Researchers have developed a method for safe reinforcement learning called adaptive probabilistic shielding. In traditional reinforcement learning, an...
Repo0 is a framework for generating code from natural-language requirements without assuming a predefined repository architecture. It uses a Dual-Dire...
Researchers have developed a new self-supervised learning framework called Next-Audio-Patch-Embedding (NAPE) prediction. NAPE uses a causal Transforme...
Researchers have developed a framework to help healthcare chatbots better understand patient queries by asking targeted follow-up questions to clarify...
Researchers have developed a method called CJSD to help streaming systems decide whether to reuse an existing model, create a new one, or delay the de...
Researchers have proposed a decision layer for streaming systems that maintain a pool of expert models. The system decides whether to reuse an existin...
Researchers have found that injecting new subjects into a language model's stream of text at regular intervals can increase judged surprise and connec...
Researchers have created a comprehensive benchmark for detecting malicious behavior in AI agents. The MaliciousSkillBench consolidates data from 13 pu...
Researchers have developed a method to quantify how much Automatic Speech Recognition (ASR) models are optimized for benchmark tests rather than real-...
Researchers have developed a framework for human-mediated AI guidance, where a more knowledgeable person interprets and adapts AI-generated informatio...
Researchers propose a new framework for open-vocabulary 3D object detection that improves both the discovery of novel objects and the robustness of mo...
Researchers have proposed a new approach to Federated Continual Learning (FCL) called FedCurv-DR. This method is designed for cultural heritage data t...