TriRelVLA introduces triadic object-hand-task relational representations and a task-grounded graph transformer with a relational bottleneck to improve generalization in robotic manipulation across scenes, objects, and tasks.
V olumetric environment representation for vision-language navigation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation
TriRelVLA introduces triadic object-hand-task relational representations and a task-grounded graph transformer with a relational bottleneck to improve generalization in robotic manipulation across scenes, objects, and tasks.