Related papers: Mitigating Wordline Crosstalk using Adaptive Trees…

A significant challenge for predictive maintenance in the pulp-and-paper industry is the infrequency of paper breaks during the production process. In this article, operational data is analyzed from a paper manufacturing machine in which…

In-Memory Computing (IMC) platforms such as analog crossbars are gaining focus as they facilitate the acceleration of low-precision Deep Neural Networks (DNNs) with high area- & compute-efficiencies. However, the intrinsic non-idealities in…

Recent advances in Retrieval-Augmented Generation (RAG) have shifted from simple vector similarity to structure-aware approaches like HippoRAG, which leverage Knowledge Graphs (KGs) and Personalized PageRank (PPR) to capture multi-hop…

Modern large reasoning models demonstrate impressive problem-solving capabilities by employing sophisticated reasoning strategies. However, they often struggle to balance efficiency and effectiveness, frequently generating unnecessarily…

We theoretically investigate cross-talk in hyperfine gate control of donor-qubit quantum computer architectures, in particular the Kane proposal. By numerically solving the Poisson and Schr\"{o}dinger equations for the gated donor system,…

Machine learning algorithms have made significant advances in many applications. However, their hardware implementation on the state-of-the-art platforms still faces several challenges and are limited by various factors, such as memory…

We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment. By the observed…

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization…

The random access methods used for support of machine-type communications (MTC) in current cellular standards are derivatives of traditional framed slotted ALOHA and therefore do not support high user loads efficiently. Motivated by the…

Large language models have limited context capacity, hindering reasoning over long conversations. We propose the Hierarchical Aggregate Tree memory structure to recursively aggregate relevant dialogue context through conditional tree…

A low-power Content-Addressable-Memory (CAM) is introduced employing a new mechanism for associativity between the input tags and the corresponding address of the output data. The proposed architecture is based on a recently developed…

Self-supervised topological deep learning (TDL) represents a nascent but underexplored area with significant potential for modeling higher-order interactions in simplicial complexes and cellular complexes to derive representations of…

We propose a technology-independent method, referred to as adjacent connection matrix (ACM), to efficiently map signed weight matrices to non-negative crossbar arrays. When compared to same-hardware-overhead mapping methods, using ACM leads…

This paper summarizes the idea of ChargeCache, which was published in HPCA 2016 [51], and examines the work's significance and future potential. DRAM latency continues to be a critical bottleneck for system performance. In this work, we…

Click-through rate (CTR) prediction plays an indispensable role in online platforms. Numerous models have been proposed to capture users' shifting preferences by leveraging user behavior sequences. However, these historical sequences often…

Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to overthink on simple problems, producing unnecessarily lengthy…

Recent advancements in large language models (LLMs) have shown remarkable potential in various complex tasks requiring multi-step reasoning methods like tree search to explore diverse reasoning paths. However, existing methods often suffer…

Chain-of-Thought (CoT) prompting has emerged as a powerful technique for enhancing language model's reasoning capabilities. However, generating long and correct CoT trajectories is challenging. Recent studies have demonstrated that Looped…

As Dynamic Random Access Memories (DRAM) scale, they are becoming increasingly susceptible to Row Hammer. By rapidly activating rows of DRAM cells (aggressor rows), attackers can exploit inter-cell interference through Row Hammer to flip…

Transformers usually expose one inference cost per trained model, while deployed systems often need multiple cost-quality operating points. We study Budgeted Attention Allocation, a monotone head-gating mechanism conditioned on a requested…