AI
Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth
Researchers have developed a method to control recurrent dynamics in AI models at test time. They fo...
AI
Multimodal Rapport Estimation in Real-World HRI
Researchers have developed a method to estimate the quality of interactions between humans and robot...
AI
More Context, Same Budget: Dual-Bounded Relational Recall Beyond Top-K Retrieval
Researchers have developed a new method for retrieving relevant information from large datasets call...
AI
Building real-time digital twin instances with Function+Data Flow: user evaluation and extension for iterative pipelines
Researchers have developed Function+Data Flow (FDF), a visual domain-specific language that enables ...
AI
When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models
Researchers have discovered that vision-language models (VLMs) designed to balan...
AI
GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval
Researchers have created a benchmark for retrieving relevant Greek statutory art...
AI
When Readability and Source Retention Diverge: An Evaluability Gap in AI Translation
Researchers have identified an 'evaluability gap' in AI translation, where even ...
AI
Corrections of Zipf's and Heaps' Laws Derived from Hapax Rate Models
Researchers have proposed corrections to Zipf's and Heaps' laws, which describe ...