arXiv research

KalMamba improves RL efficiency with probabilistic SSMs.

The paper parallelizes HMM inference for efficient long-term computations.

In an era when the performance of a single compute device plateaus, software must be designed to scale on massively parallel systems for better runtime performance. However, in the context of training deep learning models, the popular back-propagation (BP) algorithm imposes a strong sequential dependency in the process…

Let $M_n$ be the topological moduli space of all parallel n-cables of long framed oriented knots in 3-space. We construct in a combinatorial way for each natural number $n>1$ a 1-cocycle $R_n$ which represents a non trivial class in $H^1(M_n; \mathbb{Z} [x_1,x_2,...,x_1^{-1},x_2^{-1},...])$, where the number of variabl…

A new parallel algorithm speeds up Hawkes process estimation.

The seemingly infinite diversity of the natural world arises from a relatively small set of coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give rise to regularities that can be discovered through primarily unsupervised experiences and represented as abstract concepts. If such r…

Accelerated magnetic resonance (MR) scan acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address this, we investigate deep residual learning networks to remove aliasing artifacts …

A fast deep learning method for parallel MRI without calibration.

Prototype for adaptive electron microscopy scans reduces dose and time.

Study $s$-invariants from $sl(3)$-link homology, extending to other characteristics.

Gibbs sampling is a Markov Chain Monte Carlo sampling technique that iteratively samples variables from their conditional distributions. There are two common scan orders for the variables: random scan and systematic scan. Due to the benefits of locality in hardware, systematic scan is commonly used, even though most st…

A new knot invariant using tangle-valued 1-cocycles.

It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework. Noting that the versatility of modern automatic differentiation frameworks is based in large part on the unifying concept of tensors, we describe a software a…

Scanning Transmission Electron Microscopy (STEM) has become the main stay for materials characterization on atomic level, with applications ranging from visualization of localized and extended defects to mapping order parameter fields. In the last several years, attention was attracted by potential of STEM to explore b…

Random scan CAVI converges linearly under log-concave assumptions.

New technique halves scan time for multi-echo MR images.

We introduce SparseVM, a method that registers clinical-quality 3D MR scans both faster and more accurately than previously possible. Deformable alignment, or registration, of clinical scans is a fundamental task for many clinical neuroscience studies. However, most registration algorithms are designed for high-resolut…

Adapts scanning algorithm for odd Khovanov homology.

pLSTM tackles long-range language modeling and computer vision tasks with parallelizable linear source transition mark networks.

Paper explores vulnerabilities in image authenticity detection methods, especially printing and scanning attacks.

Introduces a natural parallel translation for navigation data.

Early detection and precise characterization of emerging topics in text streams can be highly useful in applications such as timely and targeted public health interventions and discovering evolving regional business trends. Many methods have been proposed for detecting emerging events in text streams using topic modeli…

Paper reproduces a kernel-based scan B-statistic for online change-point detection.

For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework. VHE…

Brain imaging analysis on clinically acquired computed tomography (CT) is essential for the diagnosis, risk prediction of progression, and treatment of the structural phenotypes of traumatic brain injury (TBI). However, in real clinical imaging scenarios, entire body CT images (e.g., neck, abdomen, chest, pelvis) are t…

GAN normalizes CT scans for consistent radiomic feature values.

Classifies 4D metric Lie algebras with parallel skew-symmetric tensors.

New Gibbs sampling method improves MCMC efficiency.

We present some results on the boundedness of the mean curvature of proper biharmonic submanifolds in spheres. A partial classification result for proper biharmonic submanifolds with parallel mean curvature vector field in spheres is obtained. Then, we completely classify the proper biharmonic submanifolds in spheres w…

Deep learning predicts SAH patient mortality from initial CT scans.

A key open problem in M-theory is the identification of the degrees of freedom that are expected to be hidden at ADE-singularities in spacetime. Comparison with the classification of D-branes by K-theory suggests that the answer must come from the right choice of generalized cohomology theory for M-branes. Here we show…

Unified view of integrable systems linking CMC, isothermic, and Willmore surfaces.

We explain how the kind of ``parallel transport'' of a wavefunction used in discussing the Berry or Geometrical phase induces the conventional parallel transport of certain real vectors. These real vectors are associated with operators whose commutators yield diagonal operators; or in Lie algebras those operators whose…

This paper classifies flat submanifolds with a special type of curvature form.

Associative submanifolds $A$ in nearly parallel $G_2$-manifolds $Y$ are minimal 3-submanifolds in spin 7-manifolds with a real Killing spinor. The Riemannian cone over $Y$ has the holonomy group contained in ${\rm Spin(7)}$ and the Riemannian cone over $A$ is a Cayley submanifold. Infinitesimal deformations of associat…

Radiological imaging of the prostate is becoming more popular among researchers and clinicians in searching for diseases, primarily cancer. Scans might be acquired with different equipment or at different times for prognosis monitoring, with patient movement between scans, resulting in multiple datasets that need to be…

Study on generalized ξ-parallel maps in Riemannian geometry.

An almost complex manifolds $(M^4,J)$ of real dimension 4 with non-degenerate torsion bundle admit a double absolute parallelism and it is provided the classification of homogeneous $(M^4,J)$ having an associated non-solvable Lie algebra. We extend such a classification to the analysis of the manifolds having an associ…

Researchers use clustering to differentiate COVID-19 lung scans.

Paper studies second order symmetric parallel tensors in generalized f.pk-space forms.

Six AI solutions accurately detect growth plate planes in mice bone scans.

Future grid scenario analysis requires a major departure from conventional power system planning, where only a handful of most critical conditions is typically analyzed. To capture the inter-seasonal variations in renewable generation of a future grid scenario necessitates the use of computationally intensive time-seri…

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the deployment of deep neural networks on resource-limited edge devices. To address this …

In this paper, we present a novel massively parallel algorithm for accelerating the decision tree building procedure on GPUs (Graphics Processing Units), which is a crucial step in Gradient Boosted Decision Tree (GBDT) and random forests training. Previous GPU based tree building algorithms are based on parallel multi-…

This note addresses the construction of a notion of parallel transport along superpaths arising from the concept of a superconnection on a vector bundle over a manifold $M$. A superpath in $M$ is, loosely speaking, a path in $M$ together with an odd vector field in $M$ along the path. We also develop a notion of parall…

New examples of non-formal Sasaki-Einstein 7-manifolds and their submanifolds found.

We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging t…

Let M be a 7-manifold with a G2-structure defined by φ\inΩ^{3}_{+}(M). We prove that φ is conformal-Killing with respect to the associated metric g(φ) if and only if the G2-structure is nearly parallel. Let M be an 8-manifold with a Spin7-structure defined by ψ\inΩ^{4}_{+}(M). We prove that ψ is conformal-Killing with …