Related papers: Are Your Epochs Too Epic? Batch Free Can Be Harmfu…

In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching systems improve hit rates mainly through…

Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding space. These embeddings can be retrieved efficiently, aiding…

The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model…

State-of-the-art techniques for addressing scaling-related main memory errors identify and repair bits that are at risk of error from within the memory controller. Unfortunately, modern main memory chips internally use on-die error…

As memory technologies continue to shrink and memory error rates increase, the demand for stronger reliability becomes increasingly critical. Fine-grain memory replication has emerged as an appealing approach to improving memory fault…

This paper presents a new strategy for scheduling soft real-time tasks on multiple identical cores. The proposed approach is based on partitioned CPU reservations and it uses a reclaiming mechanism to reduce the number of missed deadlines.…

Test-time compute allocation in large reasoning models (LRMs) is widely used and has applications in mathematical problem solving, code synthesis, and planning. Recent work has addressed this problem by scaling self-consistency and parallel…

We introduce \emph{Adaptive RAG Memory} (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a \emph{dynamic} memory substrate governed by selective remembrance and decay. Frequently retrieved…

Entity Resolution (ER) is typically implemented as a batch task that processes all available data before identifying duplicate records. However, applications with time or computational constraints, e.g., those running in the cloud, require…

Recent neural network models for algorithmic tasks have led to significant improvements in extrapolation to sequences much longer than training, but it remains an outstanding problem that the performance still degrades for very long or…

While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from three fundamental challenges: decomposition errors, where…

In-memory deep learning computes neural network models where they are stored, thus avoiding long distance communication between memory and computation units, resulting in considerable savings in energy and time. In-memory deep learning has…

The push-relabel algorithm is an efficient algorithm that solves the maximum flow/ minimum cut problems of its affinity to parallelization. As the size of graphs grows exponentially, researchers have used Graphics Processing Units (GPUs) to…

Energy efficient mobility management is an important problem in modern wireless networks with heterogeneous cell sizes and increased nodes densities. We show that optimization-based mobility protocols cannot achieve long-term optimal energy…

Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called catastrophic forgetting, wherein they…

Voltage underscaling below the nominal level is an effective solution for improving energy efficiency in digital circuits, e.g., Field Programmable Gate Arrays (FPGAs). However, further undervolting below a safe voltage level and without…

Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. This highlights the need for a versatile compute-memory…

A new class of exact-repair regenerating codes is constructed by stitching together shorter erasure correction codes, where the stitching pattern can be viewed as block designs. The proposed codes have the "help-by-transfer" property where…

With the rapid advancement of large language models (LLMs), retrieval-augmented generation (RAG) has emerged as a critical approach to supplement the inherent knowledge limitations of LLMs. However, due to the typically large volume of…

Understanding the performance of data-parallel workloads when resource-constrained has significant practical importance but unfortunately has received only limited attention. This paper identifies, quantifies and demonstrates memory…