Related papers: Is Bigger Always Better? Efficiency Analysis in Re…

With the increasing use of plastic, the challenges associated with managing plastic waste have become more challenging, emphasizing the need of effective solutions for classification and recycling. This study explores the potential of deep…

We introduce a stochastic version of the cutting-plane method for a large class of data-driven Mixed-Integer Nonlinear Optimization (MINLO) problems. We show that under very weak assumptions the stochastic algorithm is able to converge to…

Optimising the major next-generation cosmological surveys (such as {\em SNAP, KAOS etc...}) is a key problem given our ignorance of the physics underlying cosmic acceleration and the plethora of surveys planned. We propose a Bayesian design…

Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However,…

Object detection in high-resolution satellite imagery is emerging as a scalable alternative to on-the-ground survey data collection in many environmental and socioeconomic monitoring applications. However, performing object detection over…

Sensing and aggregation of noisy observations should not be considered as separate issues. The quality of collective estimation involves a difficult tradeoff between sensing quality which increases by increasing the number of sensors, and…

Despite the breakthrough deep learning performances achieved for automatic object detection, small target detection is still a challenging problem, especially when looking at fast and accurate solutions suitable for mobile or edge…

Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual…

Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse…

Object detection remains an active area of research in the field of computer vision, and considerable advances and successes has been achieved in this area through the design of deep convolutional neural networks for tackling object…

Drone-based target detection presents inherent challenges, such as the high density and overlap of targets in drone-based images, as well as the blurriness of targets under varying lighting conditions, which complicates identification.…

Spot spraying represents an efficient and sustainable method for reducing the amount of pesticides, particularly herbicides, used in agricultural fields. To achieve this, it is of utmost importance to reliably differentiate between crops…

Scaling RL for LLMs is computationally expensive, largely due to multi-sampling for policy optimization and evaluation, making efficient data selection crucial. Inspired by the Zone of Proximal Development (ZPD) theory, we hypothesize LLMs…

The integration of large-scale circuits and systems emphasizes the importance of automated defect detection of electronic components. The YOLO image detection model has been used to detect PCB defects and it has become a typical AI-assisted…

Enhancing the network architecture of the YOLO framework has been crucial for a long time, but has focused on CNN-based improvements despite the proven superiority of attention mechanisms in modeling capabilities. This is because…

Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets. This provides an efficient way for practitioners and researchers alike to compare…

This study compares the performance of state-of-the-art neural networks including variants of the YOLOv11 and RT-DETR models for detecting marsh deer in UAV imagery, in scenarios where specimens occupy a very small portion of the image and…

Mixture-of-Expert (MoE) based large language models (LLMs), such as the recent Mixtral and DeepSeek-MoE, have shown great promise in scaling model size without suffering from the quadratic growth of training cost of dense transformers. Like…

Mirrors can degrade the performance of computer vision models, but research into detecting them is in the preliminary phase. YOLOv4 achieves phenomenal results in terms of object detection accuracy and speed, but it still fails in detecting…

Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve…