Related papers: Device-Conditioned Neural Architecture Search for …

Unsupervised pre-training approaches have achieved great success in many fields such as Computer Vision (CV), Natural Language Processing (NLP) and so on. However, compared to typical deep learning models, pre-training or even fine-tuning…

Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed model architecture or model architecture given fixed…

In recent years, Multifactorial Optimization (MFO) has gained a notable momentum in the research community. MFO is known for its inherent capability to efficiently address multiple optimization tasks at the same time, while transferring…

Deep learning models are increasingly deployed in safety-critical tasks where predictions must satisfy hard constraints, such as physical laws, fairness requirements, or safety limits. However, standard architectures lack built-in…

We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it…

The rapid growth of resource-constrained mobile platforms, including mobile robots, wearable systems, and Internet-of-Things devices, has increased the demand for computationally efficient neural network controllers (NNCs) that can operate…

Deep neural network (DNN)-based policy models, such as vision-language-action (VLA) models, excel at automating complex decision-making from multi-modal inputs. However, scaling these models greatly increases computational overhead,…

Multimodal image registration is a challenging but essential step for numerous image-guided procedures. Most registration algorithms rely on the computation of complex, frequently non-differentiable similarity metrics to deal with the…

Current quantum neural networks suffer from extreme sensitivity to both adversarial perturbations and hardware noise, creating a significant barrier to real-world deployment. Existing robustness techniques typically sacrifice clean accuracy…

Training deep neural networks (DNNs) with backpropagation (BP) achieves state-of-the-art accuracy but requires global error propagation and full parameterization, leading to substantial memory and computational overhead. Direct Feedback…

The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscores the pressing need to promptly establish certified safety…

Conventional optimization methods in machine learning and controls rely heavily on first-order update rules. Selecting the right method and hyperparameters for a particular task often involves trial-and-error or practitioner intuition,…

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic,…

The visual-question localized-answering (VQLA) system can serve as a knowledgeable assistant in surgical education. Except for providing text-based answers, the VQLA system can highlight the interested region for better surgical scene…

While recent vision-language-action models trained on diverse robot datasets exhibit promising generalization capabilities with limited in-domain data, their reliance on compact action heads to predict discretized or continuous actions…

Vision-Language-Action (VLA) models have advanced rapidly with stronger backbones, broader pre-training, and larger demonstration datasets, yet their action heads remain largely homogeneous: most directly predict action commands in a fixed…

Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained…

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…

High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…

This work presents a decentralized motion planning framework for addressing the task of multi-robot navigation using deep reinforcement learning. A custom simulator was developed in order to experimentally investigate the navigation problem…