RL-Kirigami achieves 94.91% shape intersection over union on procedurally generated targets using OT-CFM and GRPO, with laser-cut prototypes produced in 8 minutes.
The OT-CFM row instantiates the shared mask-conditioned U-Net backbone at each square grid size and measures one Euler-8 OT-CFM sample plus evaluation per target without retraining
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reinforcement learning for inverse structural design and rapid laser cutting of kirigami prototypes
RL-Kirigami achieves 94.91% shape intersection over union on procedurally generated targets using OT-CFM and GRPO, with laser-cut prototypes produced in 8 minutes.