Search

In recent years, machine learning (ML) based reconstruction has been widely investigated and employed in cardiac magnetic resonance (CMR) imaging. ML-based reconstructions can deliver clinically acceptable image quality under substantially accelerated scans. ML-based reconstruction, however, also requires substantial data and computational time to train the neural network, which is often optimized for a fixed acceleration rate or image contrast. In practice, imaging parameters are often tuned to best suit the diagnosis, which may differ from the training data. This can result in degraded image quality, and multiple trained networks are needed to fulfill the clinical demands. In this study, we propose a foundation model that uses adaptive unrolling, channel-shifting, and Pattern and Contrast-Prompt-UNet (PCP-UNet) to tackle the problem. In particular, the undersampled data goes through a different number of unrolled iterations according to its acceleration rate. Channel-shifting improves reconstructed data quality. The PCP-UNet is equipped with an image contrast and sampling pattern prompt. In vivo CMR experiments were performed using mixed combinations of image contrasts, acceleration rates, and (under)sampling patterns. The proposed foundation model has significantly improved image quality for a wide range of CMR protocols and outperforms the conventional ML-based method., Comment: For MICCAI CMRxRecon Challenge 2024 team CardiAxs

Gravitational lensing is the phenomenon arising when light rays are deflected by the mass between the source and the observer. Largely magnified and highly distorted images of background galaxies are formed by these angular deflections if the deflecting mass distribution and the background sources align. As the most massive gravitationally bound objects in the universe, galaxy clusters are places where such alignments are usually found. By carefully analyzing the images of lensed galaxies, one can measure the mass, both visible and invisible, along the line-of-sight. These measurements are crucial in investigating the nature of dark matter, which constitutes most of the mass within clusters. Existing lensing analysis methods typically forward model the multiple images of dozens of background galaxies lensed by the cluster. To make this forward modeling computationally tractable, these multiple images are reduced to a much smaller summary data vector, which includes the locations, magnifications, and distortions. Our work avoids this loss of information by forward modeling the data at pixel-level. We develop a parametric model for the angular deflections near the bright arcs that allows us to control the shape of the curve that gives the directions of the eigenvectors of the Jacobian of the lensing matrix. The bright and extended images often follow such curves. We apply our analysis method to the bright arcs in gravitational lenses SDSS J1110+6459 and SDSS J0004-0103. We present our lens and source reconstructions for each system. With the application of our new method to many other lensing systems, we anticipate significant improvement in lens modeling near the critical curve, which will provide higher precision mass reconstructions for the deflectors. High-precision lens models allow for more robust de-lensing, which aids the studies of various highly magnified sources., Comment: 13 pages, 6 figures

The emergence of quantum technologies has brought much attention to the characterization of quantum resources as well as the classical simulatability of quantum processes. Quantum resources, as quantified by non-stabilizerness, have in one theoretical approach been linked to a family of entropic, monotonic functions. In this work, we demonstrate both analytically and numerically a simple relationship between non-stabilizerness and information scrambling using the fluctuations of an entropy-based quantifier. Specifically, we find that the non-stabilizerness generated by a random quantum circuit is proportional to fluctuations of mutual information. Furthermore, we explore the role of non-stabilizerness in measurement-induced entanglement phase transitions. We find that the fluctuations of mutual information decrease with increasing non-stabilizerness yielding potentially easier identification of the transition point. Our work establishes a key connection between quantum resource theory, information scrambling and measurement-induced entanglement phase transitions., Comment: 13 pages, 7 figures, code https://gitlab.com/QMAI/papers/mutualfluctuations

Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-training, offers promise for few-shot learning, aiding in manufacturability tasks where data can be limited. This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder. The pretrained model is evaluated across four manufacturability indicators obtained from CAM simulations: subtractive machining (SM) time, additive manufacturing (AM) time, residual von Mises stress, and blade collisions during Laser Power Bed Fusion process. Across all case studies, the model pre-trained by VIRL shows substantial enhancements on demonstrating improved generalizability with limited data and superior performance with larger datasets. Regarding deployment strategy, case-specific phenomenon exists where finetuning VIRL-pretrained models adversely affects AM tasks with limited data but benefits SM time prediction. Moreover, the efficacy of Low-rank adaptation (LoRA), which balances between probing and finetuning, is explored. LoRA shows stable performance akin to probing with limited data, while achieving a higher upper bound than probing as data size increases, without the computational costs of finetuning. Furthermore, static normalization of manufacturing indicators consistently performs well across tasks, while dynamic normalization enhances performance when a reliable task dependent input is available.

The massless fields in the universal NS-NS sector of string theory form $O(D, D)$ multiplets of Double Field Theory, which is a theory that provides a T-duality covariant formulation of supergravity, leading to a stringy modification of General Relativity. In this framework, it is possible to write down the extensions of the Einstein field equations and the Friedmann equations in such a way that the coupling of gravitational and matter sectors is dictated by the $O(D, D)$ symmetry universally. In this paper, we obtain the autonomous form of the $O(D, D)$-complete Friedmann equations, find the critical points and perform their stability analysis. We also include the phase portraits of the system. Cosmologically interesting cases of scalar field, radiation, and matter are separately considered and compared with the Chameleon models in a similar setting. Accelerating phases and the conditions for their existence are also given for such cases., Comment: 16 pages, 9 figures, matches the published version in The European Physical Journal C

Tens of thousands of galaxy-galaxy strong lensing systems are expected to be discovered by the end of the decade. These will form a vast new dataset that can be used to probe subgalactic dark matter structures through its gravitational effects, which will in turn allow us to study the nature of dark matter at small length scales. This work shows how we can leverage machine learning to search through the data and identify which systems are most likely to contain dark matter substructure and thus can be studied in greater depth. We use a UNet, an image segmentation architecture, on a simulated strongly-lensed dataset with realistic sources (COSMOS galaxies), lenses (power-law elliptical profiles with multipoles and external shear), and noise. Our machine learning algorithm is able to quickly detect most substructure at high image resolution and subhalo concentration. At a false positive rate of $10\%$, we are able to identify systems with substructure at a true positive rate of $71\%$ for a subhalo mass range of $10^{9}\text{-}10^{9.5}\,M_\odot$. While recent detections are consistent with higher concentrations, we find that our algorithm fails at detecting subhalos with lower concentrations (expected from $\Lambda$CDM simulations)., Comment: 8 pages, 5 figures

Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans. This review elucidates recent advances in MRI acceleration via data and physics-driven models, leveraging techniques from algorithm unrolling models, enhancement-based methods, and plug-and-play models to the emerging full spectrum of generative model-based methods. We also explore the synergistic integration of data models with physics-based insights, encompassing the advancements in multi-coil hardware accelerations like parallel imaging and simultaneous multi-slice imaging, and the optimization of sampling patterns. We then focus on domain-specific challenges and opportunities, including image redundancy exploitation, image integrity, evaluation metrics, data heterogeneity, and model generalization. This work also discusses potential solutions and future research directions, with an emphasis on the role of data harmonization and federated learning for further improving the general applicability and performance of these methods in MRI reconstruction., Comment: Accepted by IEEE Reviews in Biomedical Engineering (RBME)

Examining the properties of subhalos with strong gravitational lensing images can shed light on the nature of dark matter. From upcoming large-scale surveys, we expect to discover orders of magnitude more strong lens systems that can be used for subhalo studies. To optimally extract information from a large number of strong lensing images, machine learning provides promising avenues for efficient analysis that is unachievable with traditional analysis methods, but application of machine learning techniques to real observations is still limited. We build upon previous work, which uses a neural likelihood-ratio estimator, to constrain the effective density slopes of subhalos and demonstrate the feasibility of this method on real strong lensing observations. To do this, we implement significant improvements to the forward simulation pipeline and undertake careful model evaluation using simulated images. Ultimately, we use our trained model to predict the effective subhalo density slope from combining a set of strong lensing images taken by the \textit{Hubble Space Telescope}. We found the subhalo slope measurement of this set of observations to be steeper than the slope predictions of cold dark matter subhalos. Our result adds to several previous works that also measured high subhalo slopes in observations. Although a possible explanation for this is that subhalos with steeper slopes are easier to detect due to selection effects and thus contribute to statistical bias, our result nevertheless points to the need for careful analysis of more strong lensing observations from future surveys., Comment: 11 pages, 6 figures, v2; matches published version in MNRAS

Incorporating style-related objectives into shape design has been centrally important to maximize product appeal. However, stylistic features such as aesthetics and semantic attributes are hard to codify even for experts. As such, algorithmic style capture and reuse have not fully benefited from automated data-driven methodologies due to the challenging nature of design describability. This paper proposes an AI-driven method to fully automate the discovery of brand-related features. Our approach introduces BIGNet, a two-tier Brand Identification Graph Neural Network (GNN) to classify and analyze scalar vector graphics (SVG). First, to tackle the scarcity of vectorized product images, this research proposes two data acquisition workflows: parametric modeling from small curve-based datasets, and vectorization from large pixel-based datasets. Secondly, this study constructs a novel hierarchical GNN architecture to learn from both SVG's curve-level and chunk-level parameters. In the first case study, BIGNet not only classifies phone brands but also captures brand-related features across multiple scales, such as the location of the lens, the height-width ratio, and the screen-frame gap, as confirmed by AI evaluation. In the second study, this paper showcases the generalizability of BIGNet learning from a vectorized car image dataset and validates the consistency and robustness of its predictions given four scenarios. The results match the difference commonly observed in luxury vs. economy brands in the automobile market. Finally, this paper also visualizes the activation maps generated from a convolutional neural network and shows BIGNet's advantage of being a more human-friendly, explainable, and explicit style-capturing agent. Code and dataset can be found on Github: 1. Phone case study: github.com/parksandrecfan/bignet-phone 2. Car case study: github.com/parksandrecfan/bignet-car

Providing a stable connectivity in maritime communications is of utmost importance to unleash the full potential of smart ports. Nonetheless, due to the crowded nature of harbor environments, it is likely that some ships are shadowed by others, resulting in reduced received power that subsequently diminishes their data rates-even threatens basic connectivity requirements. Given that uncrewed aerial vehicles (UAVs) have been regarded as an integral part of future generations of wireless communication networks, they can be employed in maritime communications as well. In this paper, we investigate the use of UAV-mounted relays in order to help mitigate the reduced data rates of blocked links in maritime communications. Various communication architectures are considered based on the positioning mechanism of the UAV; in this regard, fixed, k-means algorithm-based, and landing spot-based positioning approaches are examined. Additionally, since UAVs are predominantly battery-operated, the energy consumption performances of these approaches are also measured. Results reveal that the landing spot-based UAV relay positioning approach finds the best trade-off between the data rate and energy consumption.

Strong gravitationally lensed arcs produced by galaxy clusters have been observationally detected for several decades now. These strong lensing constraints provided high-fidelity mass models for cluster lenses that include substructure down to $10^{9-10}\,\mathrm{M}_\odot$. Optimizing lens models, where the cluster mass distribution is modeled by a smooth component and subhalos associated with the locations of individual cluster galaxies, has enabled deriving the subhalo mass function, providing important constraints on the nature and granularity of dark matter. In this work, we explore and present a novel method to detect and measure individual perturbers (subhalos, line-of-sight halos, and wandering supermassive black holes) by exploiting their proximity to highly distorted lensed arcs in galaxy clusters, and by modeling the local lensing distortions with curved arc bases. This method offers the possibility of detecting individual low-mass perturber subhalos in clusters and halos along the line-of-sight down to a mass resolution of $10^8\,\mathrm{M}_\odot$. We quantify our sensitivity to low-mass perturbers ($M\sim 10^{7-9}\,\mathrm{M}_\odot$) in clusters ($M\sim 10^{14-15}\mathrm{M}_\odot$), by creating realistic mock data. Using three lensed images of a background galaxy in the cluster SMACS J0723, taken by the $\textit{James Webb Space Telescope}$, we study the retrieval of the properties of potential perturbers with masses $M=10^{7-9}\,\mathrm{M}_\odot$. From the derived posterior probability distributions for the perturber, we constrain its concentration, redshift, and ellipticity. By allowing us to probe lower-mass substructures, the use of curved arc bases can lead to powerful constraints on the nature of dark matter as discrimination between dark matter models appears on smaller scales., Comment: 18 pages, 21 figures, v2: matches published version in MNRAS

Building an AI agent that can design on its own has been a goal since the 1980s. Recently, deep learning has shown the ability to learn from large-scale data, enabling significant advances in data-driven design. However, learning over prior data limits us only to solve problems that have been solved before and biases data-driven learning towards existing solutions. The ultimate goal for a design agent is the ability to learn generalizable design behavior in a problem space without having seen it before. We introduce a self-learning agent framework in this work that achieves this goal. This framework integrates a deep policy network with a novel tree search algorithm, where the tree search explores the problem space, and the deep policy network leverages self-generated experience to guide the search further. This framework first demonstrates an ability to discover high-performing generative strategies without any prior data, and second, it illustrates a zero-shot generalization of generative strategies across various unseen boundary conditions. This work evaluates the effectiveness and versatility of the framework by solving multiple versions of two engineering design problems without retraining. Overall, this paper presents a methodology to self-learn high-performing and generalizable problem-solving behavior in an arbitrary problem space, circumventing the needs for expert data, existing solutions, and problem-specific learning., Comment: ASME. J. Mech. Des

We numerically examine the exterior solution of spherically symmetric and static configuration in scalar-tensor theories by using the nonminimally coupled scalar field with zero potential as our sample model. Our main purpose in this work is to fit the resulting data of the numerical solutions in the interested region by seeking for approximate analytical expressions which are weakly dependent of the parameters of a model, such as the nonminimal coupling constant in the present case. To this end, we determine the main forms of the mass and the metric functions in terms of the scalar field and their surface values. Then, we provide a function for the scalar field that contains only the mass and the radius of the configuration together with the surface and the asymptotic values of the scalar field. Therefore, we show that the exterior solution can be expressed in a form which does not depend on the parameters of a chosen model up to an order of accuracy around $10^{-5}$., Comment: 18 pages, 8 figures

In Video Instance Segmentation (VIS), current approaches either focus on the quality of the results, by taking the whole video as input and processing it offline; or on speed, by handling it frame by frame at the cost of competitive performance. In this work, we propose an online method that is on par with the performance of the offline counterparts. We introduce a message-passing graph neural network that encodes objects and relates them through time. We additionally propose a novel module to fuse features from the feature pyramid network with residual connections. Our model, trained end-to-end, achieves state-of-the-art performance on the YouTube-VIS dataset within the online methods. Further experiments on DAVIS demonstrate the generalization capability of our model to the video object segmentation task. Code is available at: \url{https://github.com/caganselim/TLTM}

Many dark matter (DM) models that are consistent with current cosmological data show differences in the predicted (sub)halo mass function, especially at sub-galactic scales, where observations are challenging due to the inefficiency of star formation. Strong gravitational lensing has been shown to be a useful tool for detecting dark low-mass (sub)halos through perturbations in lensing arcs, therefore allowing the testing of different DM scenarios. However, measuring the total mass of a perturber from strong lensing data is challenging. Over or underestimating perturber masses can lead to incorrect inferences about the nature of DM. In this paper, we argue that inferring an effective slope of the dark matter density profile, which is the power-law slope of perturbers at intermediate radii, where we expect the perturber to have the largest observable effect, is a promising way to circumvent these challenges. Using N-body simulations, we show that (sub)halo populations under different DM scenarios differ in their effective density slope distributions. Using realistic mocks of Hubble Space Telescope observations of strong lensing images, we show that the effective density slope of perturbers can be robustly measured with high enough accuracy to discern between different models. We also present our measurement of the effective density slope $\gamma=1.96\substack{+0.12 \\ -0.12}$ for the perturber in JVAS B1938+666, which we find to be a $2\sigma$ outlier of the cold dark matter scenario. More measurements of this kind are needed to be able to draw robust conclusions about the nature of dark matter., Comment: 23 pages, 18 figures, Matches MNRAS published version

Observations of structure at sub-galactic scales are crucial for probing the properties of dark matter, which is the dominant source of gravity in the universe. It will become increasingly important for future surveys to distinguish between line-of-sight halos and subhalos to avoid wrong inferences on the nature of dark matter. We reanalyze a sub-galactic structure (in lens JVAS B1938+666) that has been previously found using the gravitational imaging technique in galaxy-galaxy lensing systems. This structure has been assumed to be a satellite in the halo of the main lens galaxy. We fit the redshift of the perturber of the system as a free parameter, using the multi-plane thin-lens approximation, and find that the redshift of the perturber is $z_\mathrm{int} = 1.42\substack{+0.10 \\ -0.15}$ (with a main lens redshift of $z=0.881$). Our analysis indicates that this structure is more massive than the previous result by an order of magnitude. This constitutes the first dark perturber shown to be a line-of-sight halo with a gravitational lensing method., Comment: 15 pages, 2 tables, 15 figures. Code available at: https://github.com/acagansengul/interlopers_with_lenstronomy, v2: Modifications to analysis pipeline included, v3: Matches MNRAS published version

Generative design problems often encompass complex action spaces that may be divergent over time, contain state-dependent constraints, or involve hybrid (discrete and continuous) domains. To address those challenges, this work introduces Design Strategy Network (DSN), a data-driven deep hierarchical framework that can learn strategies over these arbitrary complex action spaces. The hierarchical architecture decomposes every action decision into first predicting a preferred spatial region in the design space and then outputting a probability distribution over a set of possible actions from that region. This framework comprises a convolutional encoder to work with image-based design state representations, a multi-layer perceptron to predict a spatial region, and a weight-sharing network to generate a probability distribution over unordered set-based inputs of feasible actions. Applied to a truss design study, the framework learns to predict the actions of human designers in the study, capturing their truss generation strategies in the process. Results show that DSNs significantly outperform non-hierarchical methods of policy representation, demonstrating their superiority in complex action space problems., Comment: Published in Journal of Mechanical Design

Engineering design problems often involve large state and action spaces along with highly sparse rewards. Since an exhaustive search of those spaces is not feasible, humans utilize relevant domain knowledge to condense the search space. Previously, deep learning agents (DLAgents) were introduced to use visual imitation learning to model design domain knowledge. This note builds on DLAgents and integrates them with one-step lookahead search to develop goal-directed agents capable of enhancing learned strategies for sequentially generating designs. Goal-directed DLAgents can employ human strategies learned from data along with optimizing an objective function. The visual imitation network from DLAgents is composed of a convolutional encoder-decoder network, acting as a rough planning step that is agnostic to feedback. Meanwhile, the lookahead search identifies the fine-tuned design action guided by an objective. These design agents are trained on an unconstrained truss design problem that is modeled as a sequential, action-based configuration design problem. The agents are then evaluated on two versions of the problem: the original version used for training and an unseen constrained version with an obstructed construction space. The goal-directed agents outperform the human designers used to train the network as well as the previous objective-agnostic versions of the agent in both scenarios. This illustrates a design agent framework that can efficiently use feedback to not only enhance learned design strategies but also adapt to unseen design problems.