2 papers
cs.CV2026
Interpretable Zero-shot Referring Expression Comprehension with Query-driven Scene Graphs
Yike Wu, Necva Bolucu, Stephen Wan +3
Zero-shot referring expression comprehension (REC) aims to locate target objects in images given natural language queries without relying on task-specific training data, demanding…
cs.RO2025
Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning
Xun Li, Rodrigo Santa Cruz, Mingze Xi +9
To enable robots to comprehend high-level human instructions and perform complex tasks, a key challenge lies in achieving comprehensive scene understanding: interpreting and intera…