← Search

Xiaolong Tian

2 accepted papers

2026

SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin

ICLR 2026poster

Large Language Models (LLMs) have emerged as a promising approach for binary decompilation. However, the existing LLM-based decompilers still are somewhat limited in effectively presenting a program's source-level structure with its original identifiers. To mitigate this, we introduce SK2Decompile,…

Cited by 0SourcecodeScholar
2025

Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation

NeurIPS 2025poster

Recent advances in LLM-based decompilers have been shown effective to convert low-level binaries into human-readable source code. However, there still lacks a comprehensive benchmark that provides large-scale binary-source function pairs, which is critical for advancing the LLM decompilation technol…

Cited by 0SourcecodeScholar