Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement
Kyusong Lee, Heting Ying, Tiancheng Zhao
Embodied visual tracking requires a robot to identify a designated target from visual observations and control its own motion to follow that target through an environment. Followin…
cs.CV2024
OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer
Lu Zhang, Tiancheng Zhao, Heting Ying +2
Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding. However, processing extens…