Coda is an end-to-end neural decompiler that recovers source code from binaries at 82% accuracy on unseen samples where conventional tools achieve 0%.
Lexical statistical machine translation for language migration,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Multi-stage LLM training plus compiler-guided error repair boosts functional equivalence in Java-to-Cangjie translation by 6.06% over prior methods despite scarce parallel data.
citing papers explorer
-
A Neural-based Program Decompiler
Coda is an end-to-end neural decompiler that recovers source code from binaries at 82% accuracy on unseen samples where conventional tools achieve 0%.
-
Boosting Automatic Java-to-Cangjie Translation with Multi-Stage LLM Training and Error Repair
Multi-stage LLM training plus compiler-guided error repair boosts functional equivalence in Java-to-Cangjie translation by 6.06% over prior methods despite scarce parallel data.