Artificial intelligence (AI) and machine learning tools have proved to be highly effective in tackling various tasks that entail analyzing data and making accurate predictions. Despite their advantages, these tools have significant computational demands, and when...
Machine learning & AI
Flexible multi-task computation in recurrent neural networks relies on dynamical motifs, study shows
Cognitive flexibility, the ability to rapidly switch between different thoughts and mental concepts, is a highly advantageous human capability. This salient capability supports multi-tasking, the rapid acquisition of new skills and the adaptation to new situations.
A two-stage framework to improve LLM-based anomaly detection and reactive planning
Large language models (LLMs), such as OpenAI's ChatGPT, are known to be highly effective in answering a wide range of user queries, generalizing well across many natural language processing (NLP) tasks. Recently, some studies have also been exploring the potential of...
How working with AI impacts the collective attention of teams
The effectiveness of teamwork in professional and academic environments typically depends on various factors, including communication and coordinated attention. In this context, collective attention entails the ability of team members to cooperatively focus on the...
Why editing the knowledge of LLMs post-training can create messy ripple effects
After the advent of ChatGPT, the readily available model developed by Open AI, large language models (LLMs) have become increasingly widespread, with many online users now accessing them daily to quickly get answers to their queries, source information or produce...
A visual-linguistic framework that enables open-vocabulary object grasping in robots
To be deployed in a broad range of real-world dynamic settings, robots should be able to successfully complete various manual tasks, ranging from household chores to complex manufacturing or agricultural processes. These manual tasks entail grasping, manipulating and...
New learning-based method trains robots to reliably pick up and place objects
Most robotic systems developed to date can either tackle a specific task with high precision or complete a range of simpler tasks with low precision. For instance, some industrial robots can complete specific manufacturing tasks very well but cannot easily adapt to...
Lightweight neural network enables realistic rendering of woven fabrics in real-time
Recent advances in the field of artificial intelligence (AI) and computing have enabled the development of new tools for creating highly realistic media, virtual reality (VR) environments and video games. Many of these tools are now widely used by graphics designers,...
New framework allows robots to learn via online human demonstration videos
To be successfully deployed in real-world settings, robots should be capable of reliably completing various everyday tasks, ranging from household chores to industrial processes. Some of the tasks they could complete entail manipulating fabrics, for instance when...
New system enables intuitive teleoperation of a robotic manipulator in real-time
Imitation learning is a promising method to teach robots how to reliably complete everyday tasks, such as washing dishes or cooking. Despite their potential, imitation learning frameworks rely on detailed human demonstrations, which should include data that can help...