arXiv subjects

Zahra Kazemi

Publications and source records attributed to Zahra Kazemi.

6 recordsLinked to original sources

arXiv2026

Gaokerena: A Small Persian Medical Language Model Family

The integration of artificial intelligence into medical question-answering systems has advanced rapidly; however, research remains predominantly focused on English, leaving low resource languages like Persian significantly underserved. To address this gap, this paper introduces Gaokerena, a novel family of compact Persian medical language models optimized for deployment on consumer grade hardware. As a foundational step toward localized digital healthcare, we first present Gaokerena-V, developed by training a baseline model on a newly curated 90-million-token Persian medical corpus and 20,000 expert-vetted physician Q&A pairs, which improved performance on a translated medical MMLU benchmark from 46.28% to 49.31%. Second, recognizing the critical demands of clinical reasoning, we developed Gaokerena-R by integrating a Chain-of-Thought approach with two novel Reinforcement Learning with AI Feedback (RLAIF) frameworks to optimize preference-based reasoning. Despite utilizing the same baseline architecture and a smaller dataset than Gaokerena-V, Gaokerena-R achieved a superior benchmark score of 52.98%. Furthermore, both models are equipped with custom-developed uncertainty heads that predict the model's confidence in its responses based solely on internal hidden states. While these results demonstrate significant progress in Persian medical language modeling and proactive safety estimation, current performance levels remain insufficient for direct clinical application, highlighting the necessity for further research into robust knowledge acquisition and rigorous safety verification prior to real world deployment.

cs.CL↗

arXiv2026

Bipolar plates for the next generation of proton exchange membrane fuel cells (PEMFCs): A review of the latest processing methods for unconventional flow channels

The rapid, unsustainable depletion of finite fossil fuel resources and their environmental consequences demand the deployment of affordable clean and sustainable energy solutions. Polymer electrolyte membrane fuel cell (PEMFC) technology is an important pathway in decarbonization of modern energy systems, especially when fueled by high-purity green hydrogen. In PEMFCs, bipolar plates largely determine cell efficiency, longevity, and affordability, which in turn depends on both material selection and design of the embedded flow channels. Conventional manufacturing processes have long been used to fabricate standard bipolar plate designs; however, they are incompatible with unconventional, intricate geometries due to their insufficient resolution and precision in fabrication of fine features, and reliance on multi-step post-processing modifications that limit their design adaptability. This lack of design flexibility impedes the translation of innovative laboratory-scale concepts to industrial-scale production and their practical adoption. In recent years, a growing body of research publications and patent disclosures has reported advanced manufacturing methods, such as additive manufacturing, capable of producing intricate bipolar plate geometries at competitive costs. However, a discussion of these manufacturing approaches, along with an assessment of their scalability and industrial readiness, remains absent in the literature. This study aims to fill this gap. It outlines recent progress and proposes future research directions toward affordable and efficient bipolar plate solutions for advanced PEMFC systems.

cond-mat.mtrl-sci↗

arXiv2025

Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model

The rapid advancement of language models has demonstrated the potential of artificial intelligence in the healthcare industry. However, small language models struggle with specialized domains in low-resource languages like Persian. While numerous medical-domain websites exist in Persian, no curated dataset or corpus has been available making ours the first of its kind. This study introduces a newly curated dataset comprising 20k doctor-patient Q\&A pairs and 60\% of a 90-million-token crawled corpus from medical magazines. Using a parameter-efficient fine-tuning approach, we enhanced the medical knowledge of the baseline model, aya-expanse-8b. Benchmark evaluations demonstrate that the fine-tuned model achieves improved accuracy in medical question answering and successfully passed the Iranian Basic Medical Science Entrance Exam (IBSEE) in September 2023, which the baseline model did not. Additionally, the fine-tuned model improved Persian-translated MMLU accuracy by an average of 2.67\%. This work highlights the potential of leveraging open-access online data to enrich small language models in medical fields, providing a novel solution for Persian medical AI applications suitable for resource-constrained environments. Future research could explore multimodal input to further enhance performance.

cs.CL↗

arXiv2025

Topology optimization of cathode gas channel layout in advanced proton exchange membrane fuel cells

The proton exchange membrane fuel cell (PEMFC) output relies on the transport behavior within the cathode gas channels. Current designs remain inadequate as they often rely on heuristic modifications of existing layouts or designer intuition with suboptimal performance. In this study, topology optimization is proposed to redesign the PEMFC cathode gas channel layout without a priori assumptions. The optimization aims to maximize the reactant concentration and minimize power dissipation along the flow path. The problem is solved within a three-dimensional half-cell model. For computational tractability, a reduced-order, depth-averaged two-dimensional model is also implemented. The optimized topology yields an enhanced current density with lower energy dissipation over the conventional benchmarks. At an inlet velocity of 0.15 m/s, the pressure drop is reduced by 46.7% compared to the serpentine layout, though is 28.2% higher than that of the parallel case. Within the optimized channels, oxygen flows at higher local velocities, which allows a more homogeneous reactant delivery across the domain. Relative to the serpentine layout, the improvement in mean current density reaches 20.9% with 4.9% lower standard deviation. Placing more emphasis on dissipation minimization during optimization produces more intricate, tortuous channel topologies. Such design flexibility enables the discovery of unconventional yet efficient layouts.

physics.comp-ph↗

arXiv2024

Machine learning for characterizing uncertain elastic properties of fused filament fabricated materials for topology optimization applications

The layering approach used in fused filament fabrication (FFF) enables creation of complex designs generated by topology optimization. Defects associated with the layer-by-layer process, introduce considerable random variability to the local elastic modulus of the print. The elastic modulus along the fusion layers connecting bulk materials differs from that of the bulk areas. Accurate quantitative measurements of variations in both areas are essential to achieve robust optimized designs. This study aims to quantify the parameters of the random distributions given the surface strain field of the print measured by digital image correlation (DIC). Two statistical properties, mean and standard deviation, are sufficient to characterize the stochastic elastic modulus fields in each region. An efficient neural network model is developed to estimate spatial variations in the local elastic modulus within both bulk and fusion layers. This model is trained on a dataset of synthetic strain fields with known distributions in the elastic modulus fields. It performs well in correlating the elastic modulus with the input strain, as long as the standard deviation is below 60% of the mean of the random field. The predictive accuracy of the model on testing data, measured by the R2 score, is 0.99 and 0.95 for mean and standard deviation in the fusion material. The scores for the bulk material are 0.97 each. The trained model is implemented to predict the elastic modulus distribution of an FFF-printed material at a print speed of 30 mm/s and an extrusion temperature of 493.15 K, based on its DIC-measured surface strain data. The model predicts a mean and standard deviation of 1.2 GPa and 1 GPa for the bulk material and 400 MPa and 430 MPa for the fusion region. Validation of predictions confirms the reliability of this approach in measuring uncertainty in the local properties of the prints.

cond-mat.mtrl-sci↗

arXiv2024

A Comprehensive Review of Lunar-based Manufacturing and Construction

As humankind prepares to establish outposts and infrastructure on the Moon, the ability to manufacture parts and buildings on-site is crucial. While transporting raw materials from Earth can be costly and time-consuming, in-situ resource utilization (ISRU) presents an attractive alternative. This review paper aims to provide a thorough examination of the current state and future potential of Lunar-based manufacturing and construction (LBMC), with a particular focus on the prospect of utilizing in-situ resources and additive manufacturing. The paper analyzes existing research on LBMC from various perspectives, including different manufacturing techniques and compositions, the potential of ISRU for LBMC, characterization of built parts and structures, the role of energy sources and efficiency, the impact of low-gravity and vacuum conditions, and the feasibility of using artificial intelligence, automation, and robotics. By synthesizing these findings, this review offers valuable insights into the challenges and opportunities that lie ahead for LBMC.

astro-ph.IM↗