The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neurovascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two non-invasive angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited datasets with annotations on CoW anatomy, especially for CTA. Therefore, we organized the TopCoW challenge with the release of an annotated CoW dataset. The TopCoW dataset is the first public dataset with voxel-level annotations for 13 CoW vessel components, enabled by virtual reality technology. It is also the first large dataset using 200 pairs of MRA and CTA from the same patients. As part of the benchmark, we invited submissions worldwide and attracted over 250 registered participants from six continents. The submissions were evaluated on both internal and external test datasets of 226 scans from over five centers. The top performing teams achieved over 90% Dice scores at segmenting the CoW components, over 80% F1 scores at detecting key CoW components, and over 70% balanced accuracy at classifying CoW variants for nearly all test sets. The best algorithms also showed clinical potential in classifying fetal-type posterior cerebral artery and locating aneurysms with CoW anatomy. TopCoW demonstrated the utility and versatility of CoW segmentation algorithms for a wide range of downstream clinical applications with explainability. The annotated datasets and best performing algorithms have been released as public Zenodo records to foster further methodological development and clinical tool building.

Hospitals struggle to predict critical outcomes. Traditional early warning systems, like NEWS and MEWS, rely on static variables and fixed thresholds, limiting their adaptability, accuracy, and personalization. We previously developed the Enhanced Transformer for Health Outcome Simulation (ETHOS), an AI model that tokenizes patient health timelines (PHTs) from EHRs and uses transformer-based architectures to predict future PHTs. ETHOS is a versatile framework for developing a wide range of applications. In this work, we develop the Adaptive Risk Estimation System (ARES) that leverages ETHOS to compute dynamic, personalized risk probabilities for clinician-defined critical events. ARES also features a personalized explainability module that highlights key clinical factors influencing risk estimates. We evaluated ARES using the MIMIC-IV v2.2 dataset together with its Emergency Department (ED) extension and benchmarked performance against both classical early warning systems and contemporary machine learning models. The entire dataset was tokenized resulting in 285,622 PHTs, comprising over 360 million tokens. ETHOS outperformed benchmark models in predicting hospital admissions, ICU admissions, and prolonged stays, achieving superior AUC scores. Its risk estimates were robust across demographic subgroups, with calibration curves confirming model reliability. The explainability module provided valuable insights into patient-specific risk factors. ARES, powered by ETHOS, advances predictive healthcare AI by delivering dynamic, real-time, personalized risk estimation with patient-specific explainability. Although our results are promising, the clinical impact remains uncertain. Demonstrating ARES's true utility in real-world settings will be the focus of our future work. We release the source code to facilitate future research.

Time-series forecasting and causal discovery are central in neuroscience, as predicting brain activity and identifying causal relationships between neural populations and circuits can shed light on the mechanisms underlying cognition and disease. With the rise of foundation models, an open question is how they compare to traditional methods for brain signal forecasting and causality analysis, and whether they can be applied in a zero-shot setting. In this work, we evaluate a foundation model against classical methods for inferring directional interactions from spontaneous brain activity measured with functional magnetic resonance imaging (fMRI) in humans. Traditional approaches often rely on Wiener-Granger causality. We tested the forecasting ability of the foundation model in both zero-shot and fine-tuned settings, and assessed causality by comparing Granger-like estimates from the model with standard Granger causality. We validated the approach using synthetic time series generated from ground-truth causal models, including logistic map coupling and Ornstein-Uhlenbeck processes. The foundation model achieved competitive zero-shot forecasting fMRI time series (mean absolute percentage error of 0.55 in controls and 0.27 in patients). Although standard Granger causality did not show clear quantitative differences between models, the foundation model provided a more precise detection of causal interactions. Overall, these findings suggest that foundation models offer versatility, strong zero-shot performance, and potential utility for forecasting and causal discovery in time-series data.

Hallucinations of deep neural models are amongst key challenges in automatic speech recognition (ASR). In this paper, we investigate hallucinations of the Whisper ASR model induced by non-speech audio segments present during inference. By inducting hallucinations with various types of sounds, we show that there exists a set of hallucinations that appear frequently. We then study hallucinations caused by the augmentation of speech with such sounds. Finally, we describe the creation of a bag of hallucinations (BoH) that allows to remove the effect of hallucinations through the post-processing of text transcriptions. The results of our experiments show that such post-processing is capable of reducing word error rate (WER) and acts as a good safeguard against problematic hallucinations.

We consider an effective Hubbard model with spin- and direction-dependent complex hoppings $t$, applied to twisted homobilayer WSe$_2$ using a variational Monte Carlo approach. The electronic correlations are taken into account by applying the Gutzwiller on-site correlator as well as long-range Jastrow correlators subjected to noninteracting part being of Pfaffian form. Our analysis shows the emergence of Mott insulating state at critical value of Hubbard interaction $U_{c1}\approx 6.5|t|\div7|t|$ estimated by extrapolating the density-density equal-time two-particle Green's functions. The signatures of an intermediate insulating phase between $U_{c1}$ and $U_{c2}\approx9.5|t|\div10|t|$ are also discussed. Furthermore, we report the formation of the $120^{\circ}$ in-plane N\'eel state indicated by the detailed analysis of the spin-spin correlation functions. As shown, switching between antiferromagnetic phases characterized by opposite chirality could be experimentally realized by the change of perpendicular electric field. In proper range of electric fields also a transition to in-plane ferromagnetic state appears.

Medical image registration is critical for clinical applications, and fair benchmarking of different methods is essential for monitoring ongoing progress. To date, the Learn2Reg 2020-2023 challenges have released several complementary datasets and established metrics for evaluations. However, these editions did not capture all aspects of the registration problem, particularly in terms of modality diversity and task complexity. To address these limitations, the 2024 edition introduces three new tasks, including large-scale multi-modal registration and unsupervised inter-subject brain registration, as well as the first microscopy-focused benchmark within Learn2Reg. The new datasets also inspired new method developments, including invertibility constraints, pyramid features, keypoints alignment and instance optimisation.

Software comprehension can be extremely time-consuming due to the ever-growing size of codebases. Consequently, there is an increasing need to accelerate the code comprehension process to facilitate maintenance and reduce associated costs. A crucial aspect of this process is understanding and preserving the high quality of the code dependency structure. While a variety of code structure models already exist, there is a surprising lack of models that closely represent the source code and focus on software comprehension. As a result, there are no readily available and easy-to-use tools to assist with dependency comprehension, refactoring, and quality monitoring of code. To address this gap, we propose the Semantic Code Graph (SCG), an information model that offers a detailed abstract representation of code dependencies with a close relationship to the source code. To validate the SCG model's usefulness in software comprehension, we compare it to nine other source code representation models. Additionally, we select 11 well-known and widely-used open-source projects developed in Java and Scala and perform a range of software comprehension activities on them using three different code representation models: the proposed SCG, the Call Graph (CG), and the Class Collaboration Network (CCN). We then qualitatively analyze the results to compare the performance of these models in terms of software comprehension capabilities. These activities encompass project structure comprehension, identifying critical project entities, interactive visualization of code dependencies, and uncovering code similarities through software mining. Our findings demonstrate that the SCG enhances software comprehension capabilities compared to the prevailing CCN and CG models. We believe that the work described is a step towards the next generation of tools that streamline code dependency comprehension and management.

In this work, we perform a comprehensive study of the classical and quantum chaos in a candidate five-dimensional hairy AdS soliton. It is a horizonless geometry holographically dual to a confining field theory with finite scalar potential. We probe classical chaos by using particle geodesics and closed classical string. While the former shows no signature of chaos, the latter provides chaotic dynamics of the string using the Lyapunov exponent and the evolution of the Poincaré section. We perform an independent spectral analysis using the tools of the random matrix theory (RMT), namely the level space distributions and the Dyson-Mehta(DM) $\Delta_{3}$-statistics. We observe a clear transition from the low energy Wigner-Gaussian Orthogonal Ensemble (GOE) distribution to the high energy Poisson distribution. This signifies a flow from quantum chaos in the infrared to integrability in the ultraviolet. We quantitatively characterize the inherent quantum scrambling in the dual theory by computing the butterfly velocity, the rate of spatial spread of the information scrambling, inside the bulk. We undergo two independent holographic methods -- entanglement wedge reconstruction and derivation of out-of-time-ordered correlators via shockwave analysis. In these methods, we heuristically consider the region near the soliton tip to provide the infrared physics of scrambling in analogy with the near-horizon region of a black hole. We find that the hair parameter controls various scrambling properties. Finally, we make comments on the interplay between insulator/superconductor phase transition in hairy soliton geometry and dynamical transition from integrability to chaos as both of these are affected by the presence of the hair parameter.

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at this https URL, with baselines and development kits available at this https URL.

Hybrid superconductor-semiconductor(SC-SM) nanowires remain one of the foremost platforms for engineering topological superconductivity and Majorana zero modes(MZMs) towards fault-tolerant topological qubits, especially with the rapid development of artificial Kitaev chains. In contrast to the widely used aluminum(Al)-based hybrids, lead(Pb) offers a bulk superconducting gap of ~1.4meV and a critical temperature of ~7.2K, giving rise to a proximity-induced gap that is roughly five times larger than that obtained with Al. Here we present the first three-terminal Pb-hybrid devices and perform nonlocal differential-conductance spectroscopy on this platform. The nonlocal measurement simultaneously resolves a dual-gap feature of the parent Pb gap and the large, hard, gate-tunable induced superconducting gap, distinguished by a switch between electron- and hole-like dissipation processes. Within the induced gap we observe several types of Andreev bound states(ABSs) that undergo singlet-doublet transitions. Moreover, by tuning gate voltages we achieve gate-controlled resonating sign reversals of the nonlocal conductance, identifying three distinct regimes that correspond to different configurations of quantum-dot(QD) resonances(single-resonance, double-resonance, and series-resonance). Finally, the coupling between ABSs and QDs also present and can be modulated from the weak- to strong-coupling limit, indicating the feasibility of realizing the artificial Kitaev chains. Crucially, the robust nonlocal signatures persist up to temperatures(~1K) far above the operating temperature of Al-based devices thanks to the unusually large induced gap, thereby widening the accessible parameter space greatly and underscoring the suitability of Pb-based hybrids for implementing warm temperature artificial Kitaev chains and the topological quantum devices protected by a substantially larger topological gap.

Multi-object tracking (MOT) is one of the most important problems in computer vision and a key component of any vision-based perception system used in advanced autonomous mobile robotics. Therefore, its implementation on low-power and real-time embedded platforms is highly desirable. Modern MOT algorithms should be able to track objects of a given class (e.g. people or vehicles). In addition, the number of objects to be tracked is not known in advance, and they may appear and disappear at any time, as well as be obscured. For these reasons, the most popular and successful approaches have recently been based on the tracking paradigm. Therefore, the presence of a high quality object detector is essential, which in practice accounts for the vast majority of the computational and memory complexity of the whole MOT system. In this paper, we propose an FPGA (Field-Programmable Gate Array) implementation of an embedded MOT system based on a quantized YOLOv8 detector and the SORT (Simple Online Realtime Tracker) tracker. We use a modified version of the FINN framework to utilize external memory for model parameters and to support operations necessary required by YOLOv8. We discuss the evaluation of detection and tracking performance using the COCO and MOT15 datasets, where we achieve 0.21 mAP and 38.9 MOTA respectively. As the computational platform, we use an MPSoC system (Zynq UltraScale+ device from AMD/Xilinx) where the detector is deployed in reprogrammable logic and the tracking algorithm is implemented in the processor system.

Abstract visual reasoning (AVR) involves discovering shared concepts across images through analogy, akin to solving IQ test problems. Bongard Problems (BPs) remain a key challenge in AVR, requiring both visual reasoning and verbal description. We investigate whether multimodal large language models (MLLMs) can solve BPs by formulating a set of diverse MLLM-suited solution strategies and testing $4$ proprietary and $4$ open-access models on $3$ BP datasets featuring synthetic (classic BPs) and real-world (Bongard HOI and Bongard-OpenWorld) images. Despite some successes on real-world datasets, MLLMs struggle with synthetic BPs. To explore this gap, we introduce Bongard-RWR, a dataset representing synthetic BP concepts using real-world images. Our findings suggest that weak MLLM performance on classical BPs is not due to the domain specificity, but rather comes from their general AVR limitations. Code and dataset are available at: this https URL

We study the effectiveness of molecular fingerprints for peptide property prediction and demonstrate that domain-specific feature extraction from molecular graphs can outperform complex and computationally expensive models such as GNNs, pretrained sequence-based transformers and multimodal ensembles, even without hyperparameter tuning. To this end, we perform a thorough evaluation on 126 datasets, achieving state-of-the-art results on LRGB and 5 other peptide function prediction benchmarks. We show that models based on count variants of ECFP, Topological Torsion, and RDKit molecular fingerprints and LightGBM as classification head are remarkably robust. The strong performance of molecular fingerprints, which are intrinsically very short-range feature encoders, challenges the presumed importance of long-range interactions in peptides. Our conclusion is that the use of molecular fingerprints for larger molecules, such as peptides, can be a computationally feasible, low-parameter, and versatile alternative to sophisticated deep learning models.

The size, diversity, and quality of pretraining datasets critically determine the generalization ability of foundation models. Despite their growing importance in chemoinformatics, the effectiveness of molecular representation learning has been hindered by limitations in existing small molecule datasets. To address this gap, we present MolPILE, large-scale, diverse, and rigorously curated collection of 222 million compounds, constructed from 6 large-scale databases using an automated curation pipeline. We present a comprehensive analysis of current pretraining datasets, highlighting considerable shortcomings for training ML models, and demonstrate how retraining existing models on MolPILE yields improvements in generalization performance. This work provides a standardized resource for model training, addressing the pressing need for an ImageNet-like dataset in molecular chemistry.

The segmentation of pelvic fracture fragments in CT and X-ray images is crucial for trauma diagnosis, surgical planning, and intraoperative guidance. However, accurately and efficiently delineating the bone fragments remains a significant challenge due to complex anatomy and imaging limitations. The PENGWIN challenge, organized as a MICCAI 2024 satellite event, aimed to advance automated fracture segmentation by benchmarking state-of-the-art algorithms on these complex tasks. A diverse dataset of 150 CT scans was collected from multiple clinical centers, and a large set of simulated X-ray images was generated using the DeepDRR method. Final submissions from 16 teams worldwide were evaluated under a rigorous multi-metric testing scheme. The top-performing CT algorithm achieved an average fragment-wise intersection over union (IoU) of 0.930, demonstrating satisfactory accuracy. However, in the X-ray task, the best algorithm attained an IoU of 0.774, highlighting the greater challenges posed by overlapping anatomical structures. Beyond the quantitative evaluation, the challenge revealed methodological diversity in algorithm design. Variations in instance representation, such as primary-secondary classification versus boundary-core separation, led to differing segmentation strategies. Despite promising results, the challenge also exposed inherent uncertainties in fragment definition, particularly in cases of incomplete fractures. These findings suggest that interactive segmentation approaches, integrating human decision-making with task-relevant information, may be essential for improving model reliability and clinical applicability.

Multi-class segmentation of the aorta in computed tomography angiography (CTA) scans is essential for diagnosing and planning complex endovascular treatments for patients with aortic dissections. However, existing methods reduce aortic segmentation to a binary problem, limiting their ability to measure diameters across different branches and zones. Furthermore, no open-source dataset is currently available to support the development of multi-class aortic segmentation methods. To address this gap, we organized the AortaSeg24 MICCAI Challenge, introducing the first dataset of 100 CTA volumes annotated for 23 clinically relevant aortic branches and zones. This dataset was designed to facilitate both model development and validation. The challenge attracted 121 teams worldwide, with participants leveraging state-of-the-art frameworks such as nnU-Net and exploring novel techniques, including cascaded models, data augmentation strategies, and custom loss functions. We evaluated the submitted algorithms using the Dice Similarity Coefficient (DSC) and Normalized Surface Distance (NSD), highlighting the approaches adopted by the top five performing teams. This paper presents the challenge design, dataset details, evaluation metrics, and an in-depth analysis of the top-performing algorithms. The annotated dataset, evaluation code, and implementations of the leading methods are publicly available to support further research. All resources can be accessed at this https URL

We present scg-cli, a~command line tool facilitating software comprehension. The tool extracts semantic information about code structure and dependencies from the Java and Scala projects, and structures it as a~Semantic Code Graph (SCG), an information model underlying scg-cli. The SCG data, once written into a~portable, open protobuf-based format, can be used by the scg-cli command line tool to obtain project metrics, find the most critical code entities, and compute project partitionings. The results of this analysis and the SCG data can be exported for further investigation by external tools such as Gephi software (visualization) and, notably, as a Jupyter Notebook environment with helper APIs to enable advanced analysis of the project using data analytics methods. We explain functionalities of the scg-cli tool and demonstrate its capabilities by showing an example analysis of an open-source Java project commons-io.