The use of synthetic datasets for computer vision is a key factor in the improvement of many methods. Infinigen is a procedural generator of synthetic 3D scenes of the natural world with the goal of creating datasets for computer vision research. One such area of research is Visual SLAM models, which seek to map an unknown environment while simultaneously tracking an agent’s pose. I propose a Visual SLAM benchmark based on Infinigen as well as an open-source method to generate more data for SLAM algorithms using Infinigen. The Infinigen SLAM benchmark contains extremely challenging camera motion within various indoor environments. State-of-the-art Visual SLAM models perform well on the proposed benchmark, however they perform worse than on comparable SLAM benchmarks. This suggests that Infinigen is capable of producing useful data for future SLAM research.

This thesis presents a user friendly approach to information driven antibody-antigen folding and docking.

This study uses natural language processing (NLP) techniques to analyze the syntactic and lexical differences between Standard French and Cameroonian French, as well as examine how the dialect evolves when used by the Cameroonian diaspora in France. The central methodology involves training and evaluating two distinct NLP models: one fine-tuned on a corpus of Standard French, and the other on Cameroonian French. The LSTM model, on the other hand, outperformed the Logistic Regression model in all key metrics, including accuracy, precision, recall, and F1-score. The results of this study illustrate the limitations of traditional NLP methods, such as logistic regression, when applied to dialects with syntactical and linguistic differences, and they highlight the potential of deep learning approaches to better handle these variations. The findings point to the importance of fostering linguistic diversity within computational models.

The residential building sector is a major contributor to energy consumption and greenhouse gas emissions, making electrification and intelligent energy management essential for decarbonization. However, increased electricity demand can strain the power grid, leading to higher costs and emissions. Demand-side flexibility, enabled by on-site power generation, energy storage, and optimized control algorithms, can mitigate this problem by shifting electricity consumption to times when electricity is cheaper and cleaner.

This study evaluates three methods for centralized building energy storage management using CityLearn, an open-source environment for simulating and benchmarking building energy control. The evaluation compares Model Predictive Control (MPC) with two Reinforcement Learning (RL) methods: Soft Actor-Critic (SAC) and Proximal Policy Optimization (PPO). The methods are assessed across three dimensions: (1) energy performance, including cost, carbon emissions, electricity consumption, and stability of electricity use over time; (2) computational efficiency, including training time, memory usage, and inference speed; and (3) scalability, measured across different district sizes of two, four, and eight buildings.

Overall, SAC achieved the strongest performance on cost and energy metrics, performing slightly better than PPO in those areas. PPO, however, produced smoother control behavior with more stable electricity use over time while requiring significantly less memory than SAC and less computation than MPC. Both RL methods outperformed MPC across most metrics, with MPC particularly struggling to scale. Nonetheless, MPC remained more interpretable and required no training data, though it involved substantial engineering effort to develop an accurate system model.

These findings highlight trade-offs between performance, stability, and deployability. PPO emerged as the most balanced controller, offering strong performance with scalability and computational efficiency, making it well-suited for real-world use.

Sleep has a profound impact on numerous cognitive functions, including decision-making and self-control. However, the precise mechanisms by which sleep influences these processes are not completely understood. This study explored how sleep loss impacts the weighting of short-term and long-term rewards, and thereby influences the decision-making process. Participants self-reported their sleep on the previous night and participated in a decision-making experiment involving 25 choices between pairs of food items, where the taste value of each food item represented short-term reward and the health value of the food represented long-term reward. I hypothesized that participants who slept less would exhibit less self-control and thus would place a lesser weight on health relative to taste; further, I hypothesized that self-control would deplete as trials progress.

I developed four nested computational models to characterize the decision-making process: a baseline model that assumes equal weights for taste and health, a model that fits a health weighting parameter for each participant, and two models that incorporate a linear or exponential decay parameter to simulate potential self-control depletion across trials. The model that fit a βhealth weight for each participant provided the best fit for the data, suggesting that participants vary in how they weigh taste versus health and that this weighting was relatively stable across trials. This study did not find a significant correlation between βhealth and sleep hours under any of the models. While the results did not align with my hypotheses, this may be due to a small sample size, limited variability in sleep duration, computational constraints, and other factors. Further research is needed to better explore this relationship, potentially with more extreme manipulations of sleep or the consideration of additional factors that may influence intertemporal choice.

This thesis provides a new resource for squash performance analysis by developing a computer vision system that integrates advanced object detection and tracking techniques. By stringing together YOLOv8 for precise player detection and StrongSORT for multi-object tracking, the system accurately processes game footage to collect player data. A tool developed in this project is a user-assisted manual court mapping interface corrects perspective distortions, providing the resource to generate movement based analytics that reflect on-court dynamics, such as control of the critical ’T’ position. The adaptability of the technologies used create the opportunity for the expansion of this project. Further development of this project offers valuable insight for coaching and performance improvement, and further refinements are expected to enhance the accuracy of detection and tracking even further.

Modern audio time-compression algorithms generally follow a uniform approach to speedup. Given a particular playback rate, these algorithms decrease the number of audio samples played evenly throughout the entire clip and use a variety of techniques to control the pitch so that it remains constant. This is generally e!ective until higher speeds, past which the quality of the audio degrades to a point of lacking comprehensibility to the listener. However, by designing an algorithm that analyzes the frequencies in each audio sample and removes them strategically according to their perceived importance, it is theoretically possible to preserve the intelligibility of an audio file better even at higher playback rates. This unlocks potentially higher speeds for listener comprehension and improves the listening experience at standard playback rates. This algorithm, called CATCA (Content-Aware Time Compression for Audio), is built on a content-aware approach, which assigns energies to audio samples and removes them in priority of lowest energy. While this new time-compression algorithm did not achieve intelligibility improvements over the state-of-the-art method PSOLA, it still performed better than other algorithm variations, demonstrating the utility of content-awareness as an audio time-compression approach approach given future improvements.

What is the difference between and and but? In many sentences, they can be freely interchanged—consider that both ”the weather is sunny and cold” and ”the weather is sunny but cold” are true if and only if the weather is sunny and the weather is cold. What then causes speakers to chose and over but and vice versa? To that end, I gather data from the Corpus of Contemporary American English and investigate properties of the distributions of the two conjunctions. I find that and is more unmarked and neutral, while but is more likely to appear when greater contrasts exist between the two conjuncts themselves, or more broadly in more salient contexts. Along the way, novel analyses for the underlying syntactic structure of certain uses of but are proposed.

This project proposes an automated end-to-end pipeline that transforms Journey to the West into a game-style visualization. Leveraging generative AI models for both text and image, the pipeline extracts structured data from the original narrative and converts it into consistent, stylized visual assets. These components are then integrated within an interactive interface to visualize the story. By fully automating the process, the project lowers the barrier to entry for new forms of engagement with classical literature, while also exploring the limits of prompt engineering and highlighting both the creative potential and structural challenges of using AI to reinterpret complex literary works.

The card game Hearts is a stochastic, sequential, non-zero sum, 4-player, partial information game. Such qualities of the game prevent standard game algorithms from finding optimal play in reasonable time. The Monte-Carlo tree search partially addresses this issue by offering an approximation of the payoff resulting from optimal play, so that every potential move in the game does not have to be searched for an action’s value to be evaluated. However, a standard Monte-Carlo tree search does not address imperfect information, stochastic, or N-Player games. My approach aims to close this gap by integrating other algorithms such as maxn [2] and Monte-Carlo sampling [3] to address these aspects of the game that Monte-Carlo tree search does not. The combination of these techniques results in a Hearts engine that is able to beat many base-level algorithms, existing Hearts engines, and advanced human Hearts players.

We construct a system for representing graphemes as strings, from which the original grapheme may be reconstructed in its entirety. The utility of the system in representing scripts accurately is demonstrated with the analysis of select graphemes from various scripts. From this annotation, we offer various measures of script complexity and distance. We annotate various writing systems and analyze their script complexities, and compare the performance of various metrics at formalizing the notion of script affinity. Having found statistically significant results in the task of graphemic classification, we conclude that the theory proposed here meaningfully captures information about writing systems.

The shift towards personalized content consumption in social media has driven the rise of black-box algorithms which are foundational in delivering tailored experiences. These algorithms do an incredible job at delivering tailored experiences without much effort from the user, however often utilize intrusive methods such as location, watch time, and scrolling behavior. At the same time, alternative social networks have emerged with an added emphasis on decentralization, transparency, and privacy. However, a significant gap remains in this space: the absence of alternative social media applications that provide users with feed curation tools, make these tools accessible to all end-users, and unify fragmented user communities across diverse networks. This paper introduces Pantry, a social media reader application designed to address this gap through the idea of teachable feeds, inspired by existing literature, and powered by an on-device machine learning model. Evaluation through a user study reveals that Pantry succeeds in delivering feed curation tools driven by users and provide several key insights. The results of this paper, from the user study, help inform and advance the future design space.

As AI systems become more prominent in decision-making for domains such as employment and advertising, ensuring fairness in these models is increasingly important. In this work, we design a black-box, risk-limiting audit framework for assessing fairness with the four-fifths rule. Inspired by election auditing techniques and sequential hypothesis testing, we propose two-group and multi-group algorithms that maintain risk-limiting guarantees and stop early for innocent models. Unlike fixed-sample methods, our approach evaluates fairness while continuously sampling, allowing auditors to repeatedly request more data when needed. We demonstrate the effectiveness of our algorithms through empirical evaluations on real-world employment datasets collected for New York City's Local Law 144. The audits detect fairness violations correctly 100% of the time and verify fairness after sampling on average 66% of the data in the multi-group setting. Our approach enables third-party auditors to efficiently and confidently evaluate fairness claims, even in settings with limited transparency.

Whether it’s with our closest BFFs or long-distance lovers, texting has become an integral part of how we communicate with each other in the 21st century. As it becomes an increasingly powerful substitute for chatting in real life, it also begins to naturally develop advanced mechanisms for communicating nuances that have not previously existed in standard writing systems. Discourse particles like lol, lmao, and emojis don’t just fill space — they are a modern way to convey the subtleties of body language, facial expression, and tone. In this paper, we evaluate a corpus of about 200,000 real text messages from one speaker and investigate the typology, pragmatics, and modifiers of these particles. By connecting these phenomena to existing linguistic theories of discourse particles, variation, and digital communication, we explore how texting language has evolved to fit the fast-paced, screen-based communication we engage in every day, becoming a de- tailed, blossoming structured system of its own that is a fruitful field for extensive exploration.

This project aims to build a predictive model that effectively ranks the winners of the Grammys, a prestigious music award. The project takes a data-driven approach to analyze the factors influencing Grammy recognition, focusing on both commercial success and artistic merit. By integrating data from sources such as Spotify audio features, Billboard chart performance, and Genius lyrics, the model aims to predict Grammy winners in three major categories: Song of the Year, Record of the Year, and Best Rap Song. The results show that a hybrid approach, using both a global model and category-specific models, offers the best performance by capturing both broad trends and category-specific nuances. Although the model demonstrates strong predictive capability, the project highlights areas for improvement, including the need for additional features such as genre, record label information, and artist social media engagement. Future work will focus on expanding the dataset, incorporating Grammy history, and refining the model to provide even more accurate predictions, moving us closer to understanding the factors that drive Grammy success.

Automated video editing has the potential to streamline content creation by intelligently selecting and synchronizing video clips with music. This project presents a video editing assistant that takes raw footage as input, analyzes its visual content using histogram-based scene segmentation, and applies K-Means clustering to identify the most representative clips. The system then aligns selected clips with predefined music segments, ensuring a structured and rhythmically cohesive final edit. By assuming that beat detection is handled externally, the system focuses on optimizing clip selection and sequencing, providing an efficient and adaptable approach to music-driven video editing. This research intends to contribute to the field of automated media production by enhancing creative workflow efficiency while maintaining user control over the editing process.

Despite growing awareness of potential discrimination in ad delivery, Google's ad delivery optimization has received limited attention. While researchers have hypothesized that platform-driven decisions in Google-served advertising can lead to discriminatory outcomes, no current methodologies isolate the impact of Google's algorithms in skewing delivery. To address this gap, we evaluate Google's Display Network (GDN) from both an advertiser’s and a third-party auditor’s perspective. Understanding the feasibility of diverse outreach as an advertiser and feasibility of detection of algorithmic bias in delivery are critical, especially in employment advertising, where fairness concerns have both legal and societal implications. We begin by detailing the functionality for creating ads, targeting audiences, and analyzing delivery on GDN. We then develop a novel framework that can assess gender-based skew in Google's Display Network through 61 experiments. We find that ad placements—defined as the websites and apps where ads appear—have the most prominent impact on the breakdown of demographics in delivery, consistently resulting in a delivery to an audience of 63% male users when shown on the entire GDN, and a more balanced audience of 50% of male users when shown only on YouTube's website. Importantly, the typical advertiser trying to reach a balanced audience may not be aware of the potential for such gender skew in the default placement option on GDN and may not have the tools or budget to identify ad placements that would lead to more balanced outreach. Finally, when varying ad images by implied gender, we observe no consistent delivery trends; further research is needed to understand the role of ad creatives in shaping delivery outcomes.

This paper explores generative AI-based agents for autonomous, personalized content recommendations, utilizing state-of-the-art software for high-performance custom workflows, high-dimensional vector storage and searching, language-based tasks, and autonomous 24/7 running capabilities. Using unstructured, unseen, real-time data from YouTube, we utilize large language models to quantitatively handle subjective tasks and evaluate the outcomes. In essence, we created a recommendation system that uses artificial intelligence to autonomously find content and reduce the time spent on manual search. Content recommendation is a prominent problem in the industry, and we find that the performance of our system is satisfactory, and the scope of such systems is substantial. If used in correlation with default recommendation systems, the system can provide an improved interactive recommendation experience.

This paper delves into the audio and lyrical features of popular music in the 21st century, primarily focusing on hit songs in the United States that charted on the Billboard Hot 100. Historical Billboard Hot 100 charts, lyric data from Genius Lyrics, and Spotify audio feature are the three primary datasets that construct a snapshot of contemporary popular music. Exploratory data analysis and clustering techniques highlight changes and continuities within the data, while latent Dirichlet allocation (LDA) is utilized to discover the thematic topics of hit and non-hit music. The overarching goal is to classify songs as hits and non-hits based on their underlying audio and lyrical features. To achieve this, a support vector machine model (SVM) is trained and optimized. The SVM achieves an accuracy rate of 82%, mirroring the successes of other papers in the field, while adding a new dimension to the data. Beyond the core features of the project, this paper contributes to the field of hit song science (HSS) and offers a new framework to study Billboard Hot 100 hits.

Predicting the outcome of sports games is a big and exciting problem. Sports analytics is constantly evolving and finding better ways to understand and break down a sport. Basketball, being a dynamic sport, has tremendous avenues for analysis and predictive modeling. Previously, most approaches have either used rudimentary and descriptive data or built expensive and complex models. This thesis leverages dynamic and complementary feature engineering to model matchup-specific strengths and weaknesses between competing teams. Key methodological innovations include the use of rolling averages to capture temporal trends, complementary metrics (offensive vs. defensive efficiencies, rebounding differential) to account for interactions, and era-based segmentation to analyze the evolution of feature importance across basketball history. Logistic regression with L1 regularization was employed, achieving an impressive 70% prediction accuracy—a significant improvement over other models—and uncovering interpretable insights into feature contributions. The most accurate model was trained on 40 seasons (35,000 games) of NBA data from 1985-2023.