6 accepted papers
Beyond pick-place and quasi-static manipulation, robots are increasingly expected to perform more interactive and dynamic tasks in our daily life. However, it is still very challenging for the traditional manipulator because of its high stiffness and large mass/inertia. To address the above issues,
Mixture-of-Experts (MoE) architectures have demonstrated remarkable capabilities and scalability for large language models, but incur a prohibitive memory footprint due to duplicated expert parameters. Existing compression approaches, particularly those based on low-rank decomposition, typically ope…
Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack methods make unrealistic assumptions, assuming that all trainin…
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods for learning rich visual representations. Masked autoencoders (MAE), a recently proposed self-supervised method, has exhibited exemplary performance on many vision tasks by masking and reconstructing random pa…
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled. Existing attack methods construct such adversaries by randomly s…
Pedestrian detection has attracted enormous research attention in the field of Intelligent Transportation System (ITS) due to that pedestrians are the most vulnerable traffic participants. So far, almost all pedestrian detection solutions are based on the conventional frame-based camera. However, th…