Researchers have developed BERTilda, a framework for tracking topic lifecycles in longitudinal text streams. This involves identifying how topics spli...
Researchers have developed a new method for detecting machine-generated text called Pattern Stability Score (PSS). This approach uses local statistica...
Researchers have developed a method to quantify the processing load imposed by narrative texts, called Narrative Entropy (Sn). They applied this metho...
Researchers have studied how well zero-shot classification works in agrifood vision-language models when using different types of prompts and datasets...
Researchers have developed an approach to training large language models for multiple audio and text tasks without explicit instructions. They call th...
Researchers have developed a method for efficiently running small natural language processing (NLP) models on server CPUs using the PyTorch framework....
A new approach for observing and auditing autonomous scientific agents has been proposed by researchers. These systems propose ideas, write code, run ...
Researchers investigated whether large language models (LLMs) can learn to understand figurative language by fine-tuning them on cultural data. They t...
Researchers have developed a method for segmenting words in the Tangut language, which is an extinct script that doesn't explicitly mark word boundari...
Researchers have developed OmniAlign, a single model that can align words and sentences across languages. Unlike existing tools, which typically focus...
Researchers have proposed a new neural network architecture called WhiteMatter that allows for all-to-all cross-layer connections. This is in contrast...
Researchers have proposed a new framework called MissDiag to evaluate the robustness of AI systems that answer questions based on incomplete or missin...