Search

The same computations are often expressed differently across software projects and programming languages. In particular, how computations involving loops are expressed varies due to the many possibilities to permute and compose loops. Since each variant may have unique performance properties, automatic approaches to loop scheduling must support many different optimization recipes. In this paper, we propose a priori loop nest normalization to align loop nests and reduce the variation before the optimization. Specifically, we define and apply normalization criteria, mapping loop nests with different memory access patterns to the same canonical form. Since the memory access pattern is susceptible to loop variations and critical for performance, this normalization allows many loop nests to be optimized by the same optimization recipe. To evaluate our approach, we apply the normalization with optimizations designed for only the canonical form, improving the performance of many different loop nest variants. Across multiple implementations of 15 benchmarks using different languages, we outperform a baseline compiler in C on average by a factor of $21.13$, state-of-the-art auto-schedulers such as Polly and the Tiramisu auto-scheduler by $2.31$ and $2.89$, as well as performance-oriented Python-based frameworks such as NumPy, Numba, and DaCe by $9.04$, $3.92$, and $1.47$. Furthermore, we apply the concept to the CLOUDSC cloud microphysics scheme, an actively used component of the Integrated Forecasting System, achieving a 10% speedup over the highly-tuned Fortran code.

Unsupervised Domain Adaptation (UDA) aims to utilize labeled data from a source domain to solve tasks in an unlabeled target domain, often hindered by significant domain gaps. Traditional CNN-based methods struggle to fully capture complex domain relationships, motivating the shift to vision transformers like the Swin Transformer, which excel in modeling both local and global dependencies. In this work, we propose a novel UDA approach leveraging the Swin Transformer with three key modules. A Graph Domain Discriminator enhances domain alignment by capturing inter-pixel correlations through graph convolutions and entropy-based attention differentiation. An Adaptive Double Attention module combines Windows and Shifted Windows attention with dynamic reweighting to align long-range and local features effectively. Finally, a Cross-Feature Transform modifies Swin Transformer blocks to improve generalization across domains. Extensive benchmarks confirm the state-of-the-art performance of our versatile method, which requires no task-specific alignment modules, establishing its adaptability to diverse applications.

Accurate multispectral image matching presents significant challenges due to non-linear intensity variations across spectral modalities, extreme viewpoint changes, and the scarcity of labeled datasets. Current state-of-the-art methods are typically specialized for a single spectral difference, such as visibleinfrared, and struggle to adapt to other modalities due to their reliance on expensive supervision, such as depth maps or camera poses. To address the need for rapid adaptation across modalities, we introduce XPoint, a self-supervised, modular image-matching framework designed for adaptive training and fine-tuning on aligned multispectral datasets, allowing users to customize key components based on their specific tasks. XPoint employs modularity and self-supervision to allow for the adjustment of elements such as the base detector, which generates pseudoground truth keypoints invariant to viewpoint and spectrum variations. The framework integrates a VMamba encoder, pretrained on segmentation tasks, for robust feature extraction, and includes three joint decoder heads: two are dedicated to interest point and descriptor extraction; and a task-specific homography regression head imposes geometric constraints for superior performance in tasks like image registration. This flexible architecture enables quick adaptation to a wide range of modalities, demonstrated by training on Optical-Thermal data and fine-tuning on settings such as visual-near infrared, visual-infrared, visual-longwave infrared, and visual-synthetic aperture radar. Experimental results show that XPoint consistently outperforms or matches state-ofthe-art methods in feature matching and image registration tasks across five distinct multispectral datasets. Our source code is available at https://github.com/canyagmur/XPoint., Comment: 13 pages, 11 figures, 1 table, Journal

With the emergence of wireless sensor networks (WSNs), many traditional signal processing tasks are required to be computed in a distributed fashion, without transmissions of the raw data to a centralized processing unit, due to the limited energy and bandwidth resources available to the sensors. In this paper, we propose a distributed independent component analysis (ICA) algorithm, which aims at identifying the original signal sources based on observations of their mixtures measured at various sensor nodes. One of the most commonly used ICA algorithms is known as FastICA, which requires a spatial pre-whitening operation in the first step of the algorithm. Such a pre-whitening across all nodes of a WSN is impossible in a bandwidth-constrained distributed setting as it requires to correlate each channel with each other channel in the WSN. We show that an explicit network-wide pre-whitening step can be circumvented by leveraging the properties of the so-called Distributed Adaptive Signal Fusion (DASF) framework. Despite the lack of such a network-wide pre-whitening, we can still obtain the $Q$ least Gaussian independent components of the centralized ICA solution, where $Q$ scales linearly with the required communication load., Comment: 5 pages

Hexagonal boron nitride (hBN) has emerged as a compelling platform for both classical and quantum technologies. In particular, the past decade has witnessed a surge of novel ideas and developments, which may be overwhelming for newcomers to the field. This review provides an overview of the fundamental concepts and key applications of hBN, including quantum sensing, quantum key distribution, quantum computing, and quantum memory. Additionally, we highlight critical experimental and theoretical advances that have expanded the capabilities of hBN, in a cohesive and accessible manner. The objective is to equip readers with a comprehensive understanding of the diverse applications of hBN, and provide insights into ongoing research efforts., Comment: 23 pages, 8 figures, 1 table

MoXI is a new intermediate verification language introduced in 2024 to promote the standardization and open-source implementations for symbolic model checking by extending the SMT-LIB 2 language with constructs to define state-transition systems. The tool suite of MoXI provides a translator from MoXI to Btor2, which is a lower-level intermediate language for hardware verification, and a translation-based model checker, which invokes mature hardware model checkers for Btor2 to analyze the translated verification tasks. The extensibility of such a translation-based model checker is restricted because more complex theories, such as integer or real arithmetics, cannot be precisely expressed with bit-vectors of fixed lengths in Btor2. We present MoXIchecker, the first model checker that solves MoXI verification tasks directly. Instead of translating MoXI to lower-level languages, MoXIchecker uses the solver-agnostic library PySMT for SMT solvers as backend for its verification algorithms. MoXIchecker is extensible because it accommodates verification tasks involving more complex theories, not limited by lower-level languages, facilitates the implementation of new algorithms, and is solver-agnostic by using the API of PySMT. In our evaluation, MoXIchecker uniquely solved tasks that use integer or real arithmetics, and achieved a comparable performance against the translation-based model checker from the MoXI tool suite., Comment: 13 pages, 6 figures, 2 tables

Blind single image super-resolution (SISR) is a challenging task in image processing due to the ill-posed nature of the inverse problem. Complex degradations present in real life images make it difficult to solve this problem using na\"ive deep learning approaches, where models are often trained on synthetically generated image pairs. Most of the effort so far has been focused on solving the inverse problem under some constraints, such as for a limited space of blur kernels and/or assuming noise-free input images. Yet, there is a gap in the literature to provide a well-generalized deep learning-based solution that performs well on images with unknown and highly complex degradations. In this paper, we propose IKR-Net (Iterative Kernel Reconstruction Network) for blind SISR. In the proposed approach, kernel and noise estimation and high-resolution image reconstruction are carried out iteratively using dedicated deep models. The iterative refinement provides significant improvement in both the reconstructed image and the estimated blur kernel even for noisy inputs. IKR-Net provides a generalized solution that can handle any type of blur and level of noise in the input low-resolution image. IKR-Net achieves state-of-the-art results in blind SISR, especially for noisy images with motion blur., Comment: 17 pages, 13 figures. The code of this paper is available in github: https://github.com/hfates/IKR-Net

Reference resolution is an important problem, one that is essential to understand and successfully handle context of different kinds. This context includes both previous turns and context that pertains to non-conversational entities, such as entities on the user's screen or those running in the background. While LLMs have been shown to be extremely powerful for a variety of tasks, their use in reference resolution, particularly for non-conversational entities, remains underutilized. This paper demonstrates how LLMs can be used to create an extremely effective system to resolve references of various types, by showing how reference resolution can be converted into a language modeling problem, despite involving forms of entities like those on screen that are not traditionally conducive to being reduced to a text-only modality. We demonstrate large improvements over an existing system with similar functionality across different types of references, with our smallest model obtaining absolute gains of over 5% for on-screen references. We also benchmark against GPT-3.5 and GPT-4, with our smallest model achieving performance comparable to that of GPT-4, and our larger models substantially outperforming it., Comment: Accepted at SIGDIAL 2024 (Oral presentation)

Successfully handling context is essential for any dialog understanding task. This context maybe be conversational (relying on previous user queries or system responses), visual (relying on what the user sees, for example, on their screen), or background (based on signals such as a ringing alarm or playing music). In this work, we present an overview of MARRS, or Multimodal Reference Resolution System, an on-device framework within a Natural Language Understanding system, responsible for handling conversational, visual and background context. In particular, we present different machine learning models to enable handing contextual queries; specifically, one to enable reference resolution, and one to handle context via query rewriting. We also describe how these models complement each other to form a unified, coherent, lightweight system that can understand context while preserving user privacy., Comment: Sixth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC 2023)

High-spatio-temporal resolution (HSTR) video recording plays a crucial role in enhancing various imagery tasks that require fine-detailed information. State-of-the-art cameras provide this required high frame-rate and high spatial resolution together, albeit at a high cost. To alleviate this issue, this paper proposes a dual camera system for the generation of HSTR video using reference-based super-resolution (RefSR). One camera captures high spatial resolution low frame rate (HSLF) video while the other captures low spatial resolution high frame rate (LSHF) video simultaneously for the same scene. A novel deep learning architecture is proposed to fuse HSLF and LSHF video feeds and synthesize HSTR video frames. The proposed model combines optical flow estimation and (channel-wise and spatial) attention mechanisms to capture the fine motion and complex dependencies between frames of the two video feeds. Simulations show that the proposed model provides significant improvement over existing reference-based SR techniques in terms of PSNR and SSIM metrics. The method also exhibits sufficient frames per second (FPS) for aerial monitoring when deployed on a power-constrained drone equipped with dual cameras., Comment: 15 pages, 8 figures, 8 tables

The distributed adaptive signal fusion (DASF) framework allows to solve spatial filtering optimization problems in a distributed and adaptive fashion over a bandwidth-constrained wireless sensor network. The DASF algorithm requires each node to sequentially build a compressed version of the original network-wide problem and solve it locally. However, these local problems can still result in a high computational load at the nodes, especially when the required solver is iterative. In this paper, we study the particular case of fractional programs, i.e., problems for which the objective function is a fraction of two continuous functions, which indeed require such iterative solvers. By exploiting the structure of a commonly used method for solving fractional programs and interleaving it with the iterations of the standard DASF algorithm, we obtain a distributed algorithm with a significantly reduced computational cost compared to the straightforward application of DASF as a meta-algorithm. We prove convergence and optimality of this "fractional DASF" (FDASF) algorithm and demonstrate its performance via numerical simulations.

Metal pollution onto white dwarfs is a wide-spread phenomenon that remains puzzling. Some of these white dwarfs also harbour gaseous debris disks. Emission lines from these disks open a unique window to the physical properties of the polluting material, lending insights to their origin. We model the emission line kinematics for the gas disk around SDSS J1228+1040, a system that has been monitored for over two decades. We show that the disk mass is strongly peaked at 1 solar radius (modulo the unknown inclination), and the disk eccentricity decreases from a value of 0.44 at the inner edge, to nearly zero at the outer edge. This eccentricity profile is exactly what one expects if the disk is in a global eccentric mode, precessing rigidly under general relativity and gas pressure. The precession period is about two decades. We infer that the mass of the gas disk is roughly equivalent to that of a 50-km rocky body, while the mass of the accompanying dust disk is likely insignificant. The disk eccentricity confirms an origin in tidal disruption, while the short disk diffusion time suggests that the disruption event happened a few centuries ago. Moreover, we argue that the initial orbit for the disrupted body, and that of its putative planetary perturber, fall within an AU around the white dwarf. The total mass of the source population is likely orders of magnitude more massive than our own Asteroid belt, and does not seem to exist around main-sequence stars., Comment: Accepted to AJ

With the rise of specialized hardware and new programming languages, code optimization has shifted its focus towards promoting data locality. Most production-grade compilers adopt a control-centric mindset - instruction-driven optimization augmented with scalar-based dataflow - whereas other approaches provide domain-specific and general purpose data movement minimization, which can miss important control-flow optimizations. As the two representations are not commutable, users must choose one over the other. In this paper, we explore how both control- and data-centric approaches can work in tandem via the Multi-Level Intermediate Representation (MLIR) framework. Through a combination of an MLIR dialect and specialized passes, we recover parametric, symbolic dataflow that can be optimized within the DaCe framework. We combine the two views into a single pipeline, called DCIR, showing that it is strictly more powerful than either view. On several benchmarks and a real-world application in C, we show that our proposed pipeline consistently outperforms MLIR and automatically uncovers new optimization opportunities with no additional effort., Comment: CGO'23

We propose Dual Cross-Attention (DCA), a simple yet effective attention module that is able to enhance skip-connections in U-Net-based architectures for medical image segmentation. DCA addresses the semantic gap between encoder and decoder features by sequentially capturing channel and spatial dependencies across multi-scale encoder features. First, the Channel Cross-Attention (CCA) extracts global channel-wise dependencies by utilizing cross-attention across channel tokens of multi-scale encoder features. Then, the Spatial Cross-Attention (SCA) module performs cross-attention to capture spatial dependencies across spatial tokens. Finally, these fine-grained encoder features are up-sampled and connected to their corresponding decoder parts to form the skip-connection scheme. Our proposed DCA module can be integrated into any encoder-decoder architecture with skip-connections such as U-Net and its variants. We test our DCA module by integrating it into six U-Net-based architectures such as U-Net, V-Net, R2Unet, ResUnet++, DoubleUnet and MultiResUnet. Our DCA module shows Dice Score improvements up to 2.05% on GlaS, 2.74% on MoNuSeg, 1.37% on CVC-ClinicDB, 1.12% on Kvasir-Seg and 1.44% on Synapse datasets. Our codes are available at: https://github.com/gorkemcanates/Dual-Cross-Attention, Comment: Code: https://github.com/gorkemcanates/Dual-Cross-Attention

Quantum emitters in solid-state crystals have recently attracted a lot of attention due to their simple applicability in optical quantum technologies. The polarization of single photons generated by quantum emitters is one of the key parameters that play a crucial role in the applications, such as quantum computation that uses the indistinguishability of photons. However, the degree of single photon polarization is typically quantified using time-averaged photoluminescence intensity of single emitters, which provides limited information about the dipole properties in solids. In this work, we use single defects in hexagonal boron nitride and nanodiamond as efficient room-temperature single photon sources to reveal the origin and the temporal evolution of dipole orientation in solid-state quantum emitters. The angle of excitation and emission dipoles relative to the crystal axes are determined experimentally and then calculated using density functional theory, which results in characteristic angles for every specific defect that can be used as an efficient tool for defect identification and understanding their atomic structure. Moreover, the temporal polarization dynamics reveal a strongly modified linear polarization visibility that depends on the excited state decay time of individual excitation. This effect can be traced back potentially to the excitation of excess charges in the local crystal environment. Understanding such hidden time-dependent mechanisms can further be used to improve the performance of polarization-sensitive experiments, in particular that of quantum communication with single photon emitters.

Wireless sensor networks consist of sensor nodes that are physically distributed over different locations. Spatial filtering procedures exploit the spatial correlation across these sensor signals to fuse them into a filtered signal satisfying some optimality condition. However, gathering the raw sensor data in a fusion center to solve the problem in a centralized way would lead to high energy and communication costs. The distributed adaptive signal fusion (DASF) framework has been proposed as a generic method to solve these signal fusion problems in a distributed fashion, which reduces the communication and energy costs in the network. The DASF framework assumes that there is a common goal across the nodes, i.e., the optimal filter is shared across the network. However, many applications require a node-specific objective, while all these node-specific objectives are still related via a common latent data model. In this work, we propose the DANSF algorithm which builds upon the DASF framework, and extends it to allow for node-specific spatial filtering problems., Comment: 5 pages

The brain effortlessly extracts latent causes of stimuli, but how it does this at the network level remains unknown. Most prior attempts at this problem proposed neural networks that implement independent component analysis which works under the limitation that latent causes are mutually independent. Here, we relax this limitation and propose a biologically plausible neural network that extracts correlated latent sources by exploiting information about their domains. To derive this network, we choose maximum correlative information transfer from inputs to outputs as the separation objective under the constraint that the outputs are restricted to their presumed sets. The online formulation of this optimization problem naturally leads to neural networks with local learning rules. Our framework incorporates infinitely many source domain choices and flexibly models complex latent structures. Choices of simplex or polytopic source domains result in networks with piecewise-linear activation functions. We provide numerical examples to demonstrate the superior correlated source separation capability for both synthetic and natural sources., Comment: ICLR Accepted, 34 pages

This paper studies the convergence conditions and properties of the distributed adaptive signal fusion (DASF) algorithm, the framework itself having been introduced in a `Part I' companion paper. The DASF algorithm can be used to solve linear signal and feature fusion optimization problems in a distributed fashion, and is in particular well-suited for solving spatial filtering optimization problems encountered in wireless sensor networks. The convergence conditions and results are provided along with rigorous proofs and analyses, as well as various example problems to which they apply. Additionally, we describe procedures that can be added to the DASF algorithm to ensure convergence in specific cases where some of the technical convergence conditions are not satisfied.

In this paper, we describe a general algorithmic framework for solving linear signal or feature fusion optimization problems in a distributed setting, for example in a wireless sensor network (WSN). These problems require linearly combining the observed signals (or features thereof) collected at the various sensor nodes to satisfy a pre-defined optimization criterion. The framework covers several classical spatial filtering problems, including minimum variance beamformers, multi-channel Wiener filters, principal component analysis, canonical correlation analysis, (generalized) eigenvalue problems, etc. The proposed distributed adaptive signal fusion (DASF) algorithm is an iterative method that solves these types of problems by allowing each node to share a linearly compressed version of the local sensor signal observations with its neighbors to reduce the energy and bandwidth requirements of the network. We first discuss the case of fully-connected networks and then extend the analysis to more general network topologies. The general DASF algorithm is shown to have several existing distributed algorithms from the literature as a special case, while at the same time allowing to solve new distributed problems as well with guaranteed convergence and optimality. This paper focuses on the algorithm derivation of the DASF framework along with simulations demonstrating its performance. A technical analysis along with convergence conditions and proofs are provided in a companion paper.

In this paper, a simple method is proposed to get analytical solutions (or with the help of a finite numerical calculations) of the Dirac-Weyl equation for low energy electrons in graphene in the presence of certain electric and magnetic fields. In order to decouple the Dirac-Weyl equation we have assumed a displacement symmetry of the system along a direction and some conditions on the magnetic and electric fields. The resulting equations have the natural form to apply the technique of supersymmetric quantum mechanics. The example of an electric well with square profile is worked out in detail to illustrate some of the most interesting features of this procedure., Comment: 15 pages, 6 figures

Within our international program to obtain accurate physical properties of trans-Neptunian objects (TNOs) we predicted a stellar occultation by the TNO (38628) Huya of the star Gaia DR2 4352760586390566400 (mG = 11.5 mag.) for March 18, 2019. After an extensive observational campaign, we updated the prediction and it turned out to be favorable to central Europe. Therefore, we mobilized half a hundred professional and amateur astronomers, and the occultation was finally detected from 21 telescopes located at 18 sites. This makes the Huya event one of the best ever observed stellar occultation by a TNO in terms of the number of chords. We determine accurate size, shape, and geometric albedo, and we also provide constraints on the density and other internal properties of this TNO. The 21 positive detections of the occultation by Huya allowed us to obtain well-separated chords which permitted us to fit an ellipse for the limb of the body at the moment of the occultation (i.e., the instantaneous limb) with kilometric accuracy. The projected semi-major and minor axes of the best ellipse fit obtained using the occultation data are (a', b') = (217.6 $\pm$ 3.5 km, 194.1 $\pm$ 6.1 km) with a position angle of the minor axis P' = 55.2 $\pm$ 9.1 degrees. From this fit, the projected area-equivalent diameter is 411.0 $\pm$ 7.3 km. This diameter is compatible with the equivalent diameter for Huya obtained from radiometric techniques (D = 406 $\pm$ 16 km). From this instantaneous limb, we obtained the geometric albedo for Huya (p$\rm_V$ = 0.079 $\pm$ 0.004) and we explored possible 3D shapes and constraints to the mass density for this TNO. We did not detect the satellite of Huya through this occultation, but the presence of rings or debris around Huya is constrained using the occultation data. We also derived an upper limit for a putative Pluto-like global atmosphere of about p$_{\rm surf}$ = 10 nbar., Comment: Accepted for publication in Astronomy & Astrophysics (30-April-2022). 19 pages, 7 figures