A type of artificial intelligence that focuses on designing systems that can learn from and make decisions based on data.
The research paper explores the notion of ‘easy-to-hard generalization’ in language models. It addresses the problem of training models on hard data which is often difficult to label correctly. The…
Continue readingThe article presents a framework, ARCANE, for generating synthetic datasets to improve models predicting pedestrian intentions, crucial for autonomous driving. The lack of diverse datasets with crossing and non-crossing scenarios…
Continue readingThe article discusses the Model Parameter Randomisation Test (MPRT), a widely acknowledged method in the eXplainable Artificial Intelligence (XAI) community. However, recent studies have identified issues with the empirical interpretation…
Continue readingThis paper presents a novel approach to improving quadrotor control by adapting the trajectory generation component rather than changing the controller. The authors argue that this method can enhance trajectory…
Continue readingThe article introduces a learnable Perception-Action-Communication (LPAC) architecture for decentralized navigation in robot swarms, focusing on the coverage control problem. The proposed solution involves a convolution neural network (CNN) that…
Continue readingThis research focuses on improving the performance of quadrotor systems, particularly those used for payload delivery, which often experience aerodynamic wrenches. The study argues that instead of changing the controller,…
Continue readingThe article discusses reinforcement learning (RL) in multi-agent systems (MAS), focusing on innate-values-driven behaviors of AI agents. It introduces a hierarchical compound intrinsic value reinforcement learning model, termed IVRL, to…
Continue readingThis research paper by Dominik Baumann and Thomas B. Schon discusses safe reinforcement learning in the context of uncertain variables. The authors argue that most safe learning algorithms only consider…
Continue readingThis paper focuses on the development of a new tool, ViSual_IceD, a convolutional neural network (CNN) for improved sea ice detection. This tool builds upon the classic U-Net architecture and…
Continue readingRA VEN is a novel unconditional video generative model designed to address long-term spatial and temporal dependencies. It uses a hybrid explicit-implicit tri-plane representation to model an entire video sequence….
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
