Verbal autopsy (VA) is a critical tool for estimating causes of death in resource-limited settings where medical certification is unavailable. This study presents LA-VA, a proof-of-concept pipeline that combines Large Language Models (LLMs) with traditional algorithmic approaches and embedding-based classification for improved cause-of-death prediction. Using the Population Health Metrics Research Consortium (PHMRC) dataset across three age categories (Adult: 7,580; Child: 1,960; Neonate: 2,438), we evaluate multiple approaches: GPT-5 predictions, LCVA baseline, text embed-dings, and meta-learner ensembles. Our results demonstrate that GPT-5 achieves the highest individual performance with average test site accuracies of 48.6% (Adult), 50.5% (Child), and 53.5% (Neonate), outperforming traditional statistical machine learning baselines by 5-10%. Our findings suggest that simple off-the-shelf LLM-assisted approaches could substantially improve verbal autopsy accuracy, with important implications for global health surveillance in low-resource settings.

Biomechanical forward simulation holds great potential for HCI, enabling the generation of human-like movements in interactive tasks. However, training biomechanical models with reinforcement learning is challenging, particularly for precise and dexterous movements like those required for touchscreen interactions on mobile devices. Current approaches are limited in their interaction fidelity, require restricting the underlying biomechanical model to reduce complexity, and do not generalize well. In this work, we propose practical improvements to training routines that reduce training time, increase interaction fidelity beyond existing methods, and enable the use of more complex biomechanical models. Using a touchscreen pointing task, we demonstrate that curriculum learning, action masking, more complex network configurations, and simple adjustments to the simulation environment can significantly improve the agent's ability to learn accurate touch behavior. Our work provides HCI researchers with practical tips and training routines for developing better biomechanical models of human-like interaction fidelity.

Learning rate (LR) schedules in large language model (LLM) training often follow empirical templates: warm-up, constant plateau/stable phase, and decay (WSD). However, the mechanistic explanation for this strategy remains underexplored, and the choice of plateau height and decay schedule is largely heuristic. In this paper, we connect training dynamics to a thermodynamic analogy via the Mpemba effect - a phenomenon in which a hotter system cools faster than a colder one when quenched into the same bath. We analyze a class of "valley-river" loss landscapes, where sharp (valley) directions equilibrate quickly, while flatter (river) directions govern global descent. The Mpemba effect provides an explanation for the necessity of the warm-up phase and motivates a high plateau - rather than a low one - for accelerating loss decrease during decay. We show that for certain loss landscapes, there exists an optimal plateau learning rate - the "strong Mpemba point" - at which the slowest mode vanishes, resulting in faster convergence during the decay phase. We derive analytical conditions for its existence and estimate decay dynamics required to preserve the Mpemba advantage. Our minimal model and analysis offer a principled justification for plateau-based schedulers and provide guidance for tuning LR in LLMs with minimal hyperparameter sweep.

In regions lacking medically certified causes of death, verbal autopsy (VA) is a critical and widely used tool to ascertain the cause of death through interviews with caregivers. Data collected by VAs are often analyzed using probabilistic algorithms. The performance of these algorithms often degrades due to distributional shift across populations. Most existing VA algorithms rely on centralized training, requiring full access to training data for joint modeling. This is often infeasible due to privacy and logistical constraints. In this paper, we propose a novel Bayesian Federated Learning (BFL) framework that avoids data sharing across multiple training sources. Our method enables reliable individual-level cause-of-death classification and population-level quantification of cause-specific mortality fractions (CSMFs), in a target domain with limited or no local labeled data. The proposed framework is modular, computationally efficient, and compatible with a wide range of existing VA algorithms as candidate models, facilitating flexible deployment in real-world mortality surveillance systems. We validate the performance of BFL through extensive experiments on two real-world VA datasets under varying levels of distribution shift. Our results show that BFL significantly outperforms the base models built on a single domain and achieves comparable or better performance compared to joint modeling.

As part of the Open Language Data Initiative shared tasks, we have expanded the FLORES+ evaluation set to include Emakhuwa, a low-resource language widely spoken in Mozambique. We translated the dev and devtest sets from Portuguese into Emakhuwa, and we detail the translation process and quality assurance measures used. Our methodology involved various quality checks, including post-editing and adequacy assessments. The resulting datasets consist of multiple reference sentences for each source. We present baseline results from training a Neural Machine Translation system and fine-tuning existing multilingual translation models. Our findings suggest that spelling inconsistencies remain a challenge in Emakhuwa. Additionally, the baseline models underperformed on this evaluation set, underscoring the necessity for further research to enhance machine translation quality for Emakhuwa. The data is publicly available at https://huggingface.co/datasets/LIACC/Emakhuwa-FLORES.

In settings where most deaths occur outside the healthcare system, verbal autopsies (VAs) are a common tool to monitor trends in causes of death (COD). VAs are interviews with a surviving caregiver or relative that are used to predict the decedent's COD. Turning VAs into actionable insights for researchers and policymakers requires two steps (i) predicting likely COD using the VA interview and (ii) performing inference with predicted CODs (e.g. modeling the breakdown of causes by demographic factors using a sample of deaths). In this paper, we develop a method for valid inference using outcomes (in our case COD) predicted from free-form text using state-of-the-art NLP techniques. This method, which we call multiPPI++, extends recent work in "prediction-powered inference" to multinomial classification. We leverage a suite of NLP techniques for COD prediction and, through empirical analysis of VA data, demonstrate the effectiveness of our approach in handling transportability issues. multiPPI++ recovers ground truth estimates, regardless of which NLP model produced predictions and regardless of whether they were produced by a more accurate predictor like GPT-4-32k or a less accurate predictor like KNN. Our findings demonstrate the practical importance of inference correction for public health decision-making and suggests that if inference tasks are the end goal, having a small amount of contextually relevant, high quality labeled data is essential regardless of the NLP algorithm.

On this episode of the eeDesignIt Podcast, we're joined by Dhonam Pemba to explore artificial intelligence (AI) and his new company KidX AI. Dhonam is a neural engineer by PhD, a former rocket scientist and a serial AI entrepreneur. He was CTO of the exited company, Kadho which was acquired by Roybi for its Voice AI technology. At Kadho Sports he was their Chief Scientist which had clients in MLB, USA Volleyball, NFL, NHL, NBA, and NCAA. His latest company, KidX, is in the AI edtech space, where he has built NLP and Voice assessment to serve China's leading robotics company with 4M users.

For our latest expert interview on our blog, we've welcomed Dhonam Pemba to share his thoughts on the topic of artificial intelligence (AI) and his journey behind founding KidX AI. Dhonam is a neural engineer by PhD, a former rocket scientist and a serial AI entrepreneur with one exit. He was CTO of the exited company, Kadho which was acquired by Roybi for its Voice AI technology. At Kadho Sports he was their Chief Scientist which had clients in MLB, USA Volleyball, NFL, NHL, NBA, and NCAA. His latest company, KidX, is in the AI edtech space, where he has built NLP and Voice assessment to serve China's leading robotics company with 4M users.

Dr. Dhonam Pemba is the CEO and Co-Founder of KidX, he is a neural engineer by education, a former rocket scientist by work, and AI entrepeneur by entrepeneurship. He received his Biomedical Engineering undergraduate degree from Johns Hopkins University, and hi PhD from the University of California, Irvine also in BME, but worked on neural interface for his thesis. Can you me about the NASA JPL project and how it was related to your PhD work? My PhD work was building micro implantable neural implants. Very similar to the work that Elon Musks's company Neuralink is now doing.

Google has today launched a re-imagined version of its free Earth mapping service, weaving in storytelling and artificial intelligence. The new programme lets people get a close-up look of the planet from the comfort of their computers, smartphones or tablets. The new-look Google Earth enables its users to learn about far-flung corners of the globe under the guidance of scientists from Nasa and prestigious research institutions. Google Earth's new start-up screen offers a global view of the Earth. 'This is our gift to the world,' Google Earth director Rebecca Moore said.