- talks - lists.cs.princeton.edu

Samuel Resendez will present his MSE talk "Online Contention Resolution against Online Adversaries" on April 21, 2025 at 2:30 pm in CS 302.
by Gradinfo 18 Apr '25

18 Apr '25

Samuel Resendez will present his MSE talk " Online Contention Resolution against Online Adversaries " on April 21, 2025 at 2:30 pm in CS 302. Committee: Matt Weinberg and Huacheng Yu Abstract: A framework called contention resolution schemes has been proposed as a way to unify algorithms for a relatively broad class of problems with similar combinatorial structures. A subset of this class comprises Bayesian online selection problems (BOSP). A BOSP describes an optimization problem that can be modeled as making an online selection of choices on a sequence of random variables, subject to some constraints. While the Bayesian online selection problem has been explored in many contexts we restrict ourselves to the k-uniform case. The k-uniform case describes settings where the only constraint on the selection of elements is the total cardinality of the set chosen. In particular, we are allowed to pick up to k elements from an arbitrarily large number of options. An online flavor of contention resolution schemes has been developed for BOSPs under k-uniform constraints. These schemes have been explored primarily in 2 settings. The first is the offline setting. In this setting, the ordering of elements is chosen before any of the elements are revealed. The other is the almighty setting. In this setting, we assume omnipotence for whoever is determining the element order - they are aware of all realizations of randomness, both of the elements and the algorithm, and are free to rearrange the order of elements shown at any moment. There is a third setting that lies between these two extremes - one that assumes that our opponent has a similar amount of power as us, in that they can rearrange elements arbitrarily after seeing what has been revealed, but do not know the realizations of any of the subsequent elements. This is known as the online setting. Our work demonstrates the hardness of online contention resolution against online adversaries. We develop tools to prove that the online case is more akin to the almighty case, and prove impossibility of restricted classes of algorithms against the online adversary.

1 0

Owen Xingjian Zhang will present his MSE talk “Enhancing Moderation in Decentralized Social Media: A Comprehensive Approach to Community-Level Blocklist Management and Customization on Mastodon” on Wednesday, April 23, 2025 at 1:30pm in CS 302.
by CS Grad Department 18 Apr '25

18 Apr '25

Owen Xingjian Zhang will present his MSE talk “Enhancing Moderation in Decentralized Social Media: A Comprehensive Approach to Community-Level Blocklist Management and Customization on Mastodon” on Wednesday, April 23, 2025 at 1:30pm in CS 302. The members of his committee are as follows: Andrés Monroy-Hernández (Adviser) and Manoel Horta Ribeiro (reader) All ae welcome to attend. Please see abstract below. Tools such as blocklists serve as crucial mechanisms for managing online interactions by preventing unwanted engagement and mitigating harassment. Most implementations of blocklists operate at the individual-level, where users can independently manage their blocklists. However, prior research suggests that blocklists at the community-level could be more effective, reliable, and particularly valuable for non-dominant groups seeking counterpublics where they can be safe from the systemic abuse they face online. At the same time, research on the use of community-level governance tools on platforms point to substantial challenges that would undermine the usefulness of community-level blocklists. In this work, we look to Mastodon, a decentralized social media network which allows independent servers hosting groups of users to enforce blocklists at the community-level / for the entire server; we aim to understand how community-level blocklists tools can be designed to maximize their expected benefits. Using a mock-up of a community-level blocklist tool interface informed by prior work, we ask: RQ1: What are the common features of community-level blocklists? RQ2: How do moderators perceive and utilize community-level blocklists? RQ3: What design features would enhance the usability and effectiveness of community-level blocklist management tools? Based on our results, we propose design implications to improve transparency, customization, and moderation flexibility in blocklist management tools for decentralized social media networks.

1 0

Kurtland Chua will present his FPO "Analyzing Meta-Learning in Supervised and Reinforcement Learning Settings" on Wednesday, April 30, 2025 at 2:00 PM in CS 401.
by CS Grad Department 16 Apr '25

16 Apr '25

Kurtland Chua will present his FPO "Analyzing Meta-Learning in Supervised and Reinforcement Learning Settings" on Wednesday, April 30, 2025 at 2:00 PM in CS 401. Location: CS 401 The members of Kurtland’s committee are as follows: Examiners: Jason Lee (Adviser), Elad Hazan, Benjamin Eysenbach Readers: Ryan Adams, Qi Lei (NYU) 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: Machine learning has recently seen widespread usage of large foundation models which, although highly expressive, are also prone to overfitting when trained on limited domain specific datasets. As such, training on larger but indirectly relevant datasets to extract useful representations, and more generally meta-learning, has proven to be key for using these models in data-sparse settings. This dissertation presents a theoretical study of the assumptions underlying meta-learning, focusing on two settings: Meta-Supervised Learning: Prior work has analyzed the statistical complexity of learning a fixed representation for several regression tasks. However, methods in practice, including popular gradient-based approaches like MAML, fine-tune representations for each task. As such, we performed the first theoretical study of fine-tuning-based representation learning. Firstly, we derive sample complexity bounds on a representative procedure applied to a generic class of representations. Secondly, we establish a sample complexity separation between using fine-tunable and fixed representations, illustrating when fine-tuning is preferable. Meta-Reinforcement Learning (RL): Many notions of shared task structure exist for meta-RL, including broadly useful “options” as in hierarchical RL (HRL). However, prior HRL regret bounds assume that the hierarchical structure is known a priori. To bridge this gap, we construct a notion of hierarchical structure that is provably recoverable under appropriate “coverage conditions”. Secondly, we show that the recovered hierarchy can be used to achieve downstream task regret exponentially better than minimax, under mild assumptions. These conditions encode notions such as temporal and state/action abstractions, suggesting that our analysis captures important aspects of HRL in practice.

1 0

Colin Wang will present his masters' thesis "Evaluating Multimodal Models for Chart Understanding" on April 21, 2025 at 2pm in the AI Lab (41 William Street) Conference Room (Room 274).
by CS Grad Department 16 Apr '25

16 Apr '25

Colin Wang will present his masters' thesis "Evaluating Multimodal Models for Chart Understanding" on April 21, 2025 at 2pm in the AI Lab (41 William Street) Conference Room (Room 274). The members of his committee are as follows: Danqi Chen (Adviser) and Sanjeev Arora (reader). All are welcome to attend. Please see the title and abstract below. Title : Evaluating Multimodal Models for Chart Understanding Abstract : Chart understanding and reasoning play a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. In this work, we propose CharXiv, a comprehensive evaluation suite involving 2,323 natural, challenging, and diverse charts from arXiv papers. CharXiv includes two types of questions: 1) descriptive questions about examining basic chart elements and 2) reasoning questions that require synthesizing information across complex visual elements in the chart. To ensure quality, all charts and questions are handpicked, curated, and verified by human experts. Our results reveal a substantial, previously underestimated gap between the reasoning skills of the strongest proprietary model and the strongest open-source model. All models lag far behind human performance of 80.5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs. Since its release, CharXiv has gained significant real-world adoption. It has been used internally by organizations such as OpenAI and Anthropic, and serves as an official benchmark for models including QwenVL, InternVL, and the Doubao series. CharXiv has also become a standard testbed for academic research in visual reasoning and has inspired the development of more challenging and visually-diverse evaluations in the AI community. In this talk, I will present the design and curation process of CharXiv, share key findings and failure modes from model evaluations, and reflect on CharXiv's ongoing impact within the broader research community.

1 0

Brendan Wang will present his MSE talk “Computational Modeling of Local Insulation of Chromatin in Drosophila” on Monday, April 21, 2025 at 1:00 pm in Carl Icahn 101.
by CS Grad Department 16 Apr '25

16 Apr '25

Brendan Wang will present his MSE talk “ Computational Modeling of Local Insulation of Chromatin in Drosophila ” on Monday, April 21, 2025 at 1:00 pm in Carl Icahn 101. The members of his committee are as follows: Yuri Pritykin(Adviser) and Mona Singh (reader) All ae welcome to attend. Please see abstract below. In Drosophila melanogaster, chromatin is partitioned into self-interacting regions called topologically-associated domains (TADs). At TAD boundaries, architectural proteins called insulators can provide insulation or the ability to prevent interactions between gene regulatory elements between neighboring domains. While existing methods have analyzed the sequence patterns underlying TAD boundaries, they have not thoroughly characterized how such patterns contribute to the insulatory function of TADs. Characterizing how the binding of insulators to DNA influences insulation in a genome-wide manner is crucial to deciphering the cis-regulatory rules cells use to regulate gene expression through chromatin organization. To this end, we propose Domino, a sequence-based deep learning method that predicts local insulation. Our results demonstrate that Domino can uncover the sequence patterns underlying local insulation in Drosophila and accurately predict in-silico the effects of experimental perturbations.

1 0

Natalia Khotiaintseva will present her MSE talk "GPU Acceleration of Adaptive Mesh Refinement via a Hashtable" on Monday, April 21, 2025 at 3:20pm in Friend Center 004.
by Gradinfo 15 Apr '25

15 Apr '25

Natalia Khotiaintseva will present her MSE talk "GPU Acceleration of Adaptive Mesh Refinement via a Hashtable" on Monday, April 21, 2025 at 3:20pm in Friend Center 004 (basement) Title: GPU Acceleration of Adaptive Mesh Refinement via a Hashtable Abstract: In this work we explore acceleration of computations in AMR for astrophysical simulations. Modern scientific codes widely use Adaptive Mesh Refinement, and they need to leverage GPU supercomputing power. Specifically, this thesis demonstrates a hashtable implementation on GPU to store the grid structure. On a toy problem, we compare the performance of a typical matrix implementation against a hashtable implementation in a worst-case scenario — when all grid cells are uniformly refined. Acceleration of such large-scale astrophysical hydrodynamics simulations is critically important, making optimization techniques such as GPU-based hashtable storage essential. Our result is that there is no disadvantage in the hashtable implementation versus the matrix implementation. This result is crucial for future implementation of a hashtable-based AMR with dynamic refinement and complete hydrodynamics simulation. We also explore the application of the Grace Hopper superchip to AMR code and observe a significant speedup of ~2.3 in gradient calculation, and ~14.7 speedup in hashtable creation. Additionally, we design a linter program to streamline CUDA C++ debugging process, in particular for our AMR implementation. These approaches together aim to speed up scientific code; they combine large-scale scientific computing with cutting-edge tools in computer science.

1 0

Lucy He will present her General Exam "The Hidden Risks of Benign Data: Generative AI’s Safety and Copyright Challenges" on Tuesday, April 15, 2025 at 10:30 AM in CS 302 and via zoom.
by CS Grad Department 14 Apr '25

14 Apr '25

Lucy He will present her General Exam "The Hidden Risks of Benign Data: Generative AI’s Safety and Copyright Challenges" on Tuesday, April 15, 2025 at 10:30 AM in CS 302 and via zoom. Zoom link: https://princeton.zoom.us/my/lucyhe Committee Members: Danqi Chen (co-advisor), Peter Henderson (co-advisor), Tom Griffiths Abstract: Large language models and text-to-image models can be vulnerable to seemingly harmless inputs, resulting in safety degradation or copyright risks. In the first part of the talk, I will discuss critical issues related to preserving the safety of open-weight models. I will describe a general approach to identify toxicity-promoting data. Using this approach, we find that superficially benign data, such as a collection of bullet lists and math, can be even more harmful than explicitly toxic text. In the second part of the talk, I will introduce our work examining copyright concerns in text-to-image models. We introduce an evaluation framework to evaluate both the model’s copyright compliance and consistency with user input. We then apply the framework to study how benign prompts trigger copyrighted character generation and the potential (in)effectiveness of current mitigation strategies. These works critically examine how benign data can compromise model safety and trigger copyright risks, shedding light on a better understanding and improvement of these systems for deployment. Reading List: https://docs.google.com/document/d/1JHuGtMwAplGjamaEB_v8RuBHUUrZRnxGeZwceUT… 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

Jiayi Geng will present her MSE thesis "Understanding the Failure Modes in Large Language Models"on 4/16 at 2pm in Friend 005.
by Gradinfo 14 Apr '25

14 Apr '25

Jiayi Geng will present her MSE thesis "Understanding the Failure Modes in Large Language Models"on 4/16 at 2pm in Friend 005. Date & Time: April 16th, 2:00–2:30 PM Location: Friend Center, Room 005 Thesis Title: Understanding the Failure Modes in Large Language Models Thesis advisors: Danqi Chen, Tom Griffiths Presentation Abstract: Using AI to create autonomous researchers has the potential to accelerate discovery. A prerequisite for this vision to become reality is assessing how well an AI model can identify the underlying structure of a system from its behavior. In this paper, we explore the question of whether a large language model (LLM) can learn from passive observations and actively collect informative data to refine its own hypotheses. To answer this question, we investigate the ability of LLMs to reverse-engineer four types of black-box systems, chosen to represent problems that might appear in different domains of research: list-mapping programs, formal languages, mathematical equations and board games. We use the Bayesian agents as a normative reference to study the gap between LLMs and ideal inference in reverse-engineering black-box systems. Through extensive experiments, we show that while LLMs have difficulty reverse-engineering these systems from observations alone, data generated by LLM-driven interventions can be effective. By testing edge cases, the LLM is able to refine its own hypotheses and avoid failure modes such as overcomplication, where the LLM falsely assumes prior knowledge about the black box, and overlooking, where the LLM fails to incorporate observations. These insights provide practical guidance for helping LLMs more effectively reverse-engineer black-box systems, supporting their use in making new discoveries.

1 0

Yaxin Tu will will present her General Exam "Separating Succinct Non-Interactive Arguments from Cryptographic Assumptions" on April 15, 2025 at 12pm in CS 401.
by Nicki Mahler 10 Apr '25

10 Apr '25

Yaxin Tu will will present her General Exam "Separating Succinct Non-Interactive Arguments from Cryptographic Assumptions" on April 15, 2025 at 12pm in CS 401. Committee: Alex Lombardi (adviser), Ran Raz(adviser), and Pravesh Kothari . Link to abstract and reading list: [ https://docs.google.com/document/d/1FmkljJIThGRgeHYmuChrSgzIas9uP2mUL41lulM… | https://docs.google.com/document/d/1FmkljJIThGRgeHYmuChrSgzIas9uP2mUL41lulM… ] Abstract: An argument system (computationally sound proof) for NP is succinct and non-interactive, if it contains a single prover-to-verifier message whose length is polylogarithmic the instance and witness sizes. In the past decade, the question of what cryptographic assumptions are sufficient and/or necessary for constructing SNARG, has received answers in both directions. On the one hand, the work of Gentry-Wichs’13 exhibits a barrier of using standard assumptions to construct SNARG, showing that efficient black-box reductions cannot prove the security of any SNARG construction based on any falsifiable cryptographic assumption. On the other hand, a recent line of work bypasses the Gentry-Wichs barrier by constructing SNARG based on iO and one-way functions, with a super-polynomial time security reduction. We prove an impossibility result that rules out black-box constructions of SNARG from polynomially-secure iO and one-way functions. Our result extends the Gentry-Wichs barrier, showing that there’s no black-box SNARG construction from even non-falsifiable assumptions like iO, with an efficient security reduction. Our result also shows that the super-polynomial time reduction is inherent for black-box constructions of SNARG from iO.

1 0

Simon Park will present his MSE talk “Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning” on Tuesday, April 15, 2025 at 12:00pm in Room 238, 41 William Street (AI Lab).
by CS Grad Department 10 Apr '25

10 Apr '25

Simon Park will present his MSE talk “Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning” on Tuesday, April 15, 2025 at 12:00pm in Room 238, 41 William Street (AI Lab). The members of his committee are as follows: Sanjeev Arora (Adviser) and Danqi Chen (reader) All ae welcome to attend. Please see abstract below. We introduce INSTRUCT-SKILLMIX, an automated approach for creating diverse, high quality SFT data for instruction-following. The pipeline involves two stages, each leveraging an existing powerful LLM: (1) Skill extraction: uses the LLM to extract core “skills” for instruction-following by directly prompting the model. This is inspired by “LLM metacognition” of (Didolkar et al., 2024); (2) Data generation: uses the powerful LLM to generate (instruction, response) data that exhibit a randomly chosen pair of these skills. Here, the use of random skill combinations promotes diversity and difficulty. The estimated cost of creating the dataset is under $600. Vanilla SFT (i.e., no PPO, DPO, or RL methods) on data generated from INSTRUCT-SKILLMIX leads to strong gains on instruction following benchmarks such as AlpacaEval 2.0, MT-Bench, and WildBench. With just 4K examples, LLaMA-3-8B-Base achieves 42.76% length-controlled win rate on AlpacaEval 2.0, a level similar to frontier models like Claude 3 Opus and LLaMA-3.1-405B-Instruct. Ablation studies also suggest plausible reasons for why creating open instruction-tuning datasets via naive crowd-sourcing has proved difficult. In our dataset, adding 20% low quality answers (“shirkers”) causes a noticeable degradation in performance. The INSTRUCT-SKILLMIX pipeline seems flexible and adaptable to other settings.

1 0