Search

Breast cancer remains a significant global health challenge, with prognosis and treatment decisions largely dependent on clinical characteristics. Accurate prediction of patient outcomes is crucial for personalized treatment strategies. This study employs survival analysis techniques, including Cox proportional hazards and parametric survival models, to enhance the prediction of the log odds of survival in breast cancer patients. Clinical variables such as tumor size, hormone receptor status, HER2 status, age, and treatment history were analyzed to assess their impact on survival outcomes. Data from 1557 breast cancer patients were obtained from a publicly available dataset provided by the University College Hospital, Ibadan, Nigeria. This dataset was preprocessed and analyzed using both univariate and multivariate approaches to evaluate survival outcomes. Kaplan-Meier survival curves were generated to visualize survival probabilities, while the Cox proportional hazards model identified key risk factors influencing mortality. The results showed that older age, larger tumor size, and HER2-positive status were significantly associated with an increased risk of mortality. In contrast, estrogen receptor positivity and breast-conserving surgery were linked to better survival outcomes. The findings suggest that integrating these clinical variables into predictive models improvesthe accuracy of survival predictions, helping to identify high-risk patients who may benefit from more aggressive interventions. This study demonstrates the potential of survival analysis in optimizing breast cancer care, particularly in resource-limited settings. Future research should focus on integrating genomic data and real-world clinical outcomes to further refine these models., Comment: 17 pages

Neurons in the brain are spatially organized such that neighbors on tissue often exhibit similar response profiles. In the human language system, experimental studies have observed clusters for syntactic and semantic categories, but the mechanisms underlying this functional organization remain unclear. Here, building on work from the vision literature, we develop TopoLM, a transformer language model with an explicit two-dimensional spatial representation of model units. By combining a next-token prediction objective with a spatial smoothness loss, representations in this model assemble into clusters that correspond to semantically interpretable groupings of text and closely match the functional organization in the brain's language system. TopoLM successfully predicts the emergence of the spatio-functional organization of a cortical language system as well as the organization of functional clusters selective for fine-grained linguistic features empirically observed in human cortex. Our results suggest that the functional organization of the human language system is driven by a unified spatial objective, and provide a functionally and spatially aligned model of language processing in the brain.

Diffusion models have recently shown considerable potential in solving Bayesian inverse problems when used as priors. However, sampling from the resulting denoising posterior distributions remains a challenge as it involves intractable terms. To tackle this issue, state-of-the-art approaches formulate the problem as that of sampling from a surrogate diffusion model targeting the posterior and decompose its scores into two terms: the prior score and an intractable guidance term. While the former is replaced by the pre-trained score of the considered diffusion model, the guidance term has to be estimated. In this paper, we propose a novel approach that utilises a decomposition of the transitions which, in contrast to previous methods, allows a trade-off between the complexity of the intractable guidance term and that of the prior transitions. We validate the proposed approach through extensive experiments on linear and nonlinear inverse problems, including challenging cases with latent diffusion models as priors, and demonstrate its effectiveness in reconstructing electrocardiogram (ECG) from partial measurements for accurate cardiac diagnosis.

Designing expressive typography that visually conveys a word's meaning while maintaining readability is a complex task, known as semantic typography. It involves selecting an idea, choosing an appropriate font, and balancing creativity with legibility. We introduce an end-to-end system that automates this process. First, a Large Language Model (LLM) generates imagery ideas for the word, useful for abstract concepts like freedom. Then, the FontCLIP pre-trained model automatically selects a suitable font based on its semantic understanding of font attributes. The system identifies optimal regions of the word for morphing and iteratively transforms them using a pre-trained diffusion model. A key feature is our OCR-based loss function, which enhances readability and enables simultaneous stylization of multiple characters. We compare our method with other baselines, demonstrating great readability enhancement and versatility across multiple languages and writing scripts.

This work proposes a strategy for organising quadrotors around a payload to enable hovering without external stimuli, together with a MATLAB software for modelling the dynamics of a quadrotor-payload system. Based on geometric concepts, the proposed design keeps the payload and system centre of mass aligned. Hovering tests that are successful confirm the method's efficiency. Moreover, the algorithm is improved to take thrust capacities and propeller distances into account, calculating the minimum number of quadrotors needed for hovering. The algorithm's effectiveness is demonstrated by numerical examples, which reveal that larger quadrotors may require fewer units while smaller ones give greater flexibility. Our code can be found at: \href{https://github.com/Hosnooo/Swarm-Slung-Payload}{https://github.com/Hosnooo/Swarm-Slung-Payload}, Comment: accepted for publication at AIAA SCITECH 2025

Bitcoin's global success has led to the rise of blockchain, but many systems labeled as "blockchain" deviate from its core principles, adding complexity to the ecosystem. This survey addresses the need for a comprehensive review and taxonomy to clarify the differences between blockchain and blockchain-like systems. We propose a reference model with four key layers: data, consensus, execution, and application, and introduce a new taxonomy for better classification. Through a qualitative and quantitative analysis of 44 DLT solutions and 26 consensus mechanisms, we highlight key challenges and offer research directions in the field.

The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many occasions they are associated with hidden spurious correlations which are not easy to spot. Standard approaches rely on bias audits performed by analyzing model performance in pre-defined subgroups of data samples, usually characterized by common attributes like gender or ethnicity when it comes to people, or other specific attributes defining semantically coherent groups of images. However, it is not always possible to know a-priori the specific attributes defining the failure modes of visual recognition systems. Recent approaches propose to discover these groups by leveraging large vision language models, which enable the extraction of cross-modal embeddings and the generation of textual descriptions to characterize the subgroups where a certain model is underperforming. In this work, we argue that incorporating visual explanations (e.g. heatmaps generated via GradCAM or other approaches) can boost the performance of such bias discovery and mitigation frameworks. To this end, we introduce Visually Grounded Bias Discovery and Mitigation (ViG-Bias), a simple yet effective technique which can be integrated to a variety of existing frameworks to improve both, discovery and mitigation performance. Our comprehensive evaluation shows that incorporating visual explanations enhances existing techniques like DOMINO, FACTS and Bias-to-Text, across several challenging datasets, including CelebA, Waterbirds, and NICO++., Comment: Accepted to ECCV 2024

Large Language Models (LLMs) have been shown to be effective models of the human language system, with some models predicting most explainable variance of brain activity in current datasets. Even in untrained models, the representations induced by architectural priors can exhibit reasonable alignment to brain data. In this work, we investigate the key architectural components driving the surprising alignment of untrained models. To estimate LLM-to-brain similarity, we first select language-selective units within an LLM, similar to how neuroscientists identify the language network in the human brain. We then benchmark the brain alignment of these LLM units across five different brain recording datasets. By isolating critical components of the Transformer architecture, we identify tokenization strategy and multihead attention as the two major components driving brain alignment. A simple form of recurrence further improves alignment. We further demonstrate this quantitative brain alignment of our model by reproducing landmark studies in the language neuroscience field, showing that localized model units -- just like language voxels measured empirically in the human brain -- discriminate more reliably between lexical than syntactic differences, and exhibit similar response profiles under the same experimental conditions. Finally, we demonstrate the utility of our model's representations for language modeling, achieving improved sample and parameter efficiency over comparable architectures. Our model's estimates of surprisal sets a new state-of-the-art in the behavioral alignment to human reading times. Taken together, we propose a highly brain- and behaviorally-aligned model that conceptualizes the human language system as an untrained shallow feature encoder, with structural priors, combined with a trained decoder to achieve efficient and performant language processing., Comment: Preprint

While existing literature relies on performance differences to uncover gender biases in ASR models, a deeper analysis is essential to understand how gender is encoded and utilized during transcript generation. This work investigates the encoding and utilization of gender in the latent representations of two transformer-based ASR models, Wav2Vec2 and HuBERT. Using linear erasure, we demonstrate the feasibility of removing gender information from each layer of an ASR model and show that such an intervention has minimal impacts on the ASR performance. Additionally, our analysis reveals a concentration of gender information within the first and last frames in the final layers, explaining the ease of erasing gender in these layers. Our findings suggest the prospect of creating gender-neutral embeddings that can be integrated into ASR frameworks without compromising their efficacy., Comment: Accepted at Interspeech 2024

In this paper, we investigate the deterministic multidimensional Skorokhod problem with normal reflection in a family of time-dependent convex domains that are c\`adl\`ag with respect to the Hausdorff metric. We then show the existence and uniqueness of solutions to multidimensional McKean-Vlasov stochastic differential equations reflected in these time-dependent domains. Additionally, we derive stability properties with respect to the initial condition and the coefficients. Finally, we establish a propagation of chaos result.

PAC-Bayesian analysis is a frequentist framework for incorporating prior knowledge into learning. It was inspired by Bayesian learning, which allows sequential data processing and naturally turns posteriors from one processing step into priors for the next. However, despite two and a half decades of research, the ability to update priors sequentially without losing confidence information along the way remained elusive for PAC-Bayes. While PAC-Bayes allows construction of data-informed priors, the final confidence intervals depend only on the number of points that were not used for the construction of the prior, whereas confidence information in the prior, which is related to the number of points used to construct the prior, is lost. This limits the possibility and benefit of sequential prior updates, because the final bounds depend only on the size of the final batch. We present a novel and, in retrospect, surprisingly simple and powerful PAC-Bayesian procedure that allows sequential prior updates with no information loss. The procedure is based on a novel decomposition of the expected loss of randomized classifiers. The decomposition rewrites the loss of the posterior as an excess loss relative to a downscaled loss of the prior plus the downscaled loss of the prior, which is bounded recursively. As a side result, we also present a generalization of the split-kl and PAC-Bayes-split-kl inequalities to discrete random variables, which we use for bounding the excess losses, and which can be of independent interest. In empirical evaluation the new procedure significantly outperforms state-of-the-art.

We report on an experimental platform based on an atom chip encompassing a coplanar waveguide which enables to manipulate a quantum gas of sodium atoms with strong microwave fields. We describe the production with this setup of a very elongated degenerate quantum gas with typically 10^6 atoms, that can be prepared all along the cross-over from the three-dimensional to the one-dimensional regime depending on the atom number and trapping geometry. Using the microwave field radiated by the waveguide, we drive Rabi oscillations between the hyperfine ground states, with the atoms trapped at various distances from the waveguide. At the closest position explored, the field amplitude exceeds 5 G, corresponding to a Rabi frequency larger than 6 MHz. This enables fast manipulation of the atomic internal state.

The Method of Successive Approximations (MSA) is a fixed-point iterative method used to solve stochastic optimal control problems. It is an indirect method based on the conditions derived from the Stochastic Maximum Principle (SMP), an extension of the Pontryagin Maximum Principle (PMP) to stochastic control problems. In this study, we investigate the contractivity and the convergence of MSA for a specific and interesting class of stochastic dynamical systems (when the drift coefficient is one-sided-Lipschitz with a negative constant and the diffusion coefficient is Lipschitz continuous). Our analysis unfolds in three key steps: firstly, we prove the stability of the state process with respect to the control process. Secondly, we establish the stability of the adjoint process. Finally, we present rigorous evidence to prove the contractivity and then the convergence of MSA. This study contributes to enhancing the understanding of MSA's applicability and effectiveness in addressing stochastic optimal control problems.

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More specifically, at each position in the training corpus, we ask the model to predict the following n tokens using n independent output heads, operating on top of a shared model trunk. Considering multi-token prediction as an auxiliary training task, we measure improved downstream capabilities with no overhead in training time for both code and natural language models. The method is increasingly useful for larger model sizes, and keeps its appeal when training for multiple epochs. Gains are especially pronounced on generative benchmarks like coding, where our models consistently outperform strong baselines by several percentage points. Our 13B parameter models solves 12 % more problems on HumanEval and 17 % more on MBPP than comparable next-token models. Experiments on small algorithmic tasks demonstrate that multi-token prediction is favorable for the development of induction heads and algorithmic reasoning capabilities. As an additional benefit, models trained with 4-token prediction are up to 3 times faster at inference, even with large batch sizes.

In this paper, we present two novel methods in Network Intrusion Detection Systems (NIDS) using Graph Neural Networks (GNNs). The first approach, Scattering Transform with E-GraphSAGE (STEG), utilizes the scattering transform to conduct multi-resolution analysis of edge feature vectors. This provides a detailed representation that is essential for identifying subtle anomalies in network traffic. The second approach improves node representation by initiating with Node2Vec, diverging from standard methods of using uniform values, thereby capturing a more accurate and holistic network picture. Our methods have shown significant improvements in performance compared to existing state-of-the-art methods in benchmark NIDS datasets.

Efficient early diagnosis is paramount in addressing the complexities of Parkinson's disease because timely intervention can substantially mitigate symptom progression and improve patient outcomes. In this paper, we present a pioneering deep learning architecture tailored for the binary classification of subjects, utilizing gait cycle datasets to facilitate early detection of Parkinson's disease. Our model harnesses the power of 1D-Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Graph Neural Network (GNN) layers, synergistically capturing temporal dynamics and spatial relationships within the data. In this work, 16 wearable sensors located at the end of subjects' shoes for measuring the vertical Ground Reaction Force (vGRF) are considered as the vertices of a graph, their adjacencies are modelled as edges of this graph, and finally, the measured data of each sensor is considered as the feature vector of its corresponding vertex. Therefore, The GNN layers can extract the relations among these sensors by learning proper representations. Regarding the dynamic nature of these measurements, GRU and CNN are used to analyze them spatially and temporally and map them to an embedding space. Remarkably, our proposed model achieves exceptional performance metrics, boasting accuracy, precision, recall, and F1 score values of 99.51%, 99.57%, 99.71%, and 99.64%, respectively.

Silicone is frequently used as a model system to investigate and tune wetting on soft materials. Silicone is biocompatible and shows excellent thermal, chemical, and UV stability. Moreover, the mechanical properties of the surface can be easily varied by several orders of magnitude in a controlled manner. Polydimethylsiloxane (PDMS) is a popular choice for coating applications such as lubrication, self-cleaning, and drag reduction, facilitated by low surface energy. Aiming to understand the underlying interactions and forces, motivated numerous and detailed investigations of the static and dynamic wetting behavior of drops on PDMS-based surfaces. Here, we recognize the three most prevalent PDMS surface variants, namely liquid-infused (SLIPS/LIS), elastomeric, and liquid-like (SOCAL) surfaces. To understand, optimize, and tune the wetting properties of these PDMS surfaces, we review and compare their similarities and differences by discussing (i) the chemical and molecular structure, and (ii) the static and dynamic wetting behavior. We also provide (iii) an overview of methods and techniques to characterize PDMS-based surfaces and their wetting behavior. The static and dynamic wetting ridge is given particular attention, as it dominates energy dissipation, adhesion, and friction of sliding drops and influences the durability of the surfaces. We also discuss special features such as cloaking and wetting-induced phase separation. Key challenges and opportunities of these three surface variants are outlined.

We study the equilibrium properties and the wetting behavior of a simple liquid on a polymer brush, with and without presence of lubricant by multibody Dissipative Particle Dynamics simulations. The lubricant is modelled as a polymeric liquid consisting of short chains that are chemically identical to the brush polymers. We investigate the behavior of the brush in terms of the grafting density and the amount of lubricant present. Regarding the wetting behavior, we study a sessile droplet on top of the brush. The droplet consists of non-bonded particles that form a dense phase. Our model and choice of parameters result in the formation of a wetting ridge and in the cloaking of the droplet by the lubricant, i.e. the lubricant chains creep up onto the droplet and eventually cover its surface completely. Cloaking is a phenomenon that is observed experimentally and is of integral importance to the dynamics of sliding droplets. We quantify the cloaking in terms of its thickness, which increases with the amount of lubricant present. The analysis reveals a well-defined transition point where the cloaking sets in. We propose a thermodynamic theory to explain this behavior. In addition we investigate the dependence of the contact angles on the size of the droplet and the possible effect of line tension. We quantify the variation of the contact angle with the curvature of the contact line on a lubricant free brush and find a negative value for the line tension. Finally we investigate the effect of cloaking/lubrication on the contact angles and the wetting ridge. We find that lubrication and cloaking reduce the contact angles by a couple of degrees. The effect on the wetting ridge is a reduction in the extension of the brush chains near the three phase contact line, an effect that was also observed in experiments of droplets on crosslinked gels.

Understanding the dynamics of drops on polymer-coated surfaces is crucial for optimizing applications such as self-cleaning materials or microfluidic devices. While the static and dynamic properties of deposited drops have been well characterised, a microscopic understanding of the underlying dynamics is missing. In particular, it is unclear how drop dynamics depends on the amount of uncrosslinked chains in the brush, because experimental techniques fail to quantify those. Here we use coarse-grained simulations to study droplets moving on a lubricated polymer brush substrate under the influence of an external body force. The simulation model is based on the many body dissipative particle dynamics (mDPD) method and designed to mimic a system of water droplets on polydimethylsiloxane (PDMS) brushes with chemically identical PDMS lubricant. In agreement with experiments, we find a sublinear power law dependence between the external force $F$ and the droplet velocity $v$, $F \propto v^\alpha$ with $\alpha <1$; however, the exponents differ ($\alpha \sim 0.6-0.7$ in simulations versus $\alpha \sim 0.25$ in experiments). With increasing velocity, the droplets elongate and the receding contact angle decreases, whereas the advancing contact angle remains roughly constant. Analyzing the flow profiles inside the droplet reveals that the droplets do not slide, but roll, with vanishing slip at the substrate surface. Surprisingly, adding lubricant has very little effect on the effective friction force between the droplet and the substrate, even though it has a pronounced effect on the size and structure of the wetting ridge, especially above the cloaking transition.

Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applied: information unrelated to the edits can also be changed, and other general behaviors of the model can be wrongly altered. In this work, we investigate how model editing methods unexpectedly amplify model biases post-edit. We introduce a novel benchmark dataset, Seesaw-CF, for measuring bias-related harms of model editing and conduct the first in-depth investigation of how different weight-editing methods impact model bias. Specifically, we focus on biases with respect to demographic attributes such as race, geographic origin, and gender, as well as qualitative flaws in long-form texts generated by edited language models. We find that edited models exhibit, to various degrees, more biased behavior as they become less confident in attributes for Asian, African, and South American subjects. Furthermore, edited models amplify sexism and xenophobia in text generations while remaining seemingly coherent and logical. Finally, editing facts about place of birth, country of citizenship, or gender have particularly negative effects on the model's knowledge about unrelated features like field of work., Comment: Accepted to EMNLP 2024 Main. 9 pages, 4 figures

The intricate relationship between language and culture has long been a subject of exploration within the realm of linguistic anthropology. Large Language Models (LLMs), promoted as repositories of collective human knowledge, raise a pivotal question: do these models genuinely encapsulate the diverse knowledge adopted by different cultures? Our study reveals that these models demonstrate greater cultural alignment along two dimensions -- firstly, when prompted with the dominant language of a specific culture, and secondly, when pretrained with a refined mixture of languages employed by that culture. We quantify cultural alignment by simulating sociological surveys, comparing model responses to those of actual survey participants as references. Specifically, we replicate a survey conducted in various regions of Egypt and the United States through prompting LLMs with different pretraining data mixtures in both Arabic and English with the personas of the real respondents and the survey questions. Further analysis reveals that misalignment becomes more pronounced for underrepresented personas and for culturally sensitive topics, such as those probing social values. Finally, we introduce Anthropological Prompting, a novel method leveraging anthropological reasoning to enhance cultural alignment. Our study emphasizes the necessity for a more balanced multilingual pretraining dataset to better represent the diversity of human experience and the plurality of different cultures with many implications on the topic of cross-lingual transfer., Comment: ACL 2024 (Main)

Air pollution is a major problem today that causes serious damage to human health. Urban areas are the most affected by the degradation of air quality caused by anthropogenic gas emissions. Although there are multiple proposals for air quality monitoring, in most cases, two limitations are imposed: the impossibility of processing data in Near Real-Time (NRT) for remote sensing approaches and the impossibility of reaching areas of limited accessibility or low network coverage for ground data approaches. We propose a software architecture that efficiently combines complex event processing with remote sensing data from various satellite sensors to monitor air quality in NRT, giving support to decision-makers. We illustrate the proposed solution by calculating the air quality levels for several areas of Morocco and Spain, extracting and processing satellite information in NRT. This study also validates the air quality measured by ground stations and satellite sensor data.

Diacritization plays a pivotal role in improving readability and disambiguating the meaning of Arabic texts. Efforts have so far focused on marking every eligible character (Full Diacritization). Comparatively overlooked, Partial Diacritzation (PD) is the selection of a subset of characters to be marked to aid comprehension where needed. Research has indicated that excessive diacritic marks can hinder skilled readers -- reducing reading speed and accuracy. We conduct a behavioral experiment and show that partially marked text is often easier to read than fully marked text, and sometimes easier than plain text. In this light, we introduce Context-Contrastive Partial Diacritization (CCPD) -- a novel approach to PD which integrates seamlessly with existing Arabic diacritization systems. CCPD processes each word twice, once with context and once without, and diacritizes only the characters with disparities between the two inferences. Further, we introduce novel indicators for measuring partial diacritization quality, essential for establishing this as a machine learning task. Lastly, we introduce TD2, a Transformer-variant of an established model which offers a markedly different performance profile on our proposed indicators compared to all other known systems., Comment: 14 equations, 5 tables, 5 figures