Related papers: ANTIC: Adaptive Neural Temporal In-situ Compressor
We investigate artificial compressibility (AC) techniques for the time discretization of the incompressible Navier-Stokes equations. The space discretization is based on a lowest-order face-based scheme supporting polytopal meshes, namely…
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…
Traditional computational fluid dynamics and physics-informed neural networks (PINNs) often suffer from high computational cost, mesh sensitivity, and reduced accuracy for strongly nonlinear and time-dependent flows. To address these…
We propose an end-to-end trained neural networkarchitecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on single-phase smoke simulations in 2D and 3D based on the incompressible…
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough…
Scientific discoveries are increasingly constrained by limited storage space and I/O capacities. For time-series simulations and experiments, their data often need to be decimated over timesteps to accommodate storage and I/O limitations.…
We describe Substitutional Neural Image Compression (SNIC), a general approach for enhancing any neural image compression model, that requires no data or additional tuning of the trained model. It boosts compression performance toward a…
Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g.,…
Deep learning has shown impressive performance in semantic segmentation, but it is still unaffordable for resource-constrained mobile devices. While offloading computation tasks is promising, the high traffic demands overwhelm the limited…
Spiking Neural Networks (SNNs), as a biologically plausible alternative to Artificial Neural Networks (ANNs), have demonstrated advantages in terms of energy efficiency, temporal processing, and biological plausibility. However, SNNs are…
Due to the very rapidly growing use of Artificial Neural Networks (ANNs) in real-world applications related to machine learning and Artificial Intelligence (AI), several hardware accelerator de-signs for ANNs have been proposed recently. In…
Despite its remarkable success in zero-shot image-text matching, CLIP remains highly vulnerable to adversarial perturbations on images. As adversarial fine-tuning is prohibitively costly, recent works explore various test-time defense…
Neural Image Compression (NIC) has revolutionized image compression with its superior rate-distortion performance and multi-task capabilities, supporting both human visual perception and machine vision tasks. However, its widespread…
Learned Image Compression (LIC) has shown remarkable progress in recent years. Existing works commonly employ CNN-based or self-attention-based modules as transform methods for compression. However, there is no prior research on neural…
Compressing massive LiDAR point clouds in real-time is critical to autonomous machines such as drones and self-driving cars. While most of the recent prior work has focused on compressing individual point cloud frames, this paper proposes a…
Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…
As supercomputers advance towards exascale capabilities, computational intensity increases significantly, and the volume of data requiring storage and transmission experiences exponential growth. Adaptive Mesh Refinement (AMR) has emerged…
Generative model based image lossless compression algorithms have seen a great success in improving compression ratio. However, the throughput for most of them is less than 1 MB/s even with the most advanced AI accelerated chips, preventing…
High-Performance Computing (HPC) systems provide input/output (IO) performance growing relatively slowly compared to peak computational performance and have limited storage capacity. Computational Fluid Dynamics (CFD) applications aiming to…
High-energy, large-scale particle colliders in nuclear and high-energy physics generate data at extraordinary rates, reaching up to $1$ terabyte and several petabytes per second, respectively. The development of real-time, high-throughput…