mlsanityData to 7 Oct 2026

ViC: Virtual Compiler Is All You Need For Assembly Code Search

arXiv 2408.06385 ↗First posted 10 Aug 2024cs.SE cs.AI cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Assembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs. Despite its significance, this critical task is impeded by the complexities involved in building high-quality datasets. This paper explores training a Large Language Model (LLM) to emulate a general compiler. By leveraging Ubuntu packages to compile a dataset of 20 billion tokens, we further continue pre-train CodeLlama as a Virtual Compiler (ViC), capable of compiling any source code of any language to assembly code. This approach allows for virtual compilation across a wide range of programming languages without the need for a real compiler, preserving semantic equivalency and expanding the possibilities for assembly code dataset construction. Furthermore, we use ViC to construct a sufficiently large dataset for assembly code search. Employing this extensive dataset, we achieve a substantial improvement in assembly code search performance, with our model surpassing the leading baseline by 26%.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 10 Aug 2024.

Builds on

20 of 34 references.

References · 20

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  7. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  8. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  9. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  10. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  11. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  12. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
8 more
  1. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
  2. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  3. 2023Large Language Models for Compiler Optimizationcited by 52
  4. 2021PalmTree: Learning an Assembly Language Model for Instruction Embeddingcited by 49
  5. 2022jTrans: Jump-Aware Transformer for Binary Code Similaritycited by 44
  6. 2020Trex: Learning Execution Semantics from Micro-Traces for Binary Similaritycited by 34
  7. 2024CLAP: Learning Transferable Binary Code Representations with Natural Language Supervisioncited by 17
  8. 2021Learning C to x86 Translation: An Experiment in Neural Compilationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Large Language Models (LLMs) for Source Code Analysis: applications, models and datasetscited by 15
  2. 2026The New Compiler Stack: A Survey on the Synergy of LLMs and Compilerscited by 0