Background: The rapid expansion of rehabilitation needs in China has intensified pressure on a workforce that remains unevenly distributed. Digital health technologies (DHTs) offer potential to increase service reach and efficiency. However, little is known about how rehabilitation professionals currently gather and document clinical information, nor about their readiness to integrate digital tools into routine […]
Goal Setting and Anchoring Effects on Meditation Using a Digital Platform: Large-Scale Digital Field Study
Background: Meditation has grown in popularity in recent years, but many people who try meditation often fail to establish a habit. Goal setting has been demonstrated to be an effective technique in behavior change in other health-related contexts but is understudied in the meditation context. Objective: This study had 2 objectives: (1) to assess the […]
Innovations in Deaf Health Care Communication: Systematic Review of Sign Language Recognition Systems
Background: Deaf individuals often face communication challenges when interacting with those who can hear. Within health care settings, these challenges may pose risks to their safety, potentially resulting in misdiagnoses, treatment errors, and decreased quality of care. Objective: This study aims to systematically review the evidence on communication systems reported in the literature that use […]
Misinformation in Social Media Narratives on Highly Pathogenic Avian Influenza: Systematic Content Analysis of Facebook and Instagram Posts
Background: Recurrent outbreaks of the highly pathogenic avian influenza (HPAI) A (H5N1) virus in farmed poultry, and reports of infections in dairy cattle herds in the United States since March 2024, have triggered concerns about the spillover threat to human populations and a subsequent influenza pandemic. The increasing threat that H5N1 poses to human health […]
Digital Discourse, Secondary Victimization, and Psychological Harm: Mixed-Methods Analysis of System Justification in the #MeToo Movement
Background: The #MeToo movement, initiated in 2006 and amplified on social media in 2017, mobilized women worldwide to share experiences of sexual harassment and assault online. While the movement increased awareness, it also revealed deep social divisions in digital spaces. Supportive discussions promoted solidarity and healing, whereas antagonistic responses reinforced backlash and secondary victimization. In […]
Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
arXiv:2604.06871v1 Announce Type: cross Abstract: Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs. In this paper, we empirically revisit the necessity of such granular token-level processing. Through layer-wise oracle interventions, […]
Spectral Edge Dynamics Reveal Functional Modes of Learning
arXiv:2604.06256v1 Announce Type: cross Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions — the spectral edge — which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability tools (head attribution, activation probing, sparse autoencoders) fail to capture these directions: their structure is not localized in parameter […]
ClawLess: A Security Model of AI Agents
arXiv:2604.06284v1 Announce Type: cross Abstract: Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to regulate agent behavior through training or prompting, which does not offer fundamental security guarantees. We present ClawLess, […]
Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning
arXiv:2508.07299v2 Announce Type: replace-cross Abstract: The effectiveness of unlabeled data in Semi/Self-Supervised Learning (SSL) depends on appropriate assumptions for specific scenarios, thereby enabling the selection of beneficial unsupervised pretext tasks. However, existing research has paid limited attention to assumptions in SSL, resulting in practical situations where the compatibility between the unsupervised pretext tasks and the […]
LAsset: An LLM-assisted Security Asset Identification Framework for System-on-Chip (SoC) Verification
arXiv:2601.02624v2 Announce Type: replace-cross Abstract: The growing complexity of modern system-on-chip (SoC) and IP designs is making security assurance difficult day by day. One of the fundamental steps in the pre-silicon security verification of a hardware design is the identification of security assets, as it substantially influences downstream security verification tasks, such as threat modeling, […]
Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation Framework
arXiv:2601.22451v2 Announce Type: replace-cross Abstract: Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models generate descriptions of non-existent objects, compromising their reliability. Previous work attributes this to LVLMs’ over-reliance on language priors and attempts to mitigate it through logits calibration. However, they still lack […]
MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors
arXiv:2604.06846v1 Announce Type: cross Abstract: Interactive medical dialogue benchmarks have shown that LLM diagnostic accuracy degrades significantly when interacting with non-cooperative patients, yet existing approaches either apply adversarial behaviors without graded severity or case-specific grounding, or reduce patient non-cooperation to a single ungraded axis, and none analyze cross-dimension interactions. We introduce MedDialBench, a benchmark enabling […]