• Memolet: Reifying the Reuse of User-AI Conversational Memories 

  Yen, Hen Chen (University of Waterloo, 2024-06-19)

  As users engage more frequently with AI conversational agents, conversations may exceed their "memory" capacity, leading to failures in correctly leveraging certain memories for better responses. Therefore, users have to ...

• Improving the Precision of Analyses Queries in Factbase Models of Software Systems 

  Ke, Xiang Yun (Fa Fa) (University of Waterloo, 2024-05-31)

  Large software systems are developed by multiple teams of software engineers, each working on different components that are supposed to work together. Each component is responsible for a subset of system functionality and ...

• Reliable WiFi Backscatter Communication in WiTAG 

  Adhikari, Manoj (University of Waterloo, 2024-05-31)

  WiFi backscatter systems offer the potential to provide low-powered WiFi-compatible communication. This technology is especially promising when coupled with low-power sensors to periodically communicate readings from IoT ...

• Meta-Solving via Machine Learning for Automated Reasoning 

  SCOTT, JOSEPH (University of Waterloo, 2024-05-30)

  Automated reasoning (AR) and machine learning (ML) are two of the foundational pillars of artificial intelligence (AI) and yet have developed largely independently. The integration of these two sub-fields holds the tremendous ...

• Symbolic Regression and Sequence Modelling with Conditional and Dynamic Language Models 

  Valipour, Mojtaba (University of Waterloo, 2024-05-30)

  In an era where the boundaries of machine learning are continuously being pushed, this thesis presents two more advancements in the field of deep learning and artificial intelligence, with a focus on symbolic regression ...

• Parallel Transaction Execution in Public Blockchain Systems 

  Shahid, Rizwan (University of Waterloo, 2024-05-27)

  Public blockchain systems like Ethereum and Bitcoin suffer from poor transaction throughput, leading to delayed transaction execution and high transaction fees. They execute transactions one by one, failing to extract ...

• Writing My Own Line Drawing Software as an Artist 

  Philbrick, Greg (University of Waterloo, 2024-05-24)

  I describe trying to improve my own art—line art, specifically—by developing computer science-based tools. The results of this experience are three technical contributions targeted at an NPR (Non-Photorealistic Rendering) ...

• Deep Unsupervised Learning for Biodiversity Analyses: Representation learning and clustering of bacterial, mitochondrial, and barcode DNA sequences 

  Millan Arias, Pablo (University of Waterloo, 2024-05-22)

  Amid the recent surge in next-generation sequencing technologies, alignment-free algorithms stand out as a promising alternative to traditional alignment-based methods in phylogenetic analyses. Specifically, the use of ...

• Multivariate Triangular Quantile Maps for Novelty Detection 

  Wang, Jingjing (University of Waterloo, 2024-05-21)

  Novelty detection, a fundamental task in the field of machine learning, has drawn a lot of recent attention due to its wide-ranging applications and the rise of neural approaches. In this thesis, we present a general ...

• Navigating Identities in Text: Towards an Approach for Dementia Care 

  Gano, Jess (University of Waterloo, 2024-05-21)

  Identity, as a concept, is concerned with the social positioning of the self and the other. It manifests through discourse and interactions, and expressed in relation to other perceived identities. For example, can one be ...

• Variability in Factors Influencing Pull Request Merge Decisions: A Microscopic Exploration 

  Ahmed, Nasif (University of Waterloo, 2024-05-16)

  Context: The pull-based development model is a widely adopted practice in dis- tributed version control systems, particularly in open-source projects. In this model, con- tributors submit pull requests proposing changes ...

• Explore the In-context Learning Capability of Large Language Models 

  Li, Tianle (University of Waterloo, 2024-05-10)

  The rapid evolution of Large Language Models (LLMs) has marked the beginning of a new age in AI capabilities, particularly in the domain of natural language understanding and processing. Among the forefront of these ...

• Type-Aware Optimizations with Imperfect Types 

  Ikosin, Jeremiah (University of Waterloo, 2024-05-10)

  JavaScript, a programming language originally designed for web browsers, has become ubiquitous, experiencing adoption across multiple platforms. Its dynamic type system and prototype-based object orientation are well-known ...

• Classifying Code as Human Authored or GPT-4 Generated 

  Idialu, Oseremen Joy (University of Waterloo, 2024-05-09)

  Artificial intelligence (AI) assistants such as GitHub Copilot and ChatGPT, built on large language models like GPT-4, are revolutionizing how programming tasks are performed, raising questions about whether generative AI ...

• Size Constraints in Segmentation and Size Predictions 

  Fan, Xingye (University of Waterloo, 2024-05-08)

  Segment size, which one may equivalently refer to as volume, area, or cardinality, is uniquely defined by segmentation, e.g. by aggregating pixel-level predictions. On the other hand, size provides only a very weak constraint ...

• Explaining Expert Search and Team Formation Systems with ExES 

  Golzadeh, Kiarash (University of Waterloo, 2024-05-06)

  Expert search and team formation systems operate on collaboration networks with nodes representing individuals, labeled with their skills, and edges denoting collaboration relationships. Given a query corresponding to a ...

• Not All Pull Request Rejections Are The Same 

  Shamsolhodaei, Amirreza (University of Waterloo, 2024-05-06)

  In the Open Source Software (OSS) development landscape, evaluating pull requests extends beyond code quality assessment. Recent research has revealed the significant influence of social dynamics and perceptions on pull ...

• Laconic Evaluation of Branching Programs from the Diffie-Hellman Assumption 

  Murphy, Alice (University of Waterloo, 2024-05-02)

  Secure two-party computation (2PC) enables two parties to compute a function f on their joint inputs while keeping their inputs private. Laconic cryptography is a special type of 2PC in which this is done with asymptotically ...

• CAMEO: Explaining Consensus and Expertise Across MOdels 

  Yu, Andy (University of Waterloo, 2024-05-02)

  Explainable AI methods have been proposed to help interpret complex models, e.g., by assigning importance scores to model features or perturbing the features in a way that changes the prediction. These methods apply to one ...

• Ghost Recommendations: A Protocol for Efficiently Enhancing User Privacy 

  Iyer, Kritika (University of Waterloo, 2024-04-30)

  As the amount of online information accessible to users keeps increasing, we have come to rely more on services such as Netflix, Amazon, and eBay that are successful in recommending choices to users. The main goal of such ...

View more