- talks - lists.cs.princeton.edu

Nimra Nadeem will present her MSE thesis "Interpretive Discretion in AI Systems" on Wednesday, April 22nd, 2026 in CS 402 and Zoom at 2:00pm.
by gradinfo＠cs.princeton.edu 21 Apr '26

21 Apr '26

Nimra Nadeem will present her MSE thesis "Interpretive Discretion in AI Systems" on Wednesday, April 22nd, 2026 in CS 402 and Zoom at 2:00pm. Zoom Link: https://princeton.zoom.us/j/5310001339 Advisor: Peter Henderson Reader: Lydia Liu All are welcome to attend. Abstract: Natural language is inherently ambiguous because it is open to interpretation. Resolving this ambiguity requires the exercise of interpretive discretion: the freedom to choose between multiple plausible interpretations of a given statement. We study this problem in the context of AI alignment. AI systems are increasingly governed by natural language principles, such as OpenAI's ModelSpec or Anthropic's Constitution for Claude. As in legal systems, ambiguity arises both from how principles are written and how they are applied. But while legal systems use institutional safeguards to manage such ambiguity, rule-based AI alignment pipelines lack comparable mechanisms. Drawing on US legal theory, we identify key gaps in current rule-based alignment pipelines by examining how legal systems constrain ambiguity at both the rule creation and rule application steps. We propose a computational framework that formalizes interpretive ambiguity as constrained entropy minimization and introduces two law-inspired mechanisms: (1) a rule refinement pipeline that minimizes interpretive disagreement by revising ambiguous rules, and (2) prompt-based interpretive constraints that reduce disagreement during rule application. We evaluate our framework on a 5,000-scenario subset of the WildChat dataset and show that both interventions improve judgment consistency across a panel of reasonable interpreters. We then extend our analysis to the multi-rule setting and identify some important open challenges. We conclude by discussing the normative implications of interpretive discretion in AI systems, including its impact on fairness in decision-making settings. Our work draws attention to the overlooked challenge of interpretive discretion in AI systems and offers an initial step toward systematically managing it.

1 0

AI Lab Distinguished Lecture-Elif Ertekin: Friday April 24
by Emily C. Lawrence 21 Apr '26

21 Apr '26

AI Lab Distinguished Lecture Series: Elif Ertekin, Associate Professor, University of Illinois at Urbana-Champaign Apr 24, 2026 2:00 pm – 3:00 pm Location: Robertson 002 “Physical Mechanisms or Learned Patterns? Embedding Symmetries and Equations of Motion as Inductive Biases for Materials Simulations” [ https://invent.ai.princeton.edu/events/2026/physical-mechanisms-or-learned-… | For more information and to RSVP, please visit our website. ]

1 0

Metropolis Student & Postdoc Research Symposium: Friday, April 24
by Emily C. Lawrence 21 Apr '26

21 Apr '26

Register Today to Attend the 2026 Metropolis Student and Postdoc Research Symposium | Friday, April 24, 2026 Dear CS Community, The Metropolis Initiative invites you to the 2026 Metropolis Student and Postdoc Research Symposium, co-sponsored by the Princeton Initiative. This half-day event is designed to foster interdisciplinary exchange, collaboration, and engagement across the research community. The symposium provides a platform for students and postdoctoral researchers to share their work and engage with faculty and peers in a constructive and supportive environment. It aims to deepen connections across disciplines and highlight innovative research. This year, we are excited to feature a diverse group of graduate students, undergraduate students, and postdoctoral researchers from several departments across Princeton presenting their work. Date: Friday, April 24, 2026 Time: 12:00 PM to 3:30 PM Location: Friends Center Convocation Room (Friend 113) Lunch: Provided [ https://docs.google.com/forms/d/e/1FAIpQLSeyqjIrt3IGIXtc7f9eIEJ8qJ_EStV0nkV… | Register here ] or use the QR Code Below We hope to see many of you there!

1 0

Computational Math IDeAS seminar
by Emily C. Lawrence 21 Apr '26

21 Apr '26

COMPUTATIONAL MATH – IDeAS SEMINAR Recurring weekly series · Thursdays · 224 Fine Hall ** NOTE: Earlier time than previous weeks ** This week's talk: Speaker: Tom Trogdon (University of Washington) Title: Towards PCA without the SVD: Lanczos-based spike detection Date: Thursday, April 23, 2026 Time: 1:30 PM – 2:30 PM (note earlier time) Room: 224 Fine Hall Abstract: This talk will give an overview of the study of algorithms on random data, and in particular, algorithms from numerical linear algebra (NLA) on random matrices. The combination of ideas from numerical linear algebra and random matrices goes back, at least, to the seminal work of Goldstine and von Neumann. The works of Trotter, Silverstein, Edelman, Dumitriu & Edelman, Pfrang, Deift & Menon, and many others, developed these ideas further. A core subset of NLA algorithms, the Krylov subspace methods, play particularly well with existing random matrix theory. Through the study of random orthogonal polynomials, as perturbations of deterministic orthogonal polynomials, the concentration phenomenon in these methods can be explained using local laws from random matrix theory. We will use these ideas, and methods, to efficiently and robustly perform spike detection in the spiked sample covariance model and move towards PCA without the SVD. About the speaker: Thomas Trogdon is a Professor and Chair of Applied Mathematics, an adjunct professor in the Department of Mathematics and an affiliate of the Algorithmic Foundations of Data Science Institute, all at the University of Washington. Trogdon works on a variety of computational, applied and theoretical problems from the fields of mathematical physics, random matrix theory and approximation theory. He was an NSF Postdoctoral Fellow at the Courant Institute at NYU from 2013-2016, and he won the SIAM Richard C. DiPrima Prize in 2013. Then he joined the Department of Mathematics at UC Irvine and won the 2017 SIAM Gábor Szegő Prize before he joined the University of Washington in 2019. Up next: Thursday, April 30 – Boris Landa (Yale University). There are a few slots to meet with the speakers, please let us know if you would like one (gilles(a)princeton.edu). - Liza Rebrova, Marc Aurèle Gilles, and Jorge Garza Vargas.

1 0

Fangqi Dong will present "Explicit Separations for One-Query Unitary Synthesis" on 4/21/26 at 1:30 PM in CS 301.
by Nicki Mahler 21 Apr '26

21 Apr '26

Fangqi Dong will present "Explicit Separations for One-Query Unitary Synthesis" on 4/21/26 at 1:30 PM in CS 301. Committee: Alex Lombardi(adviser), Ran Raz, Pravesh Kothari Abstract & Reading List: [ https://docs.google.com/document/d/1LiUZ2vXIhlSFCytJqTmMB5XQkjcHlBQ9Xq-m0rA… | https://docs.google.com/document/d/1LiUZ2vXIhlSFCytJqTmMB5XQkjcHlBQ9Xq-m0rA… ] Abstract: The unitary synthesis problem (Aaronson-Kuperberg CCC’07) asks whether an arbitrary n-qubit unitary U can be implemented by a polynomial size quantum circuit, given access to some classical oracle f_U that depends on U. Recently, it was proved (Lombardi-Ma-Wright STOC’24) that for a Haar-random unitary, this is impossible for any efficient synthesis algorithm that makes only one query (or polynomially many parallel queries) to an arbitrary classical oracle. In this work, we extend this line of lower bound for random unitaries to a finer structural understanding of one-query synthesis for natural explicit families. In particular, we prove one-query lower bounds for explicit families of unitaries that have efficient two-query synthesis algorithms, thereby separating the power of one-query and two-query synthesis algorithms. We also give a one-query algorithm for complex phase unitaries that achieves constant approximation, and prove a sharper separation between one-query unitary synthesis and quantum programs.

2 3

Frederick Qiu will present his General Exam "Separations between Algorithms and Truthful Mechanisms" on April 27, 2026 at 12pm in CS 302.
by Gradinfo 20 Apr '26

20 Apr '26

Frederick Qiu will present his General Exam " Separations between Algorithms and Truthful Mechanisms" on April 27, 2026 at 12pm in CS 302. Zoom Link: [ https://princeton.zoom.us/j/3603536257 | https://princeton.zoom.us/j/3603536257 ] Committee: Matthew Weinberg(adviser), Mark Braverman, and Huacheng Yu Link to Abstract and Reading List: [ https://docs.google.com/document/d/1FtdsKcw3zmFtl7DfMWENuEFNuUfa-FFOgf-ynmn… | https://docs.google.com/document/d/1FtdsKcw3zmFtl7DfMWENuEFNuUfa-FFOgf-ynmn… ] Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

2 2

Kylie Zhang will present her MSE talk "AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments" on Weds 4/22 at 10am in Sherrerd 306.
by Gradinfo 20 Apr '26

20 Apr '26

Kylie Zhang will present her MSE talk "AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments" on Weds 4/22 at 10am in Sherrerd 306. Committee: Prof. Peter Henderson (adviser) and thesis reader is Prof. Jonathan Mayer. Abstract: "In oral arguments, judges probe attorneys with questions about the factual record, legal claims, and the strength of their arguments. To prepare for this questioning, both law schools and practicing attorneys rely on moot courts: practice simulations of appellate hearings. Leveraging a dataset of U.S. Supreme Court oral argument transcripts, we examine whether AI models can effectively simulate justice-specific questioning for moot court-style training. Evaluating oral argument simulation is challenging because there is no single correct question for any given turn. Instead, effective questioning should reflect a combination of desirable qualities, such as anticipating substantive legal issues, detecting logical weaknesses, and maintaining an appropriately adversarial tone. We introduce a two-layer evaluation framework that assesses both the realism and pedagogical usefulness of simulated questions using complementary proxy metrics. We construct and evaluate both prompt-based and agentic oral argument simulators. We find that simulated questions are often perceived as realistic by human annotators and achieve high recall of ground truth substantive legal issues. However, mod- els still face substantial shortcomings, including low diversity in question types and sycophancy. Importantly, these shortcomings would remain undetected under naive evaluation approaches."

1 0

Daniel Williams will present his General Exam "Daniel Williams will present his General Exam "An Efficient and Scalable Language Design for High-Dimensional Clifford Algebras on GPU" on Wednesday, April 22, 2026 at 3:00 PM in E-Quad J223 and via zoom.
by CS Grad Department 17 Apr '26

17 Apr '26

Daniel Williams will present his General Exam "Daniel Williams will present his General Exam "An Efficient and Scalable Language Design for High-Dimensional Clifford Algebras on GPU" on Wednesday, April 22, 2026 at 3:00 PM in E-Quad J223 and via zoom. Zoom link: https://princeton.zoom.us/j/6762826001 Committee Members: Ryan Adams (advisor), David Walker, Christine Allen-Blanchette Abstract: Many of the most challenging problems in computational physics and engineering, ranging from electromagnetism to inverse design of complex mechanical systems, are fundamentally geometric. However, conventional linear algebra based numerical methods do not natively encode geometric structure, often leading to ill-conditioned optimization, constraint drift, and poor scaling in high-dimensional settings. While Clifford Algebras provide a principled and coordinate-free mathematical framework for representing symmetries, high dimensional spaces, and differential geometry on curved manifolds, its practical adoption in large-scale scientific computing has been limited by exponential memory requirements and lack of GPU-accelerated infrastructure. This work introduces a new framework for accelerated computational geometry in high dimensions using Clifford Algebras. We develop a static type system that automatically infers and reduces memory constraints, allowing numerical execution to operate on dramatically reduced representations without approximation. Building on this foundation, we implement a Python-based Just-in-Time (JIT) compiler integrated with JAX, the accelerated array computation library, that traces user-defined geometry programs of various clifford algebra signatures and lowers them into optimized GPU kernels, while preserving precision and full compatibility with automatic differentiation. Preliminary results demonstrate substantial improvements in tractable dimensionality and GPU throughput under batching, extending feasible computation from n < 6 to up to n = 20 dimensions on a single GPU by exploiting known sparsity before execution. Reading List: https://docs.google.com/document/d/1eSBhk0Irmfqf26QOlY5Jrbb_kUmhOQgN4Jbay6_… 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

Nobline Yoo will present her MSE Talk "D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation" on Monday, April 20, 2026 at 12:30p in CS 402.
by CS Grad Department 17 Apr '26

17 Apr '26

Nobline Yoo will present her MSE Talk "D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation" on Monday, April 20, 2026 at 12:30p in CS 402. Committee Members: Prof. Olga Russakovsky (advisor), Prof. Zhuang Liu (reader). All are welcome to attend. Title: D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation Abstract: Text-to-image (T2I) diffusion models have achieved strong performance in semantic alignment, yet they still struggle with generating the correct number of objects specified in prompts. Existing approaches typically incorporate auxiliary counting networks as external critics to enhance numeracy. However, since these critics must provide gradient guidance during generation, they are restricted to regression-based models that are inherently differentiable , thus excluding detector-based models with superior counting ability, whose count-via-enumeration nature is non-differentiable . To overcome this, we propose Detector-to-Differentiable ( D2D ), a novel framework that transforms non-differentiable detection models into differentiable critics, leveraging their superior counting ability to guide numeracy generation. Specifically, we design custom activation functions to convert detector logits into soft binary indicators, which are then used to optimize the noise prior at inference time with pre-trained T2I models. Our extensive experiments on SDXL-Turbo, SD-Turbo, and Pixart-DMD across four benchmarks of varying complexity (low-density, high-density, and multi-object scenarios) demonstrate consistent and substantial improvements in object counting accuracy (e.g., boosting up to 13.7% on D2D-Small, a 400-prompt, low-density benchmark), with minimal degradation in overall image quality and computational overhead.

1 0

Max Gonzalez Saez-Diez will present his MSE thesis "D3: Dataset, Diagnosis, and Deployment of Video Models for Police Body-Worn Camera Understanding" on Monday, April 20th, 2026 in CS 402 at 12:00pm.
by CS Grad Department 17 Apr '26

17 Apr '26

Max Gonzalez Saez-Diez will present his MSE thesis "D3: Dataset, Diagnosis, and Deployment of Video Models for Police Body-Worn Camera Understanding" on Monday, April 20th, 2026 in CS 402 at 12:00pm. Advisor: Peter Henderson Reader: Olga Russakovsky All are welcome to attend. Abstract: Vision-language models are increasingly applied to police body-worn camera (BWC) video, yet few public benchmarks exist and researchers have little means to evaluate private vendor claims. This thesis addresses all three gaps: constructing the data necessary for training, evaluating models in a zero-shot manner on long-tailed phenomena, and demonstrating how this data can be used to train and deploy models in practice. First, we introduce EgoPolice. To the best of our knowledge, it is the largest existing dataset for egocentric understanding of real body-worn camera footage. Second, we present BWC-Bench, a zero-shot captioning benchmark that scores whether each listed action is asserted in the generated caption. Third, we describe work with a partner agency that provided access to their videos and use-of-force reports. To the best of our knowledge, this constitutes the first analysis of real police body-worn camera footage and associated use-of-force reports at this scale. A physical-interaction detector trained on EgoPolice ranks clips from a large private archive for human review. We find that models can support human-in-the-loop analysis at a scale not previously possible and uncover evidence of substantial underreporting of use-of-force events.

1 0