Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
Zixin Zhang, Kanghao Chen, Xingwang Lin +6
The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligen…
cs.CV2024
TINA: Think, Interaction, and Action Framework for Zero-Shot Vision Language Navigation
Dingbang Li, Wenzhou Chen, Xin Lin
Zero-shot navigation is a critical challenge in Vision-Language Navigation (VLN) tasks, where the ability to adapt to unfamiliar instructions and to act in unknown environments is…