- talks - lists.cs.princeton.edu

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

Program in Linguistics Lecture ~ "Prediction and Locality in Language and Language Models" ~ Richard Futrell, University of California, Irvine - December 19 at 4:30pm
by Emily C. Lawrence 17 Dec '24

17 Dec '24

You are invited to attend a Program in Linguistics Lecture on Thursday, December 19 th : Prediction and Locality in Language and Language Models Richard Futrell Department of Language Science University of California, Irvine Thursday, December 19, 2024 4 :30- 6 :00 p.m. 1-S-5 Green Hall I argue that language models share information-processing constraints with humans, arising from the shared core task of language models and the brain: predicting upcoming input. I show that we can use constraints on sequential prediction to explain aspects of human language processing, as reflected in eyetracking and reading time data, as well as various universal properties of languages, as reflected in patterns of word order in massively cross-linguistic text corpora. Furthermore, the same constraints explain language model performance when learning human-like versus non-human-like languages. I argue that this approach points to an information-theoretic explanation for the nature of human language, and links the science of language with neuroscience and machine learning. Richard Futrell is Associate Professor of Language Science at the University of California, Irvine. His research focuses on language in humans and machines.

1 0

Program in Linguistics Lecture ~ "Understanding ambiguity" ~ Gregory Scontras, University of California, Irvine - December 10 at 4:30pm
by Emily C. Lawrence 06 Dec '24

06 Dec '24

You are invited to attend a Program in Linguistics Lecture on Tuesday, December 10 th : Understanding ambiguity Gregory Scontras Department of Language Science University of California, Irvine Tuesday, December 10, 2024 4 :30- 6 :00 p.m. 1-S-5 Green Hall Ambiguity is everywhere, yet it rarely leads to catastrophes in communication. In this talk, I present a computational cognitive model of the social reasoning that we perform when resolving ambiguities. I motivate the model on the basis of a case study in which young children perform quite differently from adults when it comes to understanding utterances with multiple potential meanings. There, we see that pragmatic factors may play a larger role than grammatical processing factors in explaining children’s non-adult-like behavior, and the computational model offers a hypothesis as to why that’s so: pragmatic factors have a larger impact on the truth-value judgment task that researchers use to investigate young children’s language understanding. I then provide additional support for the proposed model of ambiguity resolution, first from adult behavioral experiments, then from the largest-of-its-kind annotated corpus of naturally-occurring ambiguities. Finally, I show how the proposed view of ambiguity resolution as recursive social reasoning offers additional insight into the benefits of having ambiguity in language: by observing how others resolve ambiguity, we learn about the private thoughts they use to do so. Gregory Scontras is a linguist and cognitive scientist specializing in semantics, pragmatics, and their intersection with human cognition. He received his B.A. in linguistics and in philosophy from Boston University, and his Ph.D. in linguistics from Harvard. Scontras was a post-doctoral scholar in the Computation & Cognition Lab at Stanford Psychology. In 2016, he joined the University of California, Irvine, to found the Department of Language Science, where he now directs [ https://www.langsci.uci.edu/scontras/meaning/ | the meaning lab ] . Scontras’s research uses a range of qualitative, experimental, and computational methods, applied to a diverse set of cross-linguistic data — all in service of understanding the mental representations of our speech and the computational system that manipulates them. Ongoing projects investigate the cross-linguistic semantics of measurement and degrees, the development and maintenance of complexity in unbalanced (heritage) bilingualism, the communicative pressures driving cross-linguistic ordering regularities, and the pragmatic reasoning speakers engage in to arrive at meaning in context. ***** Please forward this announcement to faculty and students in your department.

1 0

DeCenter Seminar Series: Tues, Dec 10 at 4:30
by Emily C. Lawrence 04 Dec '24

04 Dec '24

Tuesday, December 10th , at 4:30 PM , the DeCenter Seminar Series continues with Muriel Médard, co-founder of Optimum and NEC Chair of Software Science and Engineering at MIT, where she is a Professor in EECS. Currently on leave from MIT, she will present a seminar titled "The Data Socket - A Canonical Construct for Web 3 and the Coding to Enable It." The event will take place in the Friend Center Convocation Room (113) . Abstract: The success of Web 2 has relied on powerful abstractions and their realization. That of Web 3 requires the same. In Web 2, TCP/IP mimics a virtual dedicated link between nodes, while operating over a heterogeneous, meshed network. For Web 3, the Optimum Data Socket (ODS) provides data access over a virtual dedicated memory instantiated over a permissionless, decentralized, possibly unreliable set of nodes. ODS gives atomic, consistent, and durable data access. Realizing ODS requires deploying new erasure coding techniques, that are infinitely composable, stateless, and optimum in permissionless systems. Bio: Muriel Médard is the co-founder of Optimum, on leave from MIT, where she holds the NEC Chair of Software Science and Engineering for the School of Engineering at MIT, and is a Professor in EECS. She obtained three bachelor’s degrees, her M.S. and Sc.D., all from MIT. Muriel is a Member of the US National Academy of Engineering (elected 2020), a Member of the German National Academy of Sciences Leopoldina (elected 2022), a Fellow of the US National Academy of Inventors (elected 2018), American Academy of Arts and Sciences (elected 2021), and a Fellow of the Institute of Electrical and Electronics Engineers (elected 2008). She holds Honorary Doctorates from the Technical University of Munich (2020), the University of Aalborg (2022) and the Budapest University of Technology and Economics (2023). Muriel was awarded the 2022 IEEE Kobayashi Computers and Communications Award. She received the 2019 Best Paper award for IEEE Transactions on Network Science and Engineering, the 2018 ACM SIGCOMM Test of Time Paper Award, as well as nine conference paper awards. Muriel served as the Editor-in-Chief (EIC) of IEEE Transactions on Information Theory and was EiC of IEEE JSAC. She was president of the IEEE Information Theory Society. Muriel received the inaugural MIT Postdoctoral Association Mentoring Award in 2022, the inaugural MIT EECS Graduate Student Association Mentor Award, voted by the students, in 2013. She set up the Women in the Information Theory Society (WithITS) and Information Theory Society Mentoring Program. She was recognized with the 2017 IEEE Aaron Wyner Distinguished Service Award. Muriel has over seventy US and international patents awarded, the vast majority of which have been licensed or acquired. Muriel has supervised over 40 master students, over 20 doctoral students and over 25 postdoctoral fellows.

1 0

CS Colloquium Speakers: week of March 4
by Emily C. Lawrence 03 Dec '24

03 Dec '24

CS Colloquium Speakers Speaker: Sewon Min, University of Washington Date: Monday, March 4 Time: 12:30pm EST Location: CS 105 Host: Danqi Chen Event page: https://www.cs.princeton.edu/events/26579 Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_5uVGEpXNTVe8eBNSLpxKtg Title: Rethinking Data Use in Large Language Models Abstract: Large language models (LMs) such as ChatGPT have revolutionized natural language processing and artificial intelligence more broadly. In this talk, I will discuss my research on understanding and advancing these models, centered around how they use the very large text corpora they are trained on. First, I will describe our efforts to understand how these models learn to perform new tasks after training, demonstrating that their so-called in context learning capabilities are almost entirely determined by what they learn from the training data. Next, I will introduce a new class of LMs—nonparametric LMs—that repurpose this training data as a data store from which they retrieve information for improved accuracy and updatability. I will describe my work on establishing the foundations of such models, including one of the first broadly used neural retrieval models and an approach that simplifies a traditional, two-stage pipeline into one. I will also discuss how nonparametric models open up new avenues for responsible data use, e.g., by segregating permissive and copyrighted text and using them differently. Finally, I will envision the next generation of LMs we should build, focusing on efficient scaling, improved factuality, and decentralization. Bio: Sewon Min is a Ph.D. candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. Her research focuses on language models (LMs): studying the science of LMs, and designing new model classes and learning methods that make LMs more performant and flexible. She also studies LMs in information-seeking, legal, and privacy contexts. She is a co-organizer of multiple tutorials and workshops, including most recently at ACL 2023 on Retrieval-based Language Models and Applications and upcoming at ICLR 2024 on Mathematical and Empirical Understanding of Foundation Models. She won a paper award at ACL 2023, received a J.P. Morgan Fellowship, and was named an EECS rising star in 2022. Speaker: Lianmin Zheng, University of California, Berkeley Date: Tuesday, March 5 Time: 12:30pm EST Location: CS 105 Host: Ravi Netravali Event page: https://www.cs.princeton.edu/events/26593 Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_ghiT2HbhSPqKBouJ-VwzFg Title: Scalable and Efficient Systems for Large Language Models Abstract: Large Language Models (LLMs) have been driving recent breakthroughs in AI. These advancements would not have been possible without the support of scalable and efficient infrastructure systems. In this talk, I will introduce several underlying systems I have designed and built to support the entire model lifecycle, from training to deployment to evaluation. First, I will present Alpa, a system for large-scale model-parallel training that automatically generates execution plans unifying data, operator, and pipeline parallelism. Next, I will discuss efficient deployment systems, covering the frontend programming interface and backend runtime optimizations for high-performance inference. Finally, I will complete the model lifecycle by presenting our model evaluation efforts, including the crowdsourced live benchmark platform, Chatbot Arena, and the automatic evaluation pipeline, LLM-as-a-Judge. These projects have collectively laid a solid foundation for large language model systems, being widely adopted by leading LLM developers and companies. I will conclude by outlining some future directions of machine learning systems, such as co-optimizing across the full stack for building AI-centric applications. Bio: Lianmin Zheng is a Ph.D. student in the EECS department at UC Berkeley, advised by Ion Stoica and Joseph E. Gonzalez. His research interests include machine learning systems, large language models, compilers, and distributed systems. He builds full-stack, scalable, and efficient systems to advance the development of AI. He co-founded LMSYS.org, where he leads impactful open-source large language model projects such as Vicuna and Chatbot Arena, which have received millions of downloads and served millions of users. He also co-organized the Big Model Tutorial at ICML 2022. He has received a Meta Ph.D. Fellowship, an IEEE Micro Best Paper Award, and an a16z open-source AI grant. Speaker: Emma Dauterman, University of California, Berkeley Date: Thursday, March 7 Time: 12:30pm EST Location: CS 105 Host: Amit Levy Event page: https://www.cs.princeton.edu/events/26585 Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_soNesOKXSFml9MPaTx_1iw Title: Secure systems from insecure components Abstract: In many computer systems today, an attacker that breaks one system component can steal data from millions of users. In this talk, I will present two systems that can withstand component compromise. I will describe (1) a single sign-on system that protects user security and privacy from a compromised single sign-on server, and (2) a secure-hardware-based backup service that protects user backups from compromised secure hardware devices. These systems provide strong security and privacy properties while taking into account practical constraints such as compatibility requirements, hardware limitations, and user expectations. Each splits user secrets across different system components, using new cryptographic tools to provide necessary functionality while protecting user data. Bio: Emma Dauterman is a Ph.D. candidate at UC Berkeley where she is advised by Raluca Ada Popa and Ion Stoica. Her research interests include computer security, systems, and applied cryptography. She has received the Microsoft Research Ada Lovelace fellowship, the NSF graduate research fellowship, and a UC Berkeley EECS excellence award.

1 22