small language model

Internalizer: Portable Context-to-Parameter Mapping for Very Large Language Models

Hypernetworks that map a context directly to a LoRA adapter let a large language model carry that context in its weights, but prior work has demonstrated them only on base models of up to 14 billion parameters. We present the Internalizer, a state-of-the-art, portable Context-to-Parameter Mapping hypernetwork that gene...

From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers

Chain-of-thought (CoT) reasoning often improves language-model performance by giving models additional computation before answering. However, explicit CoT expresses this computation as a sequence of autoregressively generated tokens. Latent reasoning replaces these tokens with compact continuous states, but most autore...

Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?

Small vision-language models may be able to read external evidence yet struggle to obtain it. We introduce Harness Compilation (HC), an offline procedure that adapts the division of work between a frozen small VLM and its external harness. A large teacher uses student execution traces to revise reusable content and con...

Learning How to Search for Plans with Exponentially Less Space

Heuristic search for a plan can store exponentially many states, even when its heuristic is almost perfect. We instead learn search control, one specification per domain, written as an indexical policy: a generalized policy with registers that hold objects and modes that sequence its rules. We add the choose rule, whic...

Doctors experiences of interruptions in UK secondary care outpatient clinics: a cross-sectional survey of prevalence, consequences and management strategies

Objectives To examine the prevalence of interruptions during UK secondary care outpatient consultations, their association with clinician mental workload, and the strategies clinicians use to manage them. Design Nationwide cross-sectional online survey. Setting Secondary care outpatient clinics, United Kingdom. Partici...

Integrating Regenerative Medicine and Stem Cell Therapy in Hearing Restoration: A Systematic Review

Hearing loss can adversely affect communication and language development and is associated with cognitive decline.Current treatments, including hearing aids and cochlear implants, can improve auditory function but do not regenerate damaged sensory cells.Stem-cell-based approaches have therefore attracted increasing int...

Making goals visible: A feasibility study of co-designed visual goal sheets to support parent implementation in early autism intervention

Background Translating individualized intervention goals into everyday family routines can be challenging. This mixed-methods feasibility study examined the use/adoption and parent-reported acceptability/social validity of visual goal sheets embedded within routine Early Start Denver Model (ESDM) care. Methods Ten fami...

Mitochondria-associated endoplasmic reticulum membranes in myocardial ischemia-reperfusion injury: integrating lipid metabolism and ferroptosis

Mitochondria-associated endoplasmic reticulum membranes (MAMs) are specialized contact structures between mitochondria and the endoplasmic reticulum, playing a significant role in maintaining cellular calcium homeostasis, lipid metabolism, mitochondrial dynamics, and the regulation of cell death. In recent years, numer...

Vision-Language Models for Gait-Based Screening via Zero-Shot and Multimodal In-Context Learning

RAC-LLM: retrieval-augmented large-small model collaboration for cloud-assisted web asset risk assessment and homologous discovery

Cloud-assisted cyber-asset monitoring services must continuously assess web assets that rapidly change domains, content, and page structure, making new variants difficult to evaluate and trace. Large language models can interpret heterogeneous and ambiguous security evidence, but their decisions benefit from bounded an...

Divergent Readability-Accuracy Strategies of Two Mistral and QWen Models in Biomedical Text Simplification

Preventing escalation in customer service: immediate motivation and 4-week outcomes in a workplace deployment of LLM role-play training

Many customer support employees encounter aggressive customer attitudes, including overt dissatisfaction, unreasonable demands, and verbal abuse. Such attitudes do not always stem solely from customers: inadequate employee responses can amplify dissatisfaction and escalate initially manageable issues, making skills tha...