Researchers have developed a new method called VAKE to help Large Language Models (LLMs) recall and verify factual knowledge. Existing methods often m...
Researchers have introduced OmniHandwritingOCR, a benchmark for evaluating the ability of large language models to recognize handwritten text. The ben...
Researchers have developed a method to expose private information in text embeddings that have been protected with noise. The method, called denoising...
Researchers propose a new framework to evaluate and improve blood pressure estimation using photoplethysmography (PPG). They argue that current method...
Researchers have proposed a new variant of the orienteering problem (OP) called OP-UTVR. This problem involves uncertain and time-varying rewards in r...
Researchers have developed a system called Aslema for a shared task at the NADI 2026 conference. The system consists of two subtasks: intent recogniti...
A study using deep learning has projected that the European Union will exceed its goal of reducing greenhouse gas emissions by 55% below 1990 levels b...
Researchers propose a method for retrieving historical images based on their content and the time period they were taken. The approach, called Tempora...
Researchers have developed a method to improve transcription accuracy in complex historical Sanskrit manuscripts. They use an iterative fine-tuning pr...
Researchers have proposed a new benchmark called MemFuseBench for evaluating memory systems that can integrate information from multiple sources. The ...
Researchers have explored how to combine two AI techniques - uncertainty quantification (UQ) and foundation models - to improve semantic segmentation....
Researchers have investigated the impact of CutMix on semantic segmentation models' reliability and robustness. CutMix is a data augmentation strategy...