Search Results for author:
Found 2 papers, 2 papers with code
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Large pretrained (e. g., "foundation") models exhibit distinct capabilities depending on the domain of data they are trained on.
Ranked #8 on
Video Retrieval
on MSR-VTT-1kA
(video-to-text R@1 metric)
Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning
Skilled robotic manipulation benefits from complex synergies between non-prehensile (e. g. pushing) and prehensile (e. g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-free.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
