Related papers: AutoMat -- Automatic Differentiation for Generaliz…

As computing system become more complex, it is becoming harder for programmers to keep their codes optimized as the hardware gets updated. Autotuners try to alleviate this by hiding as many architecture-based optimization details as…

In this article, we discuss two specific classes of models - Gaussian Mixture Copula models and Mixture of Factor Analyzers - and the advantages of doing inference with gradient descent using automatic differentiation. Gaussian mixture…

Given a deep learning model trained on data from a source site, how to deploy the model to a target hospital automatically? How to accommodate heterogeneous medical coding systems across different hospitals? Standard approaches rely on…

We study parallel algorithms for the minimization of Deterministic Finite Automata (DFAs). In particular, we implement four different massively parallel algorithms on Graphics Processing Units (GPUs). Our results confirm the expectations…

We introduce a novel architecture for neural disparity refinement aimed at facilitating deployment of 3D computer vision on cheap and widespread consumer devices, such as mobile phones. Our approach relies on a continuous formulation that…

In recent years, researchers combine both audio and video signals to deal with challenges where actions are not well represented or captured by visual cues. However, how to effectively leverage the two modalities is still under development.…

The most important way to achieve higher performance in computer systems is through heterogeneous computing, i.e., by adopting hardware platforms containing more than one type of processor, such as CPUs, GPUs, and FPGAs. Several types of…

In recent years, general matrix-matrix multiplication with non-regular-shaped input matrices has been widely used in many applications like deep learning and has drawn more and more attention. However, conventional implementations are not…

Feature transformation plays a critical role in enhancing machine learning model performance by optimizing data representations. Recent state-of-the-art approaches address this task as a continuous embedding optimization problem, converting…

As the increasing complexity of Neural Network(NN) models leads to high demands for computation, AMD introduces a heterogeneous programmable system-on-chip (SoC), i.e., Versal ACAP architectures featured with programmable logic (PL), CPUs,…

3D Gaussian Splatting (3D GS) is widely adopted for novel view synthesis due to its high training and rendering efficiency. However, its efficiency relies on the key assumption that Gaussians do not overlap in the 3D space, which leads to…

We introduce a general formulation for automatic differentiation through direct form filters, yielding a closed-form backpropagation that includes initial condition gradients. The result is a single expression that can represent both the…

Existing 2D methods utilize UNet-based diffusion models to generate multi-view physically-based rendering (PBR) maps but struggle with multi-view inconsistency, while some 3D methods directly generate UV maps, encountering generalization…

We introduce the Normalized Matching Transformer (NMT), a deep learning approach for efficient and accurate sparse semantic keypoint matching between image pairs. NMT consists of a strong visual backbone, geometric feature refinement via…

We present a GPU-based system for automatic differentiation (AD) of functions defined on triangle meshes, designed to exploit the locality and sparsity in mesh-based computation. Our system evaluates derivatives using per-element…

Based on SGD, previous works have proposed many algorithms that have improved convergence speed and generalization in stochastic optimization, such as SGDm, AdaGrad, Adam, etc. However, their convergence analysis under non-convex conditions…

In recent years, the increasing popularity of Hi-DPI screens has driven a rising demand for high-resolution images. However, the limited computational power of edge devices poses a challenge in deploying complex super-resolution neural…

Meshfree simulation methods are emerging as compelling alternatives to conventional mesh-based approaches, particularly in the fields of Computational Fluid Dynamics (CFD) and continuum mechanics. In this publication, we provide a…

With the advent of self-driving cars and autonomous robots, it is imperative to detect road impairments like cracks and potholes and to perform necessary evading maneuvers to ensure fluid journey for on-board passengers or equipment. We…

In drug discovery, molecular docking aims at characterizing the binding of a drug-like molecule to a macromolecule. AutoDock-GPU, a state-of-the-art docking software, estimates the geometrical conformation of a docked ligand-protein complex…