CTO improves code translation by training a semantic equivalence model through contrastive learning and unifying it with syntactic compiler feedback in a multi-objective direct preference optimization setup.
NeurIPS , year = 2022, pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization
CTO improves code translation by training a semantic equivalence model through contrastive learning and unifying it with syntactic compiler feedback in a multi-objective direct preference optimization setup.