3 papers
cs.RO2026
Language2Drive: Do Vision-Language-Action Models Really Follow the Instructions in Autonomous Driving?
Zihan You, Zehua Fan, Wenqi Lyu +19
Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing closed-loop benchmarks primarily me…
cs.RO2026
AR Forcing: Towards Long-Horizon Robot Navigation World Model
Yifei Yang, Zehua Fan, Huan Li +9
The diffusion based robot navigation world models are typically trained using parallel supervision, while autoregressive inference is employed during path planning. This results in…
cs.CV2026
MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction
Jiacheng Dong, Huan Li, Sicheng Zhou +3
Reconstruction is a fundamental task in 3D vision and a fundamental capability for spatial intelligence. Particularly, streaming 3D reconstruction is central to real-time spatial p…