialized Visual Encoders for Video Language Models " on Tuesday, January 14, 2025 at 10:00 AM in CS 402 and via zoom. Zoom link: https://princeton.zoom.us/my/tylerzhu Committee Members: Olga Russakovsky (advisor), Jia Deng , Danqi Chen Abstract: The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all of their visual processing, which limits the amount and type of visual information that can be conveyed to the LLM. Our method, MERV, Multi-Encoder Representation of Videos, instead leverages multiple frozen visual encoders to create a unified representation of a video, providing the VideoLLM with a comprehensive set of specialized visual knowledge. Spatio-temporally aligning the features from each encoder allows us to tackle a wider range of open-ended and multiple-choice video understanding questions and outperform prior state-of-the-art works on their data mixes. MERV is up to 3.7% better in accuracy than Video-LLaVA across the standard suite video understanding benchmarks, while also having a better Video-ChatGPT score. We also improve upon SeViLA, the previous best on zero-shot Perception Test accuracy, by 2.2%. MERV introduces minimal extra parameters and trains faster than equivalent single-encoder approaches. Finally, we provide qualitative evidence that our model captures domain knowledge from each encoder simultaneously, such as on the motion classification tasks found in Something-Something v2. Our results offer promising directions for future research in utilizing multiple vision encoders for comprehensive video understanding. Reading List: https://docs.google.com/document/d/1jBXhv-IhFRsFsC6HblTb9ZE4nZkQIfGgm2-NAMO… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0