Related papers: DCMF: A Dynamic Context Monitoring and Caching Fra…
Traditional KV cache eviction strategies, which discard less critical KV-pairs based on attention scores, often degrade generation quality, causing context loss or hallucinations. Recent efforts shift toward KV merging, merging eviction…
Effective performance profiling and analysis are essential for optimizing training and inference of deep learning models, especially given the growing complexity of heterogeneous computing environments. However, existing tools often lack…
The Internet of Things (IoT) has been continuously rising in the past few years, and its potentials are now more apparent. However, transient data generation and limited energy resources are the major bottlenecks of these networks. Besides,…
The operational lifetime of energy-harvesting wireless sensor nodes is limited by availability of the energy source and the capacity of the installed energy buffer. When a sensor node depletes its energy reserves, manual intervention is…
The development of materials science is undergoing a shift from empirical approaches to data-driven and algorithm-oriented research paradigm. The state-of-the-art platforms are confined to inorganic crystals, with limited chemical space,…
In this paper, we propose a dynamic shared context processing method based on DSC (Dynamic Shared Context) model, applied in an e-collaborative learning environment. Firstly, we present the model. This is a way to measure the relevance…
This paper considers the joint device activity detection and channel estimation problem in a massive Internet of Things (IoT) connectivity system, where a large number of IoT devices exist but merely a random subset of them become active…
The proliferation of cloud-native architectures, characterized by microservices and dynamic orchestration, has rendered modern IT infrastructures exceedingly complex and volatile. This complexity generates overwhelming volumes of…
Actual applications (mostly component based) requirements cannot be expressed without a ubiquitous and mobile part for end-users as well as for M2M applications (Machine to Machine). Such an evolution implies context management in order to…
The rapidly changing landscapes of modern optimization problems require algorithms that can be adapted in real-time. This paper introduces an Adaptive Metaheuristic Framework (AMF) designed for dynamic environments. It is capable of…
In an IoT environment, which is characterized by a multitude of interconnected smart devices with sensing and computational capabilities, many applications are (i) content-based, that is, they are only interested in finding a given type of…
We study asynchronous alignment, a first-class multimodal learning setting in which a dense primary stream must be fused with sporadic external context whose value depends on when it arrives. Unlike standard multimodal benchmarks that…
As modern data pipelines continue to collect, produce, and store a variety of data formats, extracting and combining value from traditional and context-rich sources such as strings, text, video, audio, and logs becomes a manual process…
We present ConXsense, the first framework for context-aware access control on mobile devices based on context classification. Previous context-aware access control systems often require users to laboriously specify detailed policies or they…
Despite recent progress in video generation, inference speed remains a major bottleneck. A common acceleration strategy involves reusing model outputs via caching mechanisms at fixed intervals. However, we find that such fixed-frequency…
In this study, we investigate a context-aware status updating system consisting of multiple sensor-estimator pairs. A centralized monitor pulls status updates from multiple sensors that are monitoring several safety-critical situations…
Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap:…
The field of building detection from remote sensing images has made significant progress, but faces challenges in achieving high-accuracy detection due to the diversity in building appearances and the complexity of vast scenes. To address…
Due to its low storage cost and fast query speed, cross-modal hashing (CMH) has been widely used for similarity search in multimedia retrieval applications. However, almost all existing CMH methods are based on hand-crafted features which…
The emergence of Internet of Things technology and recent advancement in sensor networks enabled transportation systems to a new dimension called Intelligent Transportation System. Due to increased usage of vehicles and communication among…