Similar Items: GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
- Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals
- Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
- CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
- StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning
- Characterizing the Expressivity of Local Attention in Transformers
- Long Context Pre-Training with Lighthouse Attention