The viewpoint-agnostic grasp pipeline using VLM and partial observation handling achieves 90% success (9/10 trials) in cluttered tabletop scenarios on a real quadruped robot, outperforming a view-dependent baseline at 30% (3/10) through open-vocabulary detection, point cloud completion, and safety-0
Open-vocabulary part-based grasping
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DSAA boosts fine-grained OVD by injecting attribute priors via APA in text embeddings, modulating K/V in BERT, and using attribute-aware contrastive loss, with gains reported on FG-OVD benchmark.
citing papers explorer
-
Viewpoint-Agnostic Grasp Pipeline using VLM and Partial Observations
The viewpoint-agnostic grasp pipeline using VLM and partial observation handling achieves 90% success (9/10 trials) in cluttered tabletop scenarios on a real quadruped robot, outperforming a view-dependent baseline at 30% (3/10) through open-vocabulary detection, point cloud completion, and safety-0
-
DSAA: Dual-Stage Attribute Activation for Fine-grained Open Vocabulary Detection
DSAA boosts fine-grained OVD by injecting attribute priors via APA in text embeddings, modulating K/V in BERT, and using attribute-aware contrastive loss, with gains reported on FG-OVD benchmark.