2 papers
cs.CV2026
When Should the Count Change? Learning State Maintenance for Causal Video Counting
Pengyiang Liu, Dongyue Lyu, Junbo Niu +3
Continuous video counting requires distinguishing new observations from new objects or completed events. We introduce StaMina (State Maintenance), which learns to maintain counting…
cs.RO2026
Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigation
Xiangyi Zheng, Xiangyu Wang, Qinan Liao +6
Language-guided UAV agents must execute long-horizon semantic instructions while producing smooth, physically feasible continuous flight commands, yet existing Vision-Language Navi…