2 papers
cs.RO2026
Trajectory-based Diffusion from One-shot Human Video for Generalizable Manipulation
Guoping Pan, Xinmiao Yu, Wannan Cao +5
Imitation learning enables robots to perform complex tasks by leveraging human-collected demonstrations. However, most existing approaches require labor-intensive data collection w…
cs.CV2025
LEGO-Motion: Learning-Enhanced Grids with Occupancy Instance Modeling for Class-Agnostic Motion Prediction
Kangan Qian, Jinyu Miao, Ziang Luo +7
Accurate and reliable spatial and motion information plays a pivotal role in autonomous driving systems. However, object-level perception models struggle with handling open scenari…