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

Wei Luo will present her MSE Thesis talk "SketchProbe: Discovering Vulnerabilities in Sketch-based Applications with Reinforcement Learning" on Wednesday, April 24, 2024 at 2pm in CS 402.
by Gradinfo 23 Apr '24

23 Apr '24

Wei Luo will present her MSE Thesis talk "SketchProbe: Discovering Vulnerabilities in Sketch-based Applications with Reinforcement Learning" on Wednesday, April 24, 2024 at 2pm in CS 402. Advisor: Maria Apostolaki, Reader: Benjamin Eysenbach All are invited to attend. Please see abstract below. Abstract: Sketches are approximate data structures critical to network traffic monitoring. They are specifically designed for environments constrained by memory, enabling the maintenance of accurate statistics within a compact space. This efficiency comes at the cost of estimation error that varies based on the workload encountered by the sketch. Traditionally, sketch-based applications are optimized for average traffic scenarios, and this assumption of standard patterns of network traffic introduces vulnerabilities, as these applications may not be prepared for atypical or adversarial traffic patterns. Manual testing for these vulnerabilities is time-intensive and often impractical due to the vast range of possible traffic scenarios. In this paper, we introduce SketchProbe, a novel system leveraging Reinforcement Learning (RL) to identify adversarial traffic patterns in sketch-based applications. Unlike manual identification, SketchProbe automates the discovery process, ensuring a thorough and efficient exploration of potential failure modes. Our evaluation indicates that SketchProbe effectively identifies critical scenarios that significantly impact the performance of sketch-based applications, which is valuable for improving the robustness of such applications.

2 1

ML in Physics: Joshua Shaevitz, tomorrow at 4:30pm in Jadwin Hall A10
by Emily C. Lawrence 23 Apr '24

23 Apr '24

Dear Colleagues, We are thrilled to invite you to the next ML in Physics Seminar talk. Here are the details: Speaker : Joshua Shaevitz (Professor of Physics and Biophysics at Princeton University) When/Where : Wednesday, April 24th at 4:30pm in Jadwin Hall A10 Title : Supervised and unsupervised algorithms for measuring animal behavior Abstract : For the past decade, my group has worked on supervised and unsupervised algorithms that take video data of behaving animals as inputs and discover stereotyped dynamics in the motion of body parts. We have used these techniques to study the patterns of behavior over an animal’s lifespan, how the brain specifies which behavior to actuate, social behaviors in pairs of animals, and the effect of neurological disorders on behavior and social interactions. I will briefly discuss the types of algorithms we use and then go through a variety of results from different experimental systems including worms, fruit flies, bumblebees, mice, and fish. For more details, including information about how to sign up for our listserv, please visit [ https://ml.physics.princeton.edu/ | https://ml.physics.princeton.edu/ ] . Sincerely, ML in Physics Organizers (Gage DeZoort, Peter Elmer, Boris Hanin, Mariangela Lisanti, and Dan Marlow)

1 0

Prachi Sinha will present her MSE talk "Augmenting Concept-Labeled Datasets for Interpretability Using Counterfactual Generation" TODAY Monday, April 22 at 12:30 PM in CS 402.
by gradinfo＠cs.princeton.edu 23 Apr '24

23 Apr '24

Prachi Sinha will present her MSE talk "Augmenting Concept-Labeled Datasets for Interpretability Using Counterfactual Generation" Monday, April 22 at 12:30 PM in CS 402. Advisor: Vikram Ramaswamy, Reader: Olga Russakovsky Abstract: Concept-based interpretability methods use a pre-defined set of human-understandable concepts to explain a model's output. These explanations are learned by "probing" the model using a concept-labeled dataset and learning how concepts can be linearly combined to predict outputs. However, there are several limitations to current methods. Explanations are highly dependent on the probe dataset, and they may reflect correlations between concepts and outputs, rather than causation. To address these issues, we augment COCO, a concept-labeled dataset, with counterfactual images in which particular semantic concepts have been removed. Using such counterfactual images, we attempt to improve the accuracy of explanations for a scene classification model, and more directly learn the causal relationships between concepts and outputs. We find that explanation accuracy improves in certain cases, but is generally still limited by the probe dataset's alignment with the model, and that counterfactual images elucidate issues with assigning weights to concepts when there are strong correlations between concepts. CS Grad Calendar: https://calendar.google.com/calendar/event?action=TEMPLATE <https://calendar.google.com/calendar/event?action=TEMPLATE&tmeid=NzljZTNoZm 1ibWc1NGU4ZmtodjJkdHRuMmggYWNnMDc5YmxzbzRtczNza2tmZThwa2lyb2dAZw&tmsrc=acg07 9blso4ms3skkfe8pkirog%40group.calendar.google.com> &tmeid=NzljZTNoZm1ibWc1NGU4ZmtodjJkdHRuMmggYWNnMDc5YmxzbzRtczNza2tmZThwa2lyb 2dAZw&tmsrc=acg079blso4ms3skkfe8pkirog%40group.calendar.google.com

1 4

PPH Lunch seminars: Yuri Pritykin and Jessica Metcalf April 26 at 12 pm at 252 Nassau Street
by Emily C. Lawrence 23 Apr '24

23 Apr '24

Please join the Princeton Precision Health Initiative for the next talks in our lunch time seminar series this Friday, April 26, at 12:00 pm, in our new space at 252 Nassau Street. Jessica Metcalf from EEB and SPIA will present a talk titled, “The life course of influenza infection: pathways to precision health”, and Yuri Pritykin from Genomics and Computer Science will present a talk titled, “Regulatory genomics of T cells in mouse and human”. Lunch will be provided. Please note that getting to the seminar space currently requires that you climb a set of stairs. If an accommodation is needed, please contact PPH in advance at: [ mailto:princetonPPH@princeton.edu | princetonPPH(a)princeton.edu ] The PPH Team ************************************ Princeton Precision Health [ http://pph.princeton.edu/ | pph.princeton.edu ] [ mailto:princetonpph@princeton.edu | princetonpph(a)princeton.edu ]

1 0

David Xu will present his MSE talk on April 26th, 2024 at 4:30pm via Zoom
by Nicki Mahler 22 Apr '24

22 Apr '24

David Xu will present his MSE talk on April 26th, 2024 at 4:30pm via Zoom. The talk will be held over zoom at [ https://princeton.zoom.us/j/99796777049 | https://princeton.zoom.us/j/99796777049 ] David's committee is as follows: Karthik Narasimhan (adviser) and Adam Finkelstein (reader) Abstract: Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing audio-language datasets are notably smaller, and manual labeling is hindered by the need to listen to entire audio clips for accurate labeling. Our method systematically generates audio-caption pairs by augmenting audio clips with natural language labels and corresponding audio signal processing operations. Leveraging a Large Language Model, we generate descriptions of augmented audio clips with a prompt template. This scalable method produces AudioSetMix, a high-quality training dataset for text-and-audio related models. Integration of our dataset improves models performance on benchmarks by providing diversified and better-aligned examples. Notably, our dataset addresses the absence of modifiers (adjectives and adverbs) in existing datasets. By enabling models to learn these concepts, and generating hard negative examples during training, we achieve state-of-the-art performance on multiple benchmarks.

1 0

Shunyu Yao will present his FPO "Language Agents: From Next-Token Prediction to Digital Automation" on Thursday, May 2, 2024 at 10:00 AM in CS 105 and Zoom.
by CS Grad Department 22 Apr '24

22 Apr '24

Shunyu Yao will present his FPO "Language Agents: From Next-Token Prediction to Digital Automation" on Thursday, May 2, 2024 at 10:00 AM in CS 105 and Zoom. Location: Zoom link: http://princeton.zoom.us/my/shunyuy The members of Shunyu’s committee are as follows: Examiners: Karthik Narasimhan (Adviser), Tom Griffiths, Benjamin Eysenbach Readers: Sanjeev Arora, Tatsunori Hashimoto (Stanford) 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: Building autonomous agents to interact with world lies at the core of artificial intelligence (AI). This thesis introduces “language agents”, a new category of agents that utilize large language models (LLMs) to reason to act, marking a departure from traditional agents via extensive rule design or learning. It is developed in three parts: Part I motivates the necessity for language agents by introducing a new set of AI problems and benchmarks based on interaction with large-scale, real-world computer environments, such as the Internet or code interfaces. These “digital automation” tasks present tremendous values for alleviating tedious labor and improving our life, yet pose significant challenges for prior agent or LLM methods in decision-making over open-ended natural language and long horizon, calling for new methodology. Part II lays the methodological foundation for language agents, where the key idea is to apply LLM reasoning for versatile and generalizable agent acting and planning, which also augments LLM reasoning to be more grounded and deliberate via external feedback and internal control. We show language agents can solve a diversity of language and agent tasks (especially digital automation tasks proposed in Part I), with notable improvements over prior LLM-based methods and traditional agents. Part III consolidates insights from Parts I and II and outlines a principled framework for language agents. The framework provides modular abstractions to organize various LLM-based methods, to understand their gaps from human cognition, and to inspire and develop new methods towards general-purpose autonomous agents. >From foundational empirical tasks and methods to a unifying conceptual framework, this thesis establishes the study of language agents as a distinct and rigorously defined field at the frontier of AI research.

1 0

Samuel Barnett will present his FPO "Incorporating human plausibility in single- and multi-agent AI systems" on Wednesday, May 1, 2024 at 9:30 AM in CS 402.
by CS Grad Department 22 Apr '24

22 Apr '24

Samuel Barnett will present his FPO " Incorporating human plausibility in single- and multi-agent AI systems " on Wednesday, May 1, 2024 at 9:30 AM in CS 402 . Location: CS 402 The members of Samuel ’s committee are as follows: Examiners: Ryan Adams (Adviser), Tom Griffiths (Adviser) , Benjamin Eysenbach Readers: Elad Hazan , Karthik Narasimhan 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: As AI systems play a progressively larger role in human affairs, it becomes more important that these systems are built with insights from human behavior. In particular, models that are developed on the principle of human plausibility will more likely yield results that are more accountable and more interpretable, in a way that greater ensures an alignment between the behavior of the system and what its stakeholders want from it. In this dissertation, I will present three projects that build on the principle of human plausibility for three distinct applications: (i) Plausible representations: I present the Priority-Adjusted Reply for Successor Representations (PARSR) algorithm, a single-agent reinforcement learning algorithm that brings together the ideas of prioritisation-based replay and successor representation learning. Both of these ideas lead to a more biologically plausible algorithm that captures human-like capabilities of transferring and generalizing knowledge from previous tasks to novel, unseen ones. (ii) Plausible inference: I present a pragmatic account of the weak evidence effect, a counterintuitive phenomenon of social cognition that occurs when humans must account for persuasive goals when incorporating evidence from other speakers. This leads to a recursive, Bayesian model that encapsulates how AI systems and their human stakeholders communicate with and understand one another in a way that accounts for the vested interests that each will have. (iii) Plausible evaluation: I introduce a tractable and generalizable measure for cooperative behavior in multi-agent systems that is counterfactually contrastive, contextual, and customizable with respect to different environmental parameters. This measure can be of practical use in disambiguating between cases in which collective welfare is achieved through genuine cooperation, or by each agent acting solely in its own self-interest, both of which result in the same outcome.

1 0

Leon Schuermann will present his general exam "Fortifying Rust’s Foreign Function Interface with Encapsulated Functions" on April 29, 2024 at 10am in Friend 110.
by Nicki Mahler 22 Apr '24

22 Apr '24

Leon Schuermann will present his general exam "Fortifying Rust’s Foreign Function Interface with Encapsulated Functions" on April 29, 2024 at 10am in Friend 110. The members of his committee are as follows: Amit Levy (adviser), Wyatt Lloyd, and Mae Milano Abstract and reading list links are below: [ https://docs.google.com/document/d/1D701FYZKlxkfQ2bxm1jaLSYEksHCrVvW0iOg26Z… | https://docs.google.com/document/d/1D701FYZKlxkfQ2bxm1jaLSYEksHCrVvW0iOg26Z… ] Abstract Memory- and type-safe languages like Rust are increasingly popular for systems development. Nonetheless, practical systems must interact with code written in memory-unsafe languages. Examples for this can be found across the spectrum, with many Rust applications linking against popular libraries such as OpenSSL, to security and safety-critical embedded systems, where subsystems such as cryptographic implementations are subject to industrial and governmental certification requirements. Direct interactions with such libraries, however, expose safe languages to significant risks: any single bug in either the foreign code or the cross-language interactions may arbitrarily violate the memory and/or type safety of the wrapping language. This talk presents Encapsulated Functions, an ongoing research project exploring how to secure cross-language interactions along with their differing guarantees and semantics around memory- and type-safety. At its core, Encapsulated Functions is a framework that combines memory protection mechanisms (such as the RISC-V Physical Memory Protection or Intel's Memory Protection Keys) with a set of portable types to both restrict and encapsulate behavior across the language boundary. Through the portability across different memory protection mechanisms we can utilize this infrastructure in both highly-restrictive embedded systems and applications running on conventional operating systems alike.

1 0

CS Colloquium Speaker: Timothy Lillicrap, Monday April 22 at 12:30pm
by Emily C. Lawrence 22 Apr '24

22 Apr '24

CS Colloquium Speaker Speaker: Timothy Lillicrap, Google DeepMind Date: Monday, April 22, 2024 Time: 12:30pm EST Location: CS 105 Host: Sanjeev Arora Event page: https://www.cs.princeton.edu/events/26640 Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_k0Dgpd3aT6SJYngnKTkxuw Title: Learning Models of the Environment for Reinforcement Learning Abstract: Model-based algorithms for decision making have long held the promise of being more powerful and data-efficient than model-free counterparts. However, the widespread application of model-based methods has been limited by the need for perfect models of the environment. The game of Go was mastered by AlphaGo using a combination of neural networks and the MCTS planning algorithm. But, planning required a perfect simulator of the game rules. For cases such as robotics or natural language understanding, where no perfect simulators are available, so model-based approaches are not easy to apply effectively. Addressing this limitation, I will describe algorithms (Dreamer and MuZero) that utilize deep neural networks to learn robust environment models. These models are used to imagine potential futures. Imagined futures can be used for planning, and for learning policy and value functions. The advent and success of powerful model-based learning algorithms offer hints about the next wave of language models. Bio: Timothy Lillicrap received an Hon. B.Sc. in Cognitive Science & Artificial Intelligence from the University of Toronto and a Ph.D. in Systems Neuroscience from Queen’s University in Canada. He moved to the University of Oxford in 2012 where he worked as a Postdoctoral Research Fellow. In 2014 he joined Google DeepMind as a Research Scientist and became a Director of Research in 2023. His research focuses on machine learning for optimal control and decision making, as well as using these mathematical frameworks to understand how the brain learns. He has developed new algorithms for exploiting deep networks in the context of reinforcement learning, and new recurrent memory architectures for one-shot learning problems. His projects have included applications of deep learning to robotics, solving games such as Go and Starcraft, and human interaction.

1 1

Gary Hu will present his General Exam "Inferring spatial diffusion and cell division rates with spatial lineage tracing data." on Wednesday, April 24, 2024 at 3:00 PM in CS 105.
by CS Grad Department 19 Apr '24

19 Apr '24

Gary Hu will present his General Exam " Inferring spatial diffusion and cell division rates with spatial lineage tracing data. " on Wednesday, April 24, 2024 at 3:00 PM in CS 105 . Committee Members: Ben Raphael (advisor), Yuri Pritykin , Olga Troyanskaya Abstract: https://docs.google.com/document/d/1wzpdne5NQ19j7iQYGZ6L1jwcu8ik4KYAeABCTyf… Reading List: https://docs.google.com/document/d/1wzpdne5NQ19j7iQYGZ6L1jwcu8ik4KYAeABCTyf… 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