Skip to main content
Search

Macquarie University

4 related articles

Subscribe to updates
  1. arXiv

    Sparse Autoencoders Localize the Clinical Triage Format Effect: Medical Features Go Inactive at the Decision Token, Scaffold Features Account for Over 91% of Gemma Attribution

    Using sparse-autoencoder (SAE) features in Gemma 3 4B/12B IT and Qwen3-8B on clinical triage vignettes, this study finds that medical features fire on the shared clinical narrative under both formats but are inactive at the multiple-choice decision token; emergency-tier information is linearly decodable from vignette representations (ROC-AUC 0.95–1.00) with no significant format difference yet is attenuated at the decision token, and scaffold-peaking features account for over 91% of unsigned attribution in both Gemma models, placing the strongest correlates of the format effect at answer selection.

  2. arXiv

    REALM adds a delay prior and stochastic expression refinement to turn listening from a frozen stare into blinks and smiles on a robot

    REALM is a coarse-to-fine framework for audio-driven reactive listening that fuses listener motion history with speaker audio through a Reactive Gated Speaker–Listener Fusion module using a delay-centered attention prior and adaptive gating, then predicts a base motion trajectory with a coarse decoder and augments it with audio-conditioned stochastic residuals in the expression subspace, improving over the evaluated baselines on multiple motion-quality metrics on ViCo and L2L and deploying to an Ameca humanoid robot with a perceptual user study.

  3. arXiv

    TextCSP combines sub-region-aware prompts with soft cascade decoding to reach 87.0% average Dice and 4.81 mm HD95 on TextBraTS

    The work proposes TextCSP, a hierarchical text-guided brain tumor segmentation framework built on the TextBraTS baseline with three components: a text-modulated soft cascade decoder that predicts WT→TC→ET in a coarse-to-fine manner, sub-region-aware prompt tuning that uses learnable soft prompts with a LoRA-adapted BioBERT encoder to generate branch-specialized text representations, and text-semantic channel modulators that convert those representations into channel-wise refinement signals; on the TextBraTS dataset it reaches 87.0% average Dice and 4.81 mm average HD95, improving over the previous best TextBraTS by 1.7% and about 6% (0.32 mm) respectively, with consistent gains across all three sub-regions.

  4. Quality of Online Information for Management of Leg Pain in Children and Adolescents With Hypermobility-Associated Conditions

    Using the search terms 'management of lower limb pain in children with hypermobility-associated conditions', this study collated webpages from Google searches and the corresponding overviews presented by Gemini, assessed webpage quality with the Health Information Website Evaluation Tool and AI overview quality with the Quality Assessment of Medical Artificial Intelligence, and evaluating 20 webpages and four AI-generated overviews found that webpage quality was mostly moderate (14 moderate, three good) while all AI overviews were rated good, with accuracy the lowest-scoring domain for webpages and completeness and provision of resources and references the lowest-scoring domains for AI overviews.

You’re all caught up