With the increasing number of edited videos, many robust video fingerprinting schemes have been proposed to solve the problem of video content authentication. However, most of them either deal with the temporal and sp...
详细信息
Recently, Neural Radiance Fields(NeRF) have shown remarkable performance in the task of novel view synthesis through multi-view. The present study introduces an advanced optimization framework, termed Pose Interpolati...
详细信息
Wireless sensor networks (WSNs) are networks with many sensor nodes that are utilized for various purposes, including the military and medical. In hazardous circumstances, precise data aggregation and routing are esse...
详细信息
When a crowdsourcing approach is used to assist the classification of a set of items,the main objective is to classify this set of items by aggregating the worker-provided labels.A secondary objective is to assess the...
详细信息
When a crowdsourcing approach is used to assist the classification of a set of items,the main objective is to classify this set of items by aggregating the worker-provided labels.A secondary objective is to assess the workers’skill levels in this process.A classical model that achieves both objectives is the famous Dawid-Skene *** this paper,we consider a third objective in this context,namely,to learn a classifier that is capable of labelling future items without further assistance of crowd *** extending the DawidSkene model to include the item features into consideration,we develop a Classification-Oriented Dawid Skene(CODS)model,which achieves the three objectives *** effectiveness of CODS on this three dimensions of the problem space is demonstrated experimentally.
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lac...
详细信息
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lack formality. In this paper, we propose how to improve NMT formality with large language models (LLMs), which combines the style transfer and evaluation capabilities of an LLM and the high-quality translation generation ability of NMT models to improve NMT formality. The proposed method (namely INMTF) encompasses two approaches. The first involves a revision approach using an LLM to revise the NMT-generated translation, ensuring a formal translation style. The second approach employs an LLM as a reward model for scoring translation formality, and then uses reinforcement learning algorithms to fine-tune the NMT model to maximize the reward score, thereby enhancing the formality of the generated translations. Considering the substantial parameter size of LLMs, we also explore methods to reduce the computational cost of INMTF. Experimental results demonstrate that INMTF significantly outperforms baselines in terms of translation formality and translation quality, with an improvement of +9.19 style accuracy points in the German-to-English task and +2.16 COMET score in the Russian-to-English task. Furthermore, our work demonstrates the potential of integrating LLMs within NMT frameworks to bridge the gap between NMT outputs and the formality required in various real-world translation scenarios.
We study Multi-Agent Path Finding for arrangements of labeled agents in the interior of a simply connected domain: Given a unique start and target position for each agent, the goal is to find a sequence of parallel, c...
详细信息
Federated recommender systems(FedRecs) have garnered increasing attention recently, thanks to their privacypreserving benefits. However, the decentralized and open characteristics of current FedRecs present at least t...
详细信息
Federated recommender systems(FedRecs) have garnered increasing attention recently, thanks to their privacypreserving benefits. However, the decentralized and open characteristics of current FedRecs present at least two ***, the performance of FedRecs is compromised due to highly sparse on-device data for each client. Second, the system's robustness is undermined by the vulnerability to model poisoning attacks launched by malicious users. In this paper, we introduce a novel contrastive learning framework designed to fully leverage the client's sparse data through embedding augmentation, referred to as CL4FedRec. Unlike previous contrastive learning approaches in FedRecs that necessitate clients to share their private parameters, our CL4FedRec aligns with the basic FedRec learning protocol, ensuring compatibility with most existing FedRec implementations. We then evaluate the robustness of FedRecs equipped with CL4FedRec by subjecting it to several state-of-the-art model poisoning attacks. Surprisingly, our observations reveal that contrastive learning tends to exacerbate the vulnerability of FedRecs to these attacks. This is attributed to the enhanced embedding uniformity, making the polluted target item embedding easily proximate to popular items. Based on this insight, we propose an enhanced and robust version of CL4FedRec(rCL4FedRec) by introducing a regularizer to maintain the distance among item embeddings with different popularity levels. Extensive experiments conducted on four commonly used recommendation datasets demonstrate that rCL4FedRec significantly enhances both the model's performance and the robustness of FedRecs.
This article reviews the electromagnetic framework used to model radio frequency interference (RFI) and the resulting development of mitigation methods. With the rise of IoT devices, wireless devices in which RF anten...
详细信息
By replacing the exponential decay function in the circular Airy beam (CAB) with a super-Gaussian function, we propose a novel abruptly autofocusing beam, the circular super-Gaussian Airy beam (CSGAB). Similar to CAB,...
详细信息
暂无评论