Researchers have proposed a solution to prevent personal language agents from leaking unauthorized information between different audiences. They sugge...
Researchers propose a new framework called QWM that combines Q-learning with world models to improve the performance of reinforcement learning agents....
Researchers have proposed an alternative formulation for active inference, a method used to select actions by minimizing expected free energy. The new...
Researchers have investigated whether Large Language Models (LLMs) can reason in a way that's meaningful in a legal context. They used cases from the ...
Researchers have developed a system to improve the durability and trustworthiness of AI audit records. This is achieved by binding each policy decisio...
Researchers have proposed a new approach to Contextual Reinforcement Learning (CRL), which involves pretraining a single policy and then fine-tuning i...
Researchers have developed a framework to optimize token usage and context window management in multi-agent AI workflows. The approach, based on inter...
Researchers have developed a web-based tool called Graphectory Viewer for analyzing software-agent trajectories. The tool transforms raw data into gra...
Researchers have developed an agent-centered architecture for general robot learning called Teach-and-Grow Learning (TGL). This approach allows robots...
Researchers have developed a framework called PACE to ensure the safety of AI agents in decentralized finance. PACE introduces typed transaction inten...
Researchers have developed a self-supervised framework called Delta2Gamma for detecting Alzheimer's disease using electroencephalography (EEG) recordi...
A new safety gate for multimodal large language models (MLLMs) called COMIC has been proposed to address a structural weakness in current defenses. Cu...