Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs are very computationally demanding largely due to the computational cost of the decoding process, which consists of a softmax layer over a large vocabulary.We observe that in the decoding of many NLP tasks, only the probabilities of the top-K hypotheses need to be calculated preciously and K is often much smaller than the vocabulary size. This paper proposes a novel softmax layer approximation algorithm, called Fast Graph Decoder (FGD), which quickly identifies, for a given context, a set of K words that are most likely to occur according to a NLM. We demonstrate that FGD reduces the decoding time by an order of magnitude while attaining close to the full softmax baseline accuracy on neural machine translation and language modeling tasks. We also prove the theoretical guarantee on the softmax approximation quality.

Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs are very computationally demanding largely due to the computational cost of the decoding process, which consists of a softmax layer over a large vocabulary.We observe that in the decoding of many NLP tasks, only the probabilities of the top-K hypotheses need to be calculated preciously and K is often much smaller than the vocabulary size. This paper proposes a novel softmax layer approximation algorithm, called Fast Graph Decoder (FGD), which quickly identifies, for a given context, a set of K words that are most likely to occur according to a NLM. We demonstrate that FGD reduces the decoding time by an order of magnitude while attaining close to the full softmax baseline accuracy on neural machine translation and language modeling tasks. We also prove the theoretical guarantee on the softmax approximation quality.

Solving Inductive Logic Programming (ILP) problems with neural networks is a key challenge in Neural-Symbolic Ar- tificial Intelligence (AI). While most research has focused on designing novel network architectures for individual prob- lems, less effort has been devoted to exploring new learning paradigms involving a sequence of problems. In this work, we investigate lifelong learning ILP, which leverages the com- positional and transferable nature of logic rules for efficient learning of new problems. We introduce a compositional framework, demonstrating how logic rules acquired from ear- lier tasks can be efficiently reused in subsequent ones, leading to improved scalability and performance. We formalize our approach and empirically evaluate it on sequences of tasks. Experimental results validate the feasibility and advantages of this paradigm, opening new directions for continual learn- ing in Neural-Symbolic AI.

The application of causal discovery to diseases like Alzheimer's (AD) is limited by the static graph assumptions of most methods; such models cannot account for an evolving pathophysiology, modulated by a latent disease pseudotime. We propose to apply an existing latent variable model to real-world AD data, inferring a pseudotime that orders patients along a data-driven disease trajectory independent of chronological age, then learning how causal relationships evolve. Pseudotime outperformed age in predicting diagnosis (AUC 0.82 vs 0.59). Incorporating minimal, disease-agnostic background knowledge substantially improved graph accuracy and orientation. Our framework reveals dynamic interactions between novel (NfL, GFAP) and established AD markers, enabling practical causal discovery despite violated assumptions.

Radiation therapy treatment planning is an iterative, expertise-dependent process, and the growing burden of cancer cases has made reliance on manual planning increasingly unsustainable, underscoring the need for automation. In this study, we propose a workflow that leverages a large language model (LLM)-based agent to navigate inverse treatment planning for intensity-modulated radiation therapy (IMRT). The LLM agent was implemented to directly interact with a clinical treatment planning system (TPS) to iteratively extract intermediate plan states and propose new constraint values to guide inverse optimization. The agent's decision-making process is informed by current observations and previous optimization attempts and evaluations, allowing for dynamic strategy refinement. The planning process was performed in a zero-shot inference setting, where the LLM operated without prior exposure to manually generated treatment plans and was utilized without any fine-tuning or task-specific training. The LLM-generated plans were evaluated on twenty head-and-neck cancer cases against clinical manual plans, with key dosimetric endpoints analyzed and reported. The LLM-generated plans achieved comparable organ-at-risk (OAR) sparing relative to clinical plans while demonstrating improved hot spot control (Dmax: 106.5% vs. 108.8%) and superior conformity (conformity index: 1.18 vs. 1.39 for boost PTV; 1.82 vs. 1.88 for primary PTV). This study demonstrates the feasibility of a zero-shot, LLM-driven workflow for automated IMRT treatment planning in a commercial TPS. The proposed approach provides a generalizable and clinically applicable solution that could reduce planning variability and support broader adoption of AI-based planning strategies.

Unlike traditional tissue tests[1, 2], cell-based liquid biopsy assays enable selection of individual CTCs for the analysis of chromosomal instability using next-generation sequencing by quantification of large-scale state transitions (LST) [3-9]. Chromosomal instability is a genomic characteristic of cancer cells that drives tumor evolution and metastatic potential [10-19]. However, whole genome sequencing assays are laborious, requiring a complex workflow that invariably results in a considerable turnaround time that sometimes is not compatible with clinical practice [20]. A previous study has shown that we can partially predict chromosomal instability in individual cells by developing algorithms that analyze a range of features, including cell shape, size, morphology, and protein levels, from images of CTCs using an automated digital pathology pipeline [3]. Predicting chromosomal instability through morphology offers significant advantages; it can significantly reduce turnaround times compared to whole-genome assays, providing crucial information about the genomic characteristics of CTCs in a patient in a shorter timeframe [3]. Timely information on the presence of CTCs with the highest metastatic potential may be critical for making optimal clinical decisions. A key challenge in predicting chromosomal instability through morphology is the utilization of a machine-learning method that accurately classifies morphology patterns from all CTC features and provides a generalization and reproducibility, compatible with potential validation for clinical use [21-24]. Key limitations of commonly used machine learning techniques in biology applications, such as support vector machines (SVMs) with Gaussian kernels, include the following [21-24]: 1) The increase in dimensionality that arises from combinations of multiple features exponentially complicates the prediction task, as often seen with cell morphologies.

Childhood vaccination is a cornerstone of public health, yet disparities in vaccination coverage persist across England. These disparities are shaped by complex interactions among various factors, including geographic, demographic, socioeconomic, and cultural (GDSC) factors. Previous studies mostly rely on cross-sectional data and traditional statistical approaches that assess individual or limited sets of variables in isolation. Such methods may fall short in capturing the dynamic and multivariate nature of vaccine uptake. In this paper, we conducted a longitudinal machine learning analysis of childhood vaccination coverage across 150 districts in England from 2021 to 2024. Using vaccination data from NHS records, we applied hierarchical clustering to group districts by vaccination coverage into low- and high-coverage clusters. A CatBoost classifier was then trained to predict districts' vaccination clusters using their GDSC data. Finally, the SHapley Additive exPlanations (SHAP) method was used to interpret the predictors' importance. The classifier achieved high accuracies of 92.1, 90.6, and 86.3 in predicting districts' vaccination clusters for the years 2021-2022, 2022-2023, and 2023-2024, respectively. SHAP revealed that geographic, cultural, and demographic variables, particularly rurality, English language proficiency, the percentage of foreign-born residents, and ethnic composition, were the most influential predictors of vaccination coverage, whereas socioeconomic variables, such as deprivation and employment, consistently showed lower importance, especially in 2023-2024. Surprisingly, rural districts were significantly more likely to have higher vaccination rates. Additionally, districts with lower vaccination coverage had higher populations whose first language was not English, who were born outside the UK, or who were from ethnic minority groups.

Grokking, or sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon that has challenged our understanding of deep learning. While a lot of progress has been made in understanding grokking, it is still not clear why generalization is delayed and why grokking often does not happen without regularization. In this work we argue that without regularization, grokking tasks push models to the edge of numerical stability, introducing floating point errors in the Softmax that we refer to as Softmax Collapse (SC). We show that SC prevents grokking and that mitigating SC leads to grokking without regularization. Investigating the root cause of SC, we find that beyond the point of overfitting, the gradients strongly align with what we call the naïve loss minimization (NLM) direction. This component of the gradient does not change the predictions of the model but decreases the loss by scaling the logits, usually through the scaling of the weights along their current direction. We show that this scaling of the logits explains the delay in generalization characteristic of grokking, and eventually leads to SC, stopping learning altogether. To validate these hypotheses, we introduce two key contributions that mitigate the issues faced in grokking tasks: (i) StableMax, a new activation function that prevents SC and enables grokking without regularization, and (ii) Grad, a training algorithm that leads to quick generalization in grokking tasks by preventing NLM altogether. These contributions provide new insights into grokking, shedding light on its delayed generalization, reliance on regularization, and the effectiveness of known grokking-inducing methods. Code for this paper can be found at: https://github.com/LucasPrietoAl/ Deep learning has been transformative for a variety of fields such as natural language processing (Devlin et al., 2019), computer vision (Krizhevsky et al., 2012), geometry processing (Qi et al., 2017), and 3D vision (Deng et al., 2018). This rapid proliferation has brought with it surprising phenomena that defy the predictions of classical statistical learning theory. In this paper we explore one such recently observed phenomenon known as grokking, first described by Power et al. (2022) as a sudden and unexpected generalization occurring after prolonged overfitting.