Recently, artificial intelligence (AI) has become a potent and innovative branch of computer science that is rapidly transforming healthcare delivery across the world. With its promise of improved diagnostics, individualized care, and effective health service management, it has the potential to fundamentally change medical practice and healthcare delivery. Yet, despite its potential, AI’s growing influence […]
Recruitment strategies and participant motivations in a digital randomized controlled trial for the prevention of anxiety disorders: the prevANS study
BackgroundAnxiety disorders are among the most prevalent mental health problems worldwide, and access to effective treatment is not always available. Preventive interventions need to be scalable and cost-effective, which can be achieved through communication and information technologies. However, recruiting participants for digital prevention trials remains a major methodological challenge.AimTo evaluate the performance of different approaches […]
Beyond demographic tables: integrating data quality in clinical trial representativeness
IntroductionClinical trial representativeness is essential for ensuring that study findings generalise to target treatment populations. Current assessment approaches rely on subjective demographic comparisons that lack standardisation and fail to account for data quality. Existing data quality frameworks assess completeness at the dataset level as the availability of required data values but do not address cohort-specific […]
Barriers and facilitators to implementing an integrated electronic health records system to improve tuberculosis preventive treatment among people living with HIV: a content analysis study from Georgia
IntroductionThe integration of tuberculosis (TB) preventive treatment (TPT) into HIV services through electronic health records (EHR) can improve outcomes by enhancing care coordination, reducing redundancies, and supporting data-driven decision-making. In Georgia, despite close collaboration between TB and HIV programs, service delivery and data systems remain siloed, forcing patients to navigate between facilities and limiting the […]
A framework for culturally adapting mental mHealth apps
Mobile health (mHealth) apps are increasingly deployed for evidence-based mental health interventions, broadening access to care. While effective, Internet-based Cognitive Behavioural Therapy, delivered via web or app, frequently overlooks ethnic minority and migrant populations. Effective cultural adaptation of mHealth apps is critical to their impact and accessibility; however, existing frameworks often lack specific guidance for […]
Diabetic Retinopathy Classification using Downscaling Algorithms and Deep Learning
arXiv:2605.11430v1 Announce Type: cross Abstract: Diabetic Retinopathy (DR) is an art and science of recording and classifying the retinal images of a diabetic patient. DR classification deals with classifying retinal fundus image into five stages on the basis of severity of diabetes. One of the major issue faced while dealing with DR classification problem is […]
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
arXiv:2605.11235v1 Announce Type: cross Abstract: In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics or auxiliary models, risking misalignment with the policy’s training dynamics. In this paper, we introduce METIS (METacognitive Internalized Self-judgment), a novel framework that internalizes curriculum judgment as a native […]
Epistemic Uncertainty for Test-Time Discovery
arXiv:2605.11328v1 Announce Type: cross Abstract: Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which leads the policy to prioritize familiar patterns. As a result, the maximum reward plateaus even as the average reward increases. Overcoming this limitation requires a signal that distinguishes unexplored regions […]
ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
arXiv:2605.11048v1 Announce Type: cross Abstract: Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remain a significant challenge due to complex contact dynamics that demand high-precision force feedback and control. Although recent efforts have attempted to integrate force/torque sensing into policies, how to build a simple yet […]
Interpretability Can Be Actionable
arXiv:2605.11161v1 Announce Type: cross Abstract: Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impact, raising questions about its relevance and utility. This position paper argues that the central missing ingredient is not new methods, but evaluation […]
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
arXiv:2605.10983v1 Announce Type: cross Abstract: Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing visual mode collapse and amplifying unreliable rewards. We identify the root cause as the mode-seeking nature of these […]
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
arXiv:2605.11011v1 Announce Type: cross Abstract: Looped computation shows promise in improving the reasoning-oriented performance of LLMs by scaling test-time compute. However, existing approaches typically require either training recurrent models from scratch or applying disruptive retrofits, which involve substantial computational costs and may compromise pretrained capabilities. To address these limitations, we introduce textbfLooped Depth Up-Scaling (LoopUS), […]