Related papers: Reclaiming memory for lock-free data structures: t…
Distributed data storage systems are essential to deal with the need to store massive volumes of data. In order to make such a system fault-tolerant, some form of redundancy becomes crucial, incurring various overheads - most prominently in…
We introduce the hollow heap, a very simple data structure with the same amortized efficiency as the classical Fibonacci heap. All heap operations except delete and delete-min take $O(1)$ time, worst case as well as amortized; delete and…
With the increase of huge amounts of data in volume, velocity, and variety, the need for capacity of Redundant Arrays of Inexpensive Disks (RAID) storage systems is dramatically growing. However, the probability of disk failures in RAID…
Future generations of processors will exhibit an increase of faults over their lifetime, and it becomes increasingly expensive to solve the resulting reliability issues purely at the hardware level. We propose to model computations in terms…
Classifiers that can be implemented on chip with minimal computational and memory resources are essential for edge computing in emerging applications such as medical and IoT devices. This paper introduces a machine learning model based on…
Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize…
Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model…
Erasure coding (EC) affords data redundancy for large-scale systems. XOR-based EC is an easy-to-implement method for optimizing EC. This paper addresses a significant performance gap between the state-of-the-art XOR-based EC approach (with…
While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce…
Storing tabular data to balance storage and query efficiency is a long-standing research question in the database community. In this work, we argue and show that a novel DeepMapping abstraction, which relies on the impressive memorization…
Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input…
The Engram module -- a hash-keyed, O(1) associative memory injected into Transformer layers -- was recently shown to improve large language model pretraining, with the appealing interpretation that it provides a content-addressed shortcut…
Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on…
Processing in memory (PiM) represents a promising computing paradigm to enhance performance of numerous data-intensive applications. Variants performing computing directly in emerging nonvolatile memories can deliver very high energy…
Efficient low complexity error correcting code(ECC) is considered as an effective technique for mitigation of multi-bit upset (MBU) in the configuration memory(CM)of static random access memory (SRAM) based Field Programmable Gate Array…
We address the problem of unsupervised learning of complex articulated object models from 3D range data. We describe an algorithm whose input is a set of meshes corresponding to different configurations of an articulated object. The…
The amount of data available in the world is growing faster than our ability to deal with it. However, if we take advantage of the internal \emph{structure}, data may become much smaller for machine learning purposes. In this paper we focus…
Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…
With powerful and integrative large language models (LLMs), medical AI agents have demonstrated unique advantages in providing personalized medical consultations, continuous health monitoring, and precise treatment plans.…
MDS array codes are widely used in storage systems due to their computationally efficient encoding and decoding procedures. An MDS code with $r$ redundancy nodes can correct any $r$ node erasures by accessing all the remaining information…