41 papers - avg viability 6.8
DGS-Net is an end-to-end grasp prediction network that learns dense grasp configurations from single-view point clouds in multi-object scenes.
ForceVLA2 enhances robotic manipulation by integrating hybrid force-position control with explicit force awareness for improved task performance.
DexHiL is a human-in-the-loop framework that enhances dexterous manipulation in robotic systems through coordinated interventions and adaptive learning.
DreamPlan enhances Vision-Language Models for robotic manipulation through efficient reinforcement fine-tuning using video world models.
AnchorVLA4D enhances robotic manipulation by integrating visual anchors for improved spatial-temporal reasoning.
FG-CLTP enhances robotic manipulation by integrating fine-grained tactile sensing with vision-language-action models.
MoE-ACT enhances robotic manipulation by integrating language-conditioned Mixture-of-Experts into a lightweight multi-task imitation learning framework.
Transform the Inspire RH56DFX hand into a reliable research tool for dexterous manipulation with enhanced control and planning capabilities.
COAD enables constant-time planning for robotic manipulation tasks by using a compressed library and online adaptation.
PRIMO R1 transforms video MLLMs into active critics for enhanced robotic manipulation through process reasoning.