3 papers
cs.RO2026
SUN: Agentic Robot Policy Learning with Persistent Task Programs
Weiqi Wang, Zhi Li, Yudong Lei +7
Model-based control can directly execute specified objectives, while learning can amortize such behaviors into reactive policies, making their combination a natural solution to mul…
cs.RO2026
FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences
Omar Rayyan, Zhi Li, Max Argus +4
Visual loco-manipulation policies that can generalize to novel scenes and objects have long been a goal of robotics research. However, today's data-hungry algorithms make collectin…
cs.CV2022
Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions
Zhi Li, Lu He, Huijuan Xu
Action understanding has evolved into the era of fine granularity, as most human behaviors in real life have only minor differences. To detect these fine-grained actions accurately…