paper-with-me

Papers

ADELT: Transpilation Between Deep Learning Frameworks

2023-03-07 · Linyuan Gong, Jiayi Wang, Alvin Cheung

We propose the Adversarial DEep Learning Transpiler (ADELT), a novel approach to source-to-source transpilation between deep learning frameworks. ADELT uniquely decouples code skeleton transpilation and API keyword mapping. For code skeleton transpilation, it uses few-shot prompting on large language models (LLMs), while for API keyword mapping, it uses contextual embeddings from a code-specific BERT. These embeddings are trained in a domain-adversarial setup to generate a keyword translation dictionary. ADELT is trained on an unlabeled web-crawled deep learning corpus, without relying on any hand-crafted rules or parallel data. It outperforms state-of-the-art transpilers, improving pass@1 rate by 17.4 pts and 15.0 pts for PyTorch-Keras and PyTorch-MXNet transpilation pairs respectively. We provide open access to our code at https://github.com/gonglinyuan/adelt.

📄 PDF Abstract BibTeX arXiv:2303.03593

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
WordPiece 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Weight Decay 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

C2RUST-BENCH: A Minimized, Representative Dataset for C-to-Rust Transpilation Evaluation

2025-04-21 · Melih Sirlanci, Carter Yagemann, Zhiqiang Lin

Despite the effort in vulnerability detection over the last two decades, memory safety vulnerabilities continue to be a critical problem. Recent reports suggest that the key solution is to migrate to memory-safe language…

Vulnerability Detection

MetaDelta: A Meta-Learning System for Few-shot Image Classification

2021-02-22 · Yudong Chen, Chaoyu Guan, Zhikun Wei, Xin Wang 외

Meta-learning aims at learning quickly on novel tasks with limited data by transferring generic experience learned from previous tasks. Naturally, few-shot learning has been one of the most popular applications for meta-…

ClassificationDecoderFew-Shot Image ClassificationFew-Shot Learning+4

CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora

2026-04-20 · Shangyu Li, Juyong Jiang, Meibo Ren, Sizhe Zhong 외 arxiv

Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream applications, from modernizing large legacy codebases to augmenting data…

Reinforcement LearningCode Translation

Guess & Sketch: Language Model Guided Transpilation

2023-09-25 · Celine Lee, Abdulrahman Mahmoud, Michal Kurek, Simone Campanoni 외

Maintaining legacy software requires many software and systems engineering hours. Assembly code programs, which demand low-level control over the computer machine state and have no variable names, are particularly diffic…

Language ModelingLanguage ModellingmodelTranslation

HPCTransCompile: An AI Compiler Generated Dataset for High-Performance CUDA Transpilation and LLM Preliminary Exploration

2025-06-12 · Jiaqi Lv, Xufeng He, Yanchen Liu, Xu Dai 외

The rapid growth of deep learning has driven exponential increases in model parameters and computational demands. NVIDIA GPUs and their CUDA-based software ecosystem provide robust support for parallel computing, signifi…

CPUData Augmentation