Researchers have created a benchmark called OmegaUse-OfficeVal to evaluate large language model (LLM) agents' ability to complete office-suite tasks e...
Researchers have proposed a new framework for deep search called G-ReAct. It organizes reasoning as state evolution over a fixed-topology query graph,...
A team of researchers has investigated the vulnerability of clinical decision support systems to 'gaming' by shortcuts. These systems involve committe...
Researchers have developed VDGR-RAG, a unified framework for enterprise knowledge question answering. It integrates vector retrieval, directory-driven...
Researchers have identified a specific circuit in a multilingual model that causes the model to refuse or comply with requests. This 'cross-lingual re...
Researchers have proposed a new framework called Rationale-Guided Learning (RGL) to improve multimodal emotion recognition in conversations. This appr...
Researchers have developed an AI tool called Distribird that helps build informative prior distributions for Bayesian model calibration. This process ...
Researchers have developed a pipeline that uses large language models (LLMs) to generate graphs for optimizing complex problems. The pipeline is probl...
A recent study on natural language generation (NLG) evaluation has found that the standard method of collecting human ratings may not accurately refle...
Researchers have proposed a framework for evaluating deep neural networks in detecting and quantifying lymphoma from PET/CT images. The framework addr...
Researchers have developed a new model called ManiCM for real-time robotic manipulation. The model uses a consistency constraint to improve efficiency...
Researchers have developed an algorithm called QCDC-DR-GA that optimizes container loading and unloading at ports by combining two techniques: Quay Cr...