Researchers have developed a framework called MKG-CARE for medical image diagnosis that uses multimodal knowledge graphs to incorporate similar cases ...
Researchers have proposed a new framework for understanding how concepts form in transformer language models, which they call the Concept Allocation Z...
Researchers have proposed a new tool called FaithMATE to investigate the relationship between two ways of measuring how accurately large language mode...
Researchers have introduced Geometric Evolution Maps (GEMs), a new approach to extracting stable concept probes from transformer residual streams. A c...
Researchers introduced a new approach to improve AI personalization by creating an 'interpretive layer' called Behavioral Specification. This layer ca...
Researchers investigated the effectiveness of Markov boundary in tabular prediction tasks. They found that restricting a model to the Markov boundary ...
Researchers have investigated whether AI-generated predictions about the behavior of objects in the physical world can actually occur in reality. They...
Researchers have introduced GEM (Geometric Erasure by Contrastive Velocity Matching in Rectified Flows), a framework for erasing unwanted concepts fro...
Researchers have proposed a new framework called MPCoT for improving the performance of Vision-Language-Action (VLA) policies in long-horizon and high...
Researchers have created a benchmark to test the reliability of agent skill retrieval systems. These systems are used in AI applications where skills ...
Researchers have developed a tool to map and analyze AI programs in the United States. The tool, available at cicmap.ai, was used to survey 361 underg...
Researchers have developed a new method for learning symbolic models of real-world robot tasks from visual demonstrations. The PO-PDDL system construc...