IEEE

Optimizing Pre-Trained Code Embeddings With Triplet Loss for Code Smell Detection

Abstract: Code embedding represents code semantics in vector form. Although code embedding-based systems have been successfully applied to various source code analysis tasks, further research is ...
IEEE

HexT5: Unified Pre-Training for Stripped Binary Code Information Inference

Abstract: Decompilation is a widely used process for reverse engineers to significantly enhance code readability by lifting assembly code to a higher-level C-like language, pseudo-code. Nevertheless, ...
GitHub

Time Series Foundation Model - TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

The official code for ["TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024)"]. TEMPO is one of the very first open source Time Series Foundation Models for ...
GitHub

Outlier-Safe Pre-Training

Quantization plays a crucial role in deploying Large Language Models (LLMs) in resource-constrained environments. However, the presence of outlier features significantly hinders low-bit quantization.