small language model

FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model

This work proposes FrameLite, a compact cropping model built on Qwen3, which outperforms the compared large-VLM croppers across public benchmarks with a substantially smaller backbone and develops three-stage training to turn this potential into stronger direct predictions.

MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search

The Multi-Hypothesis Verification Framework (MHVF) is proposed for training-free GUI grounding that combines multi-hypothesis exploration with local visual verification using a single pretrained vision-language model.

RepProbe: Can Video Language Models Count Repeated Actions? A Diagnostic Benchmark

RepProbe, a benchmark of 42K real and synthetic video clips containing exactly k in [1, 20] complete repetitions, finds a consistent representation-to-output dissociation: substantial count information remains linearly decodable even when models fail to report the correct count.

A neuro-symbolic clinical decision support system for chronic pain management using structured derivation traces, adaptive compute, and knowledge graph constraint checking: comparison with 30 physicians from pain-relevant specialties

Chronic pain management requires complex multidisciplinary reasoning integrating pharmacological, interventional, rehabilitative, and psychosocial approaches across multiple guideline frameworks (International Association for the Study of Pain [IASP], American College of Rheumatology [ACR], European Alliance of Associa...

Authenticity and autonomy in EFL classrooms in Macao and Indonesia

Mark Feng Teng incorporates authentic materials into his academic writing classes in Macao to expose students to real-life language use and designs tasks to develop communicative skills. He structures lessons into three phases: teacher’s time, when he models academic skills that students will use later; learners’ time,...

Simulation-Based Training Tools for Cleft Lip Repair: A Systematic Review

Background: Simulation may supplement operative exposure in cleft lip surgery, but the strength and clinical relevance of evidence remain uncertain. This systematic review evaluated cleft lip repair simulators, focusing on characteristics, validity evidence, educational effectiveness, and implementation. Methods: PubMe...

Do LLM Proposers Improve Budgeted Search for Ionizable Lipids?

Efficient lipid design under limited experimental budgets is a central challenge in computational chemistry and drug discovery. We introduce LEAF (Lipid Evolutionary Adaptive Framework), a matched-budget protocol for testing whether language-model proposers improve combinatorial molecular search relative to classical b...

MiND: Minimal Deterministic Middleware for Auditable Large Language Model Interactions

Large language models (LLMs) are increasingly embedded in research software, yet many integrations preserve only the visible prompt and answer while losing structured evidence about configuration, provider metadata, timing, failures, and the exact request procedure. MiND is an open-source, provider-neutral middleware t...

Evidence-Grounded Contract Clause Classification with Small Language Models

Enhancing AI Interpretability Through Localised Architectures

Abstract Recent advances in generative AI, especially powerful Large Language Models (LLMs), raise concerns over the interpretability, safety and sustainability of these large and opaque AI models. The power of such architectures is derived not only from the scalability of deep neural networks (DNNs), but also massivel...

Editorial: Evolving health landscapes: the role of network governance in integrated care

In this Editorial, network governance is understood as a broad umbrella concept rather than a single institutional model. It refers to arrangements in which interdependent actors coordinate across organizational and sectoral boundaries through negotiation, trust, and shared rules, rather than through hierarchy or marke...

Family Socioeconomic Status and Child and Adolescent Developmental Outcomes: A Review and Meta-Analysis

Lower family socioeconomic status (SES) is widely linked to poorer child development, but the magnitude of the association varies across outcomes and samples. To synthesise correlational evidence on SES and externalizing/antisocial behaviour, internalizing/depressive symptoms, and language/literacy in children and adol...