AI
VISD: Enhancing Video Reasoning via Structured Self-Distillation
A new AI framework called VISD is proposed to improve video reasoning in large language models. Curr...
AI
MKG-CARE: Case-Aware Reasoning with Multimodal Knowledge Graphs for Explainable Medical Image Diagnosis
Researchers have developed a framework called MKG-CARE for medical image diagnosis that uses multimo...
AI
The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
Researchers have proposed a new framework for understanding how concepts form in transformer languag...
AI
Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
Researchers have proposed a new tool called FaithMATE to investigate the relationship between two wa...
AI
Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams
Researchers have introduced Geometric Evolution Maps (GEMs), a new approach to e...
AI
Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization
Researchers introduced a new approach to improve AI personalization by creating ...
AI
The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
Researchers investigated the effectiveness of Markov boundary in tabular predict...
AI
Can Predicted Dynamics Exist in the Physical World?
Researchers have investigated whether AI-generated predictions about the behavio...