3 papers
cs.CV2026
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
Qifeng Zhang, Kaixiang Huang, Heng Dong +6
Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overlooking global spatial awarenes…
cs.RO2026
Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
Zixuan Wang, Huang Fang, Shaoan Wang +4
While large vision-language models (VLMs) show promise for object goal navigation, current methods still struggle with low success rates and inefficient localization of unseen obje…
cs.AI2025
Robix: A Unified Model for Robot Interaction, Reasoning and Planning
Huang Fang, Mengxi Zhang, Heng Dong +6
We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the hig…