Self-improvement of a decoder-only transformer yields plans averaging 30% shorter than a source symbolic planner, over 80% optimal where known, with sub-exponential latency scaling.
Numerische mathematik , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Vesselpose predicts voxel-wise direction vectors to extend the TEASAR algorithm for topologically accurate vascular graph reconstruction from 3D images.
citing papers explorer
-
Self-Improvement for Fast, High-Quality Plan Generation
Self-improvement of a decoder-only transformer yields plans averaging 30% shorter than a source symbolic planner, over 80% optimal where known, with sub-exponential latency scaling.