Related papers: Analyzing a Two-Tier Disaggregated Memory Protecti…

Data deduplication saves storage space by identifying and removing repeats in the data stream. Compared with traditional compression methods, data deduplication schemes are more time efficient and are thus widely used in large scale storage…

Retrieval-augmented generation (RAG) has emerged as a paradigm for grounding large language models in external knowledge, yet most existing RAG systems assume centralized knowledge access and ample computation. These assumptions break down…

The parameter-efficient fine-tuning paradigm has garnered significant attention with the advancement of foundation models. Although numerous methods have been proposed to reduce the number of trainable parameters, their substantial memory…

Retrieval-Augmented Neural Machine Translation (RAMT) architectures retrieve examples from memory to guide the generation process. While most works in this trend explore new ways to exploit the retrieved examples, the upstream retrieval…

Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused…

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Dynamic graphs, featuring continuously updated vertices and edges, have grown in importance for numerous real-world applications. To accommodate this, graph frameworks, particularly their internal data structures, must support both…

Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires \emph{sequentially} computing two gradients, effectively doubling the per-iteration cost compared to base…

The current flash memory technology focuses on the cost minimization of its static storage capacity. However, the resulting approach supports a relatively small number of program-erase cycles. This technology is effective for consumer…

Affine rank minimization algorithms typically rely on calculating the gradient of a data error followed by a singular value decomposition at every iteration. Because these two steps are expensive, heuristic approximations are often used to…

Multimodal models trained on complete modality data often exhibit a substantial decrease in performance when faced with imperfect data containing corruptions or missing modalities. To address this robustness challenge, prior methods have…

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of…

Resistive random access memories (RRAM) are novel nonvolatile memory technologies, which can be embedded at the core of CMOS, and which could be ideal for the in-memory implementation of deep neural networks. A particularly exciting vision…

Despite the prevalence of retrieval-augmented language models (RALMs), the seamless integration of these models with retrieval mechanisms to enhance performance in document-based tasks remains challenging. While some post-retrieval…

Memory disaggregation has recently been adopted in data centers to improve resource utilization, motivated by cost and sustainability. Recent studies on large-scale HPC facilities have also highlighted memory underutilization. A promising…

Vulnerabilities emanating from DRAM errors pose a vexing problem that remains, as of yet, unsolved and elusive but cannot be ignored. Prior defenses focused on specific details of early RowHammer attacks and fail to generalize with the…

This paper addresses the issues of insufficient coverage, unstable results, and limited reliability in retrieval-augmented generation under complex knowledge environments, and proposes a confidence control method that integrates…

The resurgence of near-memory processing (NMP) with the advent of big data has shifted the computation paradigm from processor-centric to memory-centric computing. To meet the bandwidth and capacity demands of memory-centric computing, 3D…

Increasing storage density exacerbates DRAM read disturbance, a circuit-level vulnerability exploited by system-level attacks. Unfortunately, existing defenses are either ineffective or prohibitively expensive. Efficient mitigation is…