December 2024 - talks - lists.cs.princeton.edu

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