Related papers: POS-ISP: Pipeline Optimization at the Sequence Lev…
Understanding the steps required to perform a task is an important skill for AI systems. Learning these steps from instructional videos involves two subproblems: (i) identifying the temporal boundary of sequentially occurring segments and…
End-to-end (E2E) artificial intelligence (AI) pipelines are composed of several stages including data preprocessing, data ingestion, defining and training the model, hyperparameter optimization, deployment, inference, postprocessing,…
The simple assembly line balancing problem (SALBP) concerns the assignment of tasks with pre-defined processing times to work stations that are arranged in a line. Hereby, precedence constraints between the tasks must be respected. The…
Modern solutions to the single image super-resolution (SISR) problem using deep neural networks aim not only at better performance accuracy but also at a lighter and computationally efficient model. To that end, recently, neural…
The inspection-planning problem calls for computing motions for a robot that allow it to inspect a set of points of interest (POIs) while considering plan quality (e.g., plan length). This problem has applications across many domains where…
Intelligent reflecting surface (IRS) can be densely deployed in complex environment to create cascaded line-of-sight (LoS) paths between multiple base stations (BSs) and users via tunable IRS reflections, thereby significantly enhancing the…
Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking…
Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt…
Low-light Object detection is crucial for many real-world applications but remains challenging due to degraded image quality. While recent studies have shown that RAW images offer superior potential over RGB images, existing approaches…
Reconfigurable Intelligent Surfaces (RISs) are recently gaining remarkable attention as a low-cost, hardware-efficient, and highly scalable technology capable of offering dynamic control of electro-magnetic wave propagation. Their…
Recurrent Neural Networks (RNNs) have been shown to be valuable for constructing Intrusion Detection Systems (IDSs) for network data. They allow determining if a flow is malicious or not already before it is over, making it possible to take…
Selecting optimal parameters for a neural network architecture can often make the difference between mediocre and state-of-the-art performance. However, little is published which parameters and design choices should be evaluated or selected…
Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. However, manually designed prompts require expertise and…
In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classification is found to be easily misled by increasingly complex image…
In this paper, we propose a physical layer security (PLS) framework for an intelligent reflecting surface (IRS)-assisted integrated sensing and semantic communication (ISASC) system, where a multi-antenna dual-functional semantic base…
By activating blocked users and altering successive interference cancellation (SIC) sequences, reconfigurable intelligent surfaces (RISs) become promising for enhancing non-orthogonal multiple access (NOMA) systems. This work investigates…
To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…
Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in…
The proliferation of large-scale AI and data-intensive applications has driven the development of Computing Power Networks (CPN). It is a key paradigm for delivering ubiquitous, on-demand computational services with high efficiency.…
Beamforming design for intelligent reflecting surface (IRS)-assisted multi-user communication (IRS-MUC) systems critically depends on the acquisition of accurate channel state information (CSI). However, channel estimation (CE) in IRS-MUC…