Researchers have developed a method to control recurrent dynamics in AI models at test time. They found that the behavior of these models can be predi...
Researchers have developed a method to estimate the quality of interactions between humans and robots in real-world environments. They used multimodal...
Researchers have developed a new method for retrieving relevant information from large datasets called Dual-Bounded Relational Recall (DBRR). Unlike t...
Researchers have developed Function+Data Flow (FDF), a visual domain-specific language that enables the composition and reuse of machine learning mode...
Researchers have discovered that vision-language models (VLMs) designed to balance safe generation behavior with grounded visual reasoning may priorit...
Researchers have created a benchmark for retrieving relevant Greek statutory articles in legal question answering tasks. The new benchmark, called Gre...
Researchers have identified an 'evaluability gap' in AI translation, where even when the source text is shown, it's hard to determine what aspects of ...
Researchers have proposed corrections to Zipf's and Heaps' laws, which describe the distribution of word frequencies in language. The corrections are ...
Researchers have proposed a method to detect hallucinations in large language models. Hallucinations are factual errors generated by these models when...
Researchers have created a dataset called CONSPIRED to study the language patterns of conspiracy theories and how they affect large language models. T...
Researchers have developed a new method for training large language models offline, without requiring online interactions. The approach, called Future...
Researchers have evaluated the effectiveness of Chain-of-Thought (CoT) speech-to-text translation systems in using both spoken words and their transcr...