• Scott, J. (CSE) – Mechanistic Specialization Does Not Guarantee Performance: Evidence from Dual AttentionTransformers

    Virtual Event

    Dual Attention Transformers (DATs) extend decoder-only Transformers with a dedicated relational-attention stream, making them a natural architecture for abstract identity rules such asABA and ABB. Surprisingly, we find that comparably sized GPT-2 models outperform DATs on these tasks. We investigate this gap with two complementary mechanistic analyses. First, causal mediation analysis shows that DATs exhibit […]

  • Kembay, A. (ECE) – Sparse and Continual Foundations for Adaptive General Intelligence

    Engineering 2 Engineering 2 1156 High Street, Santa Cruz, CA
    Hybrid Event

    While the human brain learns continually, mastering new tasks without forgetting the old and adapting to unfamiliar ones from context alone, modern neural networks still lack both. To bridge the gap between biological adaptivity and modern AI, we have established foundational work on sparsity as a computational principle at three levels of neural computation, through […]

  • Holmes, J. (CM) – Towards a Multi-dimensional Model of User Load

    Virtual Event

    Games user researchers (GURs) use various methods to understand when a game is overloading its players. In games research where data-driven multimodal approaches are necessary to drive insights, the currently available tools to measure user load are coarse, one-dimensional, and often aggregated. The more dominant instruments, such as the Cognitive Load Scale (CLS) and the […]

  • Li, J. (CM) – Detecting Failure to Adapt: Reading Self-Regulated Learning Breakdowns from Game Telemetry through Plan Recognition

    Virtual Event

    Three learners who fail the same level of an educational game the same number of times can be failing in three different ways, and the difference determines what each should do next. Yet the measures a game’s logs are usually reduced to (completion time, error counts, mastery estimates) render the three identical. This proposal takes […]