paper-with-me

Papers

GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback

2025-01-29 · Mohamed Abdelaal, Samuel Lokadjaja, Gilbert Engert

This paper introduces GLLM, an innovative tool that leverages Large Language Models (LLMs) to automatically generate G-code from natural language instructions for Computer Numerical Control (CNC) machining. GLLM addresses the challenges of manual G-code writing by bridging the gap between human-readable task descriptions and machine-executable code. The system incorporates a fine-tuned StarCoder-3B model, enhanced with domain-specific training data and a Retrieval-Augmented Generation (RAG) mechanism. GLLM employs advanced prompting strategies and a novel self-corrective code generation approach to ensure both syntactic and semantic correctness of the generated G-code. The architecture includes robust validation mechanisms, including syntax checks, G-code-specific verifications, and functional correctness evaluations using Hausdorff distance. By combining these techniques, GLLM aims to democratize CNC programming, making it more accessible to users without extensive programming experience while maintaining high accuracy and reliability in G-code generation.

📄 PDF Abstract BibTeX arXiv:2501.17584

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationRAGRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Behavior Optimized Image Generation

2023-11-18 · Varun Khurana, Yaman K Singla, Jayakumar Subramanian, Rajiv Ratn Shah 외

The last few years have witnessed great success on image generation, which has crossed the acceptance thresholds of aesthetics, making it directly applicable to personal and commercial applications. However, images, espe…

Image GenerationMarketing

Generative Large Language Models (gLLMs) in Content Analysis: A Practical Guide for Communication Research

2025-10-28 · Daria Kravets-Meinke, Hannah Schmid-Petri, Sonja Niemann, Ute Schmid arxiv

Generative Large Language Models (gLLMs), such as ChatGPT, are increasingly being used in communication research for content analysis. Studies show that gLLMs can outperform both crowd workers and trained coders, such as…

Prompt Engineering

A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4

2023-10-04 · Katikapalli Subramanyam Kalyan

Large language models (LLMs) are a special class of pretrained language models obtained by scaling model size, pretraining corpus and computation. LLMs, because of their large size and pretraining on large volumes of tex…

Data AugmentationSelf-Supervised LearningSurveyTransfer Learning

DrugLLM: Open Large Language Model for Few-shot Molecule Generation

2024-05-07 · Xianggen Liu, Yan Guo, Haoran Li, Jin Liu 외

Large Language Models (LLMs) have made great strides in areas such as language processing and computer vision. Despite the emergence of diverse techniques to improve few-shot learning capacity, current LLMs fall short in…

Drug DesignDrug DiscoveryFew-Shot LearningLanguage Modeling+3

SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding

2025-08-30 · Zhen Chen, Xingjian Luo, Kun Yuan, Jinlin Wu 외 arxiv

Surgical video understanding is crucial for facilitating Computer-Assisted Surgery (CAS) systems. Despite significant progress in existing studies, two major limitations persist, including inadequate visual content perce…

Video Reconstruction