Related papers: SA-Kura: An Energy-Efficient Systolic Array Accele…

The Kuramoto phase diffusion equation is a nonlinear partial differential equation which describes the spatio-temporal evolution of a phase variable in an oscillatory reaction diffusion system. Synchronization manifests itself in a…

The parametric radiative transfer equation (RTE) arises in multi-query applications, such as design optimization, inverse problems, and uncertainty quantification, which require solving the RTE multiple times for various parameters.…

Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular…

We derive and prove the path-kernel formula for the linear response (parameter-derivative of averaged statistics) of SDEs. The parameter may affect the drift coefficient, the diffusion coefficient, and the initial condition. The formula…

Deploying adaptive intelligence at the edge remains challenging due to the high computational and energy cost of training neural models. Spiking Neural Networks (SNNs) offer a promising alternative, but enabling on-device learning requires…

The next significant step in the evolution and proliferation of artificial intelligence technology will be the integration of neural network (NN) models within embedded and mobile systems. This calls for the design of compact, energy…

Siamese trackers have been among the state-of-the-art solutions in each Visual Object Tracking (VOT) challenge over the past few years. However, with great accuracy comes great computational complexity: to achieve real-time processing,…

Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM…

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

Stencil codes are performance-critical in many compute-intensive applications, but suffer from significant address calculation and irregular memory access overheads. This work presents SARIS, a general and highly flexible methodology for…

We study diffusive shock acceleration (DSA) of protons and electrons at nonrelativistic, high Mach number, quasiparallel, collisionless shocks by means of self-consistent 1D particle-in-cell simulations. For the first time, both species are…

This paper presents SynapticCore-X, a modular and resource-efficient neural processing architecture optimized for deployment on low-cost FPGA platforms. The design integrates a lightweight RV32IMC RISC-V control core with a configurable…

Neuromorphic accelerators promise unparalleled energy efficiency and computational density for spiking neural networks (SNNs), especially in edge intelligence applications. However, most existing platforms exhibit rigid architectures with…

Hardware failures are a growing challenge for machine learning accelerators, many of which are based on systolic arrays. When a permanent hardware failure occurs in a systolic array, existing solutions include localizing and isolating the…

Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic…

While iterative stereo matching achieves high accuracy, its dependence on Recurrent Neural Networks (RNN) hinders edge deployment, a challenge underexplored in existing researches. We analyze iterative refinement and reveal that disparity…

As datasets continue to increase in size and multi-core computer architectures are developed, asynchronous parallel optimization algorithms become more and more essential to the field of Machine Learning. Unfortunately, conducting the…

This report summarizes the weak scaling performance of the diffusion-synthetic acceleration (DSA) of transport sweeps in PDT (a massively parallel deterministic transport solver developed at Texas A\&M University). It provides an assessment…

Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration…

Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a…