الباحثون

Muhammad Zubair Irshad

المنشورات 2

نسخة أولية وصول مفتوح

What 30,000 Hours of Ego-centric Video Does Not Teach

Jiahua Dong, Anurag Bagchi, Yash Jangir وآخرون · 2026

World models offer a promising alternative to physics-based simulators, yet remain far from practical deployment. We ask how far scaling ego-centric human video takes them, using a dataset of 30,000 hours spanning over 1,000 scene types and 14,000 contributors. Rather than relying on opaque downstream metrics, we direc …

نسخة أولية وصول مفتوح

H2RBench: A Real-to-Sim Benchmark for Evaluating Human-to-Robot Transfer

Chuyang Xiao, Haotian Zhan, Sriram Krishna وآخرون · 2026

Learning robot manipulation policies from human video demonstrations constitutes a promising avenue for scalable robot learning. However, comparing different human-to-robot (H2R) transfer methods remains challenging, as existing approaches are evaluated under different settings, including differing task suites, scene l …

المؤلفون المشاركون