AwesomeREA.org

2026 · Conference paper

The CodeInverter Suite: Structure- and Data-Aware Binary Decompilation with Efficient LLMs

Peipei Liu; Jian Sun; Rongkang Sun; Li Chen; Zhaoteng Yan; Xiaoling Zhang; Dawei Wang; Dapeng Sun; Peizheng Zhang; Dan Li

CodeInverter studies function-level LLM decompilation using control-flow graphs and memory-to-data mappings extracted with IDA/objdump. It presents a prompt workflow, training corpus and model family, evaluated through compilation, benchmark input/output tests and edit similarity.

Scope and limitations

Evaluation covers individual C functions under 32/64-bit GCC settings. Whole-program recovery, aggressive optimization and protected binaries remain limitations; passing benchmark tests does not establish general equivalence. The text reports one epoch (15 steps), while the pinned launch example sets one epoch and 100 warmup steps; the exact training schedule remains unresolved. No upstream code, models or experiments were run for this collection.

Why it fits this collection

Adds structure- and data-informed LLM decompilation with separate compilation, execution-test and similarity evidence.

Publication and review details

Venue
ASE 2026
Status
Conference paper
Publication / posting date
October 7, 2026
Date source
Online and print publication date in ACM’s Crossref deposit; arXiv first submission is recorded separately.
First arXiv submission
March 10, 2025
arXiv
2503.07215
Reviewed arXiv version
v3
DOI
10.1145/3832783.3837554

The v3 title and ten-author order match ACM’s Crossref deposit. The repository README at 548e59c still cites v2/2025. Direct ACM access returned HTTP 403: this record uses the publisher deposit and author v3 DOI header, not a reviewed publisher PDF. Artifact snapshots are separately versioned. The training directory contains MIT and DeepSeek notices; the CIM-1.3B card declares CC BY 4.0, but a uniform license for all code, weights and data is not established. Weights and dataset archives were not downloaded.

Sources reviewed

Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.

Primary sources

  1. https://api.crossref.org/works/10.1145/3832783.3837554
  2. https://arxiv.org/abs/2503.07215v3
  3. https://arxiv.org/pdf/2503.07215v3
  4. https://arxiv.org/html/2503.07215v3
  5. https://arxiv.org/abs/2503.07215v1
  6. https://arxiv.org/abs/2503.07215v2
  7. README.md GitHub · LiuPeiP-CS/CodeInverter · Revision 548e59c
  8. https://zenodo.org/api/records/19351453
  9. https://huggingface.co/CodeInverter/CIM-1.3b/raw/1f7745e19c5420a8c5896f5c31d6938f83454be4/README.md
  10. code4train/train/run_ms2decllm_train.sh GitHub · LiuPeiP-CS/CodeInverter · Revision 548e59c
  11. code4train/LICENSE GitHub · LiuPeiP-CS/CodeInverter · Revision 548e59c
  12. code4train/LICENSE-MODEL GitHub · LiuPeiP-CS/CodeInverter · Revision 548e59c