‘Hacking’ Assistive Technology: Creating Personal AI Tools for Access

Algebraic Structure in Lattice Cryptography

An Empirical Exploration of Algorithmic Accountability

Minimal 3D Priors for Sparse View Reconstruction

The Critical Role of Consent in Digital Systems

Conversational Modeling for Healthcare Communication

Beyond Benchmarks: Human-Aligned Evaluation Frameworks for Large Language Models

Modeling Affect in Speech and Language in the Presence of Natural Inconsistency

Codes & Lattices: Computational Complexity and Constructions

Evaluating and Designing Defenses against Input Perturbation Attacks on Black-Box Machine-Learning Models

A Qualitative Exploration of Programming Instruction for Alternative Endpoints in Post-Secondary Computing Education

Measuring and Mitigating Adversarial Intermediaries on the Global Internet

Towards Scalable and Stable Machine Learning in Clinical Contexts: Addressing Computational Efficiency and Dataset Shift

Enhancing Security, Safety, and Reliability of Modern Cyber-physical Systems

Towards Generalist Vision-Language Models for Videos in Embodied AI

Towards Controllability, Efficiency, and Trustworthiness of Text Generation Systems

Efficiently Scaling Machine Learning Systems Across Heterogeneous Resources

Streamlining High-Performance Heterogeneous Hardware Design

Towards Having Personalized, Situated, and Grounded Conversations with Human Like Human

Domain-specific Benchmarks and Architectures for Applications using Graph-based Data

User-Centric Machine Learning Systems

Leveraging Priors of Generative Models

Usable and Ubiquitous Privacy-Aware Sensing Devices

Situated Language Grounding for Multimodal AI Assistant Modeling

Unfairness Detection and Evaluation in Data-driven Decision-making Algorithms