Related papers: LLM-based Control Code Generation using Image Reco…
With the rapid development of Large Language Models (LLMs), their powerful code-generation capabilities have been widely applied in tasks like code completion and automated development, demonstrating the value of improving coding…
LLM-based code generation tools are essential to help developers in the software development process. Existing tools often disconnect with the working context, i.e., the code repository, causing the generated code to be not similar to human…
The capabilities of Large Language Models (LLMs) in code generation have been extensively studied, particularly for implementing target functionalities from natural-language descriptions. Alternatively, input-output (I/O) examples provide…
Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning ability on many NLP tasks. A common practice is to recast the task into a text-to-text format such that generative LLMs of natural…
With the advent of generative LLMs and their advanced code generation capabilities, some people already envision the end of traditional software engineering, as LLMs may be able to produce high-quality code based solely on the requirements…
Graph computational tasks are inherently challenging and often demand the development of advanced algorithms for effective solutions. With the emergence of large language models (LLMs), researchers have begun investigating their potential…
The escalating complexity of modern digital systems has imposed significant challenges on integrated circuit (IC) design, necessitating tools that can simplify the IC design flow. The advent of Large Language Models (LLMs) has been seen as…
Code Large Language Models (Code LLMs) have been increasingly used by developers to boost productivity, but they often generate vulnerable code. Thus, there is an urgent need to ensure that code generated by Code LLMs is correct and secure.…
Recent works have shown great potentials of Large Language Models (LLMs) in robot task and motion planning (TAMP). Current LLM approaches generate text- or code-based reasoning chains with sub-goals and action plans. However, they do not…
While Large Language Models (LLMs) are increasingly used for synthesizing textual PLC programming languages like Structured Text (ST) code, other IEC 61131-3 standard graphical languages like Sequential Function Charts (SFCs) remain…
Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…
A range of applications for automatic machine learning need the generation process to be controllable. In this work, we propose a way to control the output via a sequence of simple actions, that are called semantic code classes. Finally, we…
This study evaluates the efficiency of code generation by Large Language Models (LLMs) and measures their performance against human-crafted solutions using a dataset from Leetcode. We compare 18 LLMs, considering factors such as model…
Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets through problem rephrasing, but face issues with generation…
Deploying large language model-based code generation in real-world client-side development remains challenging due to heterogeneous inputs, strict engineering constraints, and complex interaction logic expressed in product requirement…
Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG) and knowledge graphs offer new opportunities for interacting with engineering diagrams such as Piping and Instrumentation Diagrams (P&IDs). However, directly…
Ladder Logics is a programming language standardized in IEC 61131-3 and widely used for programming industrial Programmable Logic Controllers (PLC). A PLC program consists of inputs (whose values are given at runtime by factory sensors),…
The generation of large, high-quality datasets for code understanding and generation remains a significant challenge, particularly when aligning decompiled binaries with their original source code. To address this, we present CodableLLM, a…
Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…
This paper contributes to speeding up the design and deployment of engineering dynamical systems by proposing a strategy for exploiting domain and expert knowledge for the automated generation of a dynamical system computational model…