BACKGROUND
Personalized meal planning by registered dietitian nutritionists (RDNs) is time-intensive. Large language models (LLMs) may automate drafting meal plans, but their nutritional accuracy in clinical practice is uncertain.
METHODS
In this proof-of-concept study, five outpatient RDNs and four LLMs (Gemini, CoPilot, ChatGPT 4.0, and customized ChatGPT 4.0) each generated 3-day meal plans for five validated clinical scenarios. Effectiveness was defined as accuracy in meeting pre-specified energy, protein, carbohydrate, fat, and sodium targets. Time to create plans and RDN comfort (self-rated confidence in nutritional accuracy and clinical appropriateness on 1-5 Likert scale) were recorded. Three independent RDNs, blinded to source, analyzed nutrient content using Nutritionist Pro. Group differences were assessed with t-test and ANOVA.
RESULTS
All LLMs and RDNs produced feasible meal plans. LLMs generated meal plans in under 1 min, whereas RDNs required a mean of 44 min per scenario. RDNs reported comfort levels ranging from 3.8 to 4.8. Across most scenarios, LLM plans delivered a smaller proportion of requested energy than RDN plans, which more consistently approached energy targets. Both groups performed similarly for the Mediterranean diet scenario. Overall, protein accuracy did not differ. However, in chronic kidney disease, LLMs undershot the guideline-based protein target, while RDNs tended to modestly exceed it. Accuracy for low-carbohydrate, fat, and sodium diets was comparable.
CONCLUSION
LLMs can rapidly generate clinically plausible meal plans but are less reliable than RDNs in achieving prescribed energy and selected macronutrient goals. Prompt precision is essential for nutrient-specific targets. A hybrid model in which RDNs refine LLM-generated drafts may leverage efficiency without sacrificing clinical accuracy.
M. Mundi, Osman Mohamed Elfadil, Danielle P. Johnson et al.· Nutrition in clinical practi...· 0 citations
This paper presents FlashAttention-V, a blocked FlashAttention for scalable vector architectures that adapts efficiently from short to very long vectors by exploiting parallelism across attention heads, inter-head packing to enable efficient utilization of vector lengths beyond the head dimension, and improving vector register utilization and memory access locality.
This paper introduces *TranslatePsy-AfriSLM*, a collection of open-source MT resources for 19 Sub-Saharan African languages, including curated parallel data, African-specialized synthetic data, and a family of fine-tuned SLMs.
Milan Gritta, Patrik Lambert, Jihye Back et al.· 0 citations
COSTA leverages the domain gap through proven test-time adaptation, and groups each batch of target-domain points into a small set of semantic clusters based on the similarity distribution in the adapted feature space, and propagates high-confidence pseudo labels obtained from an open-vocabulary vision-language model to all points through cluster-level voting.
Yanghong Lin, Li Fang, Tianyu Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The results suggest that bitsandbytes 4-bit quantization can impose an additional cost on applications relying on long, updatable, semantically dense contexts, even when aggregate benchmark accuracy appears largely unaffected.
Large Language Models show potential in their diagnostic accuracy and consequent ability to reduce clinician burden, and may provide the greatest benefit when used to optimise referral quality at source, improving both clinician and potentially LLM triage downstream.
K. Surendran, I. Aziz, Glyndwr Jenkins· Current Surgery Reports· 0 citations
The Institutional Newspapers Pipeline is presented, a modular system designed to extract high-quality, structured datasets from historical newspaper scans that was architected so that each step remains interpretable and customizable, and so that the pipeline as a whole remains computationally frugal enough to run on workstation-level hardware.
Matteo Cargnelutti, Catherine Brobston, Eben English et al.· 0 citations
The designs produced by Mise-en-Sc\`ene are the closest to the ground truth in perceived quality among all compared methods, by a wide margin over both an LLM layout planner and a specialized layout transformer, while the match-and-place stage bridges the remaining fidelity gap to the ground-truth composites.
Zipeng Xu, Ryan Murdock, Umberto Michieli· 0 citations
Small- and medium-sized enterprises (SMEs) increasingly need to reconfigure how they create, deliver, and capture value in response to digitalisation, sustainability demands, and environmental uncertainty. This study systematically reviews 162 English-language articles published in SSCI-indexed journals to integrate fragmented research on business model innovation (BMI) in SMEs. Descriptive analysis, keyword co-occurrence analysis, and article-level qualitative content analysis are combined. The findings identify four broad knowledge domains and show that 41 studies treat BMI primarily as an outcome, 44 as an organisational process, 17 as an antecedent of subsequent outcomes, and 36 as part of a combined causal relationship; a further 24 studies are descriptive or typological. Across these roles, the literature explains BMI through resource mobilisation, entrepreneurial action logics, absorptive and dynamic capabilities, experimentation, and network mobilisation. Its effects on performance, growth, resilience, internationalisation, and sustainability depend on complementary resources, implementation capabilities, stakeholder alignment, and environmental conditions. The evidence supports an adaptive and iterative interpretation of SME BMI, but direct evidence of recursive feedback remains limited. Resource constraints also have conditional effects, stimulating bricolage and focused experimentation in some circumstances while inhibiting substantive change when shortages become severe. The review provides an integrative synthesis specific to SMEs and advances digital business model innovation research by explaining how digital pressures are translated into changes in value proposition, value creation and delivery, and value capture through organisational and relational mechanisms.
Bi Zhang, Nurul Atasha Jamaludin, Shanshan Yue et al.· Future Business Journal· 0 citations
This survey presents a critical review of VLMs for egocentric video understanding, tracing the progression from conventional recognition architectures to multimodal foundation models and embodied systems, and examines how first-person perception and multimodal foundation models support wearable assistance, robot skill learning, human-to-robot transfer, and embodied decision making.
Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions. Patching, gradients, Hessian-vector products, and subset interventions provide different measurements under different access assumptions and may target different quantities. We formulate their shared measurement structure as mechanistic tomography: designed measurement for recovering internal mechanisms and intervention effects. For a chosen basis and intervention family, measurements take the form y = Ax + w, where A describes the interventions, x is the target map, and w contains nonlinear response, sampling error, and basis misspecification. This language gives a practical procedure: start with the least costly measurements, test on held-out interventions at the intended scale, calibrate simple mismatch, and expand the measurement family when structured residuals remain. Control provides a demanding validation setting because an estimate that guides an intervention acts as an observer. In a two-HMM model, control error rises with observer error, while target improvement can hide nuisance-state movement. Under forward-only access, sparse aggregate measurements recover a finite-effect map with fewer interventions than coordinate patching. With gradient access, finite probes improve a local attribution map. Lifted measurements and Hessian-vector products recover interactions missed by first-order maps, while Tracr shows that the required family depends on the basis. On GPT-2-small IOI, the Name Mover-Negative Name Mover interaction is the largest held-out predictive term among three tested cross-group pairs. On Qwen-2.5-7B, finite calibration makes an additive refusal-response map adequate, so held-out error does not support pairwise lifting.
The results show that referent selection and boundary precision are partially separable, with different components moving opposing regions of the IoU curve -- behavior a single threshold cannot reveal.
