3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact-free fly-throughs. Recent work started mitigating artifacts that break multi-view coherence, including popping artifacts due to inconsistent transparency sorting and perspective-correct outlines of (2D) splats. At the same time, real-time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective-correct 3D Gaussians while using a high-quality approximation of accurate blending, hybrid transparency, on a per-pixel level, in order to retain real-time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per-pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2$\times$ higher frame rates, 2$\times$ faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks.

We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world robotics, including active perception, agile full-body control, and long-horizon planning in a dynamic, partially-observable, multi-agent domain. We rely on large-scale, simulation-based data generation to obtain complex behaviors from egocentric vision which can be successfully transferred to physical robots using low-cost sensors. To achieve adequate visual realism, our simulation combines rigid-body physics with learned, realistic rendering via multiple Neural Radiance Fields (NeRFs). We combine teacher-based multi-agent RL and cross-experiment data reuse to enable the discovery of sophisticated soccer strategies. We analyze active-perception behaviors including object tracking and ball seeking that emerge when simply optimizing perception-agnostic soccer play. The agents display equivalent levels of performance and agility as policies with access to privileged, ground-truth state. To our knowledge, this paper constitutes a first demonstration of end-to-end training for multi-agent robot soccer, mapping raw pixel observations to joint-level actions, that can be deployed in the real world. Videos of the game-play and analyses can be seen on our website this https URL .

Recent advancements in massively multilingual machine translation systems have significantly enhanced translation accuracy; however, even the best performing systems still generate hallucinations, severely impacting user trust. Detecting hallucinations in Machine Translation (MT) remains a critical challenge, particularly since existing methods excel with High-Resource Languages (HRLs) but exhibit substantial limitations when applied to Low-Resource Languages (LRLs). This paper evaluates sentence-level hallucination detection approaches using Large Language Models (LLMs) and semantic similarity within massively multilingual embeddings. Our study spans 16 language directions, covering HRLs, LRLs, with diverse scripts. We find that the choice of model is essential for performance. On average, for HRLs, Llama3-70B outperforms the previous state of the art by as much as 0.16 MCC (Matthews Correlation Coefficient). However, for LRLs we observe that Claude Sonnet outperforms other LLMs on average by 0.03 MCC. The key takeaway from our study is that LLMs can achieve performance comparable or even better than previously proposed models, despite not being explicitly trained for any machine translation task. However, their advantage is less significant for LRLs.

The LUX-ZEPLIN (LZ) experiment is searching for dark matter interactions in a liquid xenon time projection chamber (LXe-TPC). This article demonstrates how control of the flow state in the LXe-TPC enables the identification of pairs of sequential alpha-decays, which are used to map fluid flow and ion drift in the liquid target. The resulting transport model is used to tag $^{214}$Pb beta-decays, a leading background to dark matter signals in LZ. Temporally evolving volume selections, at a cost of 9.0% of exposure, target the decay of each $^{214}$Pb atom up to 81 minutes after production, resulting in (63 $\pm$ 6$_{\mathrm{stat}}$ $\pm$ 7$_{\mathrm{sys}}$)% identification of $^{214}$Pb decays to ground state. We also demonstrate how flow-based tagging techniques enable a novel calibration side band that is concurrent with science data.

The LUX-ZEPLIN (LZ) experiment aims to detect rare interactions between dark matter particles and xenon. Although the detector is designed to be the most sensitive to GeV/$c^2$--TeV/$c^2$ Weakly Interacting Massive Particles (WIMPs), it is also capable of measuring low-energy ionization signals down to a single electron that may be produced by scatters of sub-GeV/$c^2$ dark matter. The major challenge in exploiting this sensitivity is to understand and suppress the ionization background in the few-electron regime. We report a characterization of the delayed electron backgrounds following energy depositions in the LZ detector under different detector conditions. In addition, we quantify the probability for photons to be emitted in coincidence with electron emission from the high voltage grids. We then demonstrate that spontaneous grid electron emission can be identified and rejected with a high efficiency using a coincident photon tag, which provides a tool to improve the sensitivity of future dark matter searches.

We present a novel locality-based learning method for cleaning and solving optical motion capture data. Given noisy marker data, we propose a new heterogeneous graph neural network which treats markers and joints as different types of nodes, and uses graph convolution operations to extract the local features of markers and joints and transform them to clean motions. To deal with anomaly markers (e.g. occluded or with big tracking errors), the key insight is that a marker's motion shows strong correlations with the motions of its immediate neighboring markers but less so with other markers, a.k.a. locality, which enables us to efficiently fill missing markers (e.g. due to occlusion). Additionally, we also identify marker outliers due to tracking errors by investigating their acceleration profiles. Finally, we propose a training regime based on representation learning and data augmentation, by training the model on data with masking. The masking schemes aim to mimic the occluded and noisy markers often observed in the real data. Finally, we show that our method achieves high accuracy on multiple metrics across various datasets. Extensive comparison shows our method outperforms state-of-the-art methods in terms of prediction accuracy of occluded marker position error by approximately 20%, which leads to a further error reduction on the reconstructed joint rotations and positions by 30%. The code and data for this paper are available at this https URL.

The separation of overlapping objects presents a significant challenge in scientific imaging. While deep learning segmentation-regression algorithms can predict pixel-wise intensities, they typically treat all regions equally rather than prioritizing overlap regions where attribution is most ambiguous. Recent advances in instance segmentation show that weighting regions of pixel overlap in training can improve segmentation boundary predictions in regions of overlap, but this idea has not yet been extended to segmentation regression. We address this with Overlap-Aware Segmentation of ImageS (OASIS): a new segmentation-regression framework with a weighted loss function designed to prioritize regions of object-overlap during training, enabling extraction of pixel intensities and topological features from heavily obscured objects. We demonstrate OASIS in the context of the MIGDAL experiment, which aims to directly image the Migdal effect--a rare process where electron emission is induced by nuclear scattering--in a low-pressure optical time projection chamber. This setting poses an extreme test case, as the target for reconstruction is a faint electron recoil track which is often heavily-buried within the orders-of-magnitude brighter nuclear recoil track. Compared to unweighted training, OASIS improves median intensity reconstruction errors from -32% to -14% for low-energy electron tracks (4-5 keV) and improves topological intersection-over-union scores from 0.828 to 0.855. These performance gains demonstrate OASIS's ability to recover obscured signals in overlap-dominated regions. The framework provides a generalizable methodology for scientific imaging where pixels represent physical quantities and overlap obscures features of interest. All code is openly available to facilitate cross-domain adoption.

The Data Acquisition System (DAQ) for the LUX-ZEPLIN (LZ) dark matter detector is described. The signals from 745 PMTs, distributed across three subsystems, are sampled with 100-MHz 32-channel digitizers (DDC-32s). A basic waveform analysis is carried out on the on-board Field Programmable Gate Arrays (FPGAs) to extract information about the observed scintillation and electroluminescence signals. This information is used to determine if the digitized waveforms should be preserved for offline analysis. The system is designed around the Kintex-7 FPGA. In addition to digitizing the PMT signals and providing basic event selection in real time, the flexibility provided by the use of FPGAs allows us to monitor the performance of the detector and the DAQ in parallel to normal data acquisition. The hardware and software/firmware of this FPGA-based Architecture for Data acquisition and Realtime monitoring (FADR) are discussed and performance measurements are described.

Replaying data is a principal mechanism underlying the stability and data efficiency of off-policy reinforcement learning (RL). We present an effective yet simple framework to extend the use of replays across multiple experiments, minimally adapting the RL workflow for sizeable improvements in controller performance and research iteration times. At its core, Replay Across Experiments (RaE) involves reusing experience from previous experiments to improve exploration and bootstrap learning while reducing required changes to a minimum in comparison to prior work. We empirically show benefits across a number of RL algorithms and challenging control domains spanning both locomotion and manipulation, including hard exploration tasks from egocentric vision. Through comprehensive ablations, we demonstrate robustness to the quality and amount of data available and various hyperparameter choices. Finally, we discuss how our approach can be applied more broadly across research life cycles and can increase resilience by reloading data across random seeds or hyperparameter variations.

Efficient automatic segmentation of multi-level (i.e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications. However, most existing methods concentrate only on main PA or branch PA segmentation separately and ignore segmentation efficiency. Besides, there is no public large-scale dataset focused on PA segmentation, which makes it highly challenging to compare the different methods. To benchmark multi-level PA segmentation algorithms, we organized the first \textbf{P}ulmonary \textbf{AR}tery \textbf{SE}gmentation (PARSE) challenge. On the one hand, we focus on both the main PA and the branch PA segmentation. On the other hand, for better clinical application, we assign the same score weight to segmentation efficiency (mainly running time and GPU memory consumption during inference) while ensuring PA segmentation accuracy. We present a summary of the top algorithms and offer some suggestions for efficient and accurate multi-level PA automatic segmentation. We provide the PARSE challenge as open-access for the community to benchmark future algorithm developments at \url{this https URL}.

Cyclists face a disproportionate risk of injury, yet conventional crash records are too limited to reconstruct the circumstances of incidents or to diagnose risk at the finer spatial and temporal detail needed for targeted interventions. Recently, naturalistic studies have gained traction as a way to capture the complex behavioural and infrastructural factors that contribute to crashes. These approaches typically involve the collection and analysis of video data. A video promising format is panoramic video, which can record 360-degree views around a rider. However, its use is limited by severe distortions, large numbers of small objects and boundary continuity. This study addresses these challenges by proposing a novel three-step framework: (1) enhancing object detection accuracy on panoramic imagery by segmenting and projecting the original 360-degree images into four perspective sub-images, thus reducing distortion; (2) modifying multi-object tracking models to incorporate boundary continuity and object category information for improved tracking consistency; and (3) validating the proposed approach through a real-world application focused on detecting overtaking manoeuvres by vehicles around cyclists. The methodology is evaluated using panoramic videos recorded by cyclists on London's roadways under diverse conditions. Experimental results demonstrate notable improvements over baseline methods, achieving higher average precision across varying image resolutions. Moreover, the enhanced tracking approach yields a 3.0% increase in multi-object tracking accuracy and a 4.6% improvement in identification F-score. The overtaking detection task achieves a high F-score of 0.81, illustrating the practical effectiveness of the proposed method in real-world cycling safety scenarios. The code is available on GitHub (this https URL) to ensure reproducibility.

The integration of sensing and communication (ISAC) functionalities have recently gained significant research interest as a hardware-, power-, spectrum- and cost- efficient solution. This experimental work focuses on a dual-functional radar sensing and communication framework where a single radiation waveform, either omnidirectional or directional, can realize both radar sensing and communication functions. We study a trade-off approach that can balance the performance of communications and radar sensing. We design an orthogonal frequency division multiplexing (OFDM) based multi-user multiple input multiple output (MIMO) software-defined radio (SDR) testbed to validate the dual-functional model. We carry out over-the-air experiments to investigate the optimal trade-off factor to balance the performance for both functions. On the radar performance, we measure the output beampatterns of our transmission to examine their similarity to simulation based beampatterns. On the communication side, we obtain bit error rate (BER) results from the testbed to show the communication performance using the dual-functional waveform. Our experiment reveals that the dual-functional approach can achieve comparable BER performance with pure communication-based solutions while maintaining fine radar beampatterns simultaneously.

While functional Magnetic Resonance Imaging (fMRI) offers valuable insights into cognitive processes, its inherent spatial limitations pose challenges for detailed analysis of the fine-grained functional architecture of the brain. More specifically, MRI scanner and sequence specifications impose a trade-off between temporal resolution, spatial resolution, signal-to-noise ratio, and scan time. Deep Learning (DL) Super-Resolution (SR) methods have emerged as a promising solution to enhance fMRI resolution, generating high-resolution (HR) images from low-resolution (LR) images typically acquired with lower scanning times. However, most existing SR approaches depend on supervised DL techniques, which require training ground truth (GT) HR data, which is often difficult to acquire and simultaneously sets a bound for how far SR can go. In this paper, we introduce a novel self-supervised DL SR model that combines a DL network with an analytical approach and Total Variation (TV) regularization. Our method eliminates the need for external GT images, achieving competitive performance compared to supervised DL techniques and preserving the functional maps.

The LZ experiment is a liquid xenon time-projection chamber (TPC) searching for evidence of particle dark matter interactions. In the simplest assumption of elastic scattering, many dark matter models predict an energy spectrum which rises quasi-exponentially with decreasing energy transfer to a target atom. LZ expects to detect coherent neutrino-nucleus scattering of $^{8}$B solar neutrinos, the signal from which is very similar to a dark matter particle with mass of about 5.5 GeV/$c^{2}$, which result in typical nuclear recoil energies of <5 keV$_{\text{nr}}$. Therefore, it is of crucial importance to calibrate the response of recoiling xenon nuclei to keV-energy recoils. This analysis details the first in situ photoneutron calibration of the LZ detector and probes its response in this energy regime.

Recent advancements in Large Language Models (LLMs) have positioned them as powerful tools for clinical decision-making, with rapidly expanding applications in healthcare. However, concerns about bias remain a significant challenge in the clinical implementation of LLMs, particularly regarding gender and ethnicity. This research investigates the evaluation and mitigation of bias in LLMs applied to complex clinical cases, focusing on gender and ethnicity biases. We introduce a novel Counterfactual Patient Variations (CPV) dataset derived from the JAMA Clinical Challenge. Using this dataset, we built a framework for bias evaluation, employing both Multiple Choice Questions (MCQs) and corresponding explanations. We explore prompting with eight LLMs and fine-tuning as debiasing methods. Our findings reveal that addressing social biases in LLMs requires a multidimensional approach as mitigating gender bias can occur while introducing ethnicity biases, and that gender bias in LLM embeddings varies significantly across medical specialities. We demonstrate that evaluating both MCQ response and explanation processes is crucial, as correct responses can be based on biased \textit{reasoning}. We provide a framework for evaluating LLM bias in real-world clinical cases, offer insights into the complex nature of bias in these models, and present strategies for bias mitigation.

Traffic accidents present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic accident prediction model is crucial to addressing growing public safety concerns and enhancing the safety of urban mobility systems. Traditional methods face limitations at fine spatiotemporal scales due to the sporadic nature of highrisk accidents and the predominance of non-accident characteristics. Furthermore, while most current models show promising occurrence prediction, they overlook the uncertainties arising from the inherent nature of accidents, and then fail to adequately map the hierarchical ranking of accident risk values for more precise insights. To address these issues, we introduce the Spatiotemporal Zero-Inflated Tweedie Graph Neural Network STZITDGNN -- the first uncertainty-aware probabilistic graph deep learning model in roadlevel traffic accident prediction for multisteps. This model integrates the interpretability of the statistical Tweedie family model and the expressive power of graph neural networks. Its decoder innovatively employs a compound Tweedie model,a Poisson distribution to model the frequency of accident occurrences and a Gamma distribution to assess injury severity, supplemented by a zeroinflated component to effectively identify exessive nonincident instances. Empirical tests using realworld traffic data from London, UK, demonstrate that the STZITDGNN surpasses other baseline models across multiple benchmarks and metrics, including accident risk value prediction, uncertainty minimisation, non-accident road identification and accident occurrence accuracy. Our study demonstrates that STZTIDGNN can effectively inform targeted road monitoring, thereby improving urban road safety strategies.

This study developed an improved dog heart rate and blood oxygen sensor system using Arduino. Traditional methods face accuracy and reliability issues. Our system integrates advanced computational techniques with hardware-based sensing to enhance measurement precision. An Arduino microcontroller connected to a heart rate and blood oxygen sensor collects raw data, which is preprocessed and filtered to remove noise. Experimental plans include long-term monitoring of multiple dogs and comparative analysis with traditional methods to validate the system's effectiveness, aiming for widespread use in the home or veterinary clinics. Additionally, the system offers dog owners the possibility to interact with their virtual dogs in the metaverse using AR/VR, allowing them to better understand their real dogs' health conditions by observing their virtual health status.