PhyEdit improves physical accuracy in image object manipulation by using explicit geometric simulation as 3D-aware guidance combined with joint 2D-3D supervision.
Lava-man: Learning visual action representations for robot manipulation.arXiv preprint arXiv:2508.19391, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PAPO-VLA identifies planning actions via variation and outcome, estimates their causal importance, and folds that importance into GRPO to emphasize key decisions while still using full-trajectory feedback.
citing papers explorer
-
PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing
PhyEdit improves physical accuracy in image object manipulation by using explicit geometric simulation as 3D-aware guidance combined with joint 2D-3D supervision.
-
PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
PAPO-VLA identifies planning actions via variation and outcome, estimates their causal importance, and folds that importance into GRPO to emphasize key decisions while still using full-trajectory feedback.