Related papers: BRAVO -- Biased Locking for Reader-Writer Locks

We propose an annotation approach that captures not only labels but also the reading process underlying annotators' decisions, e.g., what parts of the text they focus on, re-read or skim. Using this framework, we conduct a case study on the…

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved efficiency and performance. Despite their benefits, MoE…

Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs). However, the limited expressive capacity of LoRA, stemming from the low-rank constraint, has been recognized as a…

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…

Non-orthogonal multiple access (NOMA) has been proposed for massive connectivity in future generations of wireless communications. A dominant NOMA scheme is based on power optimization, in which decoding of target user is assumed to be…

This paper proposes and optimizes a cooperative non-orthogonal multiple-access (Co-NOMA) scheme in the context of multicell visible light communications (VLC) networks, as a means to mitigate inter-cell interference in Co-NOMA-enabled…

This brief introduces a read bias circuit to improve readout yield of magnetic random access memories (MRAMs). A dynamic bias optimization (DBO) circuit is proposed to enable the real-time tracking of the optimal read voltage across…

Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…

Existing neural network calibration methods often treat calibration as a static, post-hoc optimization task. However, this neglects the dynamic and temporal nature of real-world inference. Moreover, existing methods do not provide an…

In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects. First, a reattention mechanism is proposed to refine current attentions by…

Recent advances in deep learning underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or private information through Machine Unlearning (MU). However,…

This work is focused on improving the character recognition capability of feed-forward back-propagation neural network by using one, two and three hidden layers and the modified additional momentum term. 182 English letters were collected…

Crossbar resistive memory with 1 Selector 1 Resistor (1S1R) structure is attractive for low-cost and high-density nonvolatile memory applications. As technology scales down to the single-nm regime, the increasing resistivity of…

The busy-forbidden protocol is a new readers-writer lock with no resource contention between readers, which allows it to outperform other locks. For its verification, specifications of its implementation and its less complex external…

The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…

In this work, we aim to evaluate different Distributed Lock Management service designs with Remote Direct Memory Access (RDMA). In specific, we implement and evaluate the centralized and the RDMA-enabled lock manager designs for fast…

Visible light communications (VLC) is gaining interest as one of the enablers of short-distance, high-data-rate applications, in future beyond 5G networks. Moreover, non-orthogonal multiple-access (NOMA)-enabled schemes have recently…

In cloud computing, storage area networks, remote backup storage, and similar settings, stored data is modified with updates from new versions. Representing information and modifying the representation are both expensive. Therefore it is…

Employing one or more additional classifiers to break the self-learning loop in tracing-by-detection has gained considerable attention. Most of such trackers merely utilize the redundancy to address the accumulating label error in the…

The pairwise reachability problem for a multi-threaded program asks, given control locations in two threads, whether they can be simultaneously reached in an execution of the program. The problem is important for static analysis and is used…