Related papers: AutoPLC: Generating Vendor-Aware Structured Text f…

Since the introduction of Large Language Models (LLMs), they have been widely adopted for various tasks such as text summarization, question answering, speech-to-text translation, and more. In recent times, the use of LLMs for code…

While recent AI-for-math has made strides in pure mathematics, areas of applied mathematics, particularly PDEs, remain underexplored despite their significant real-world applications. We present PDE-Controller, a framework that enables…

The ability of Large Language Models (LLMs) to generate structured outputs that follow arbitrary schemas is crucial to a wide range of downstream tasks that require diverse structured representations of results such as information…

Synthetic data has the potential to improve the performance, training efficiency, and privacy of real training examples. Nevertheless, existing approaches for synthetic text generation are mostly heuristics and cannot generate…

Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human…

Advanced Planning and Scheduling (APS) systems have become indispensable for modern manufacturing operations, enabling optimized resource allocation and production efficiency in increasingly complex and dynamic environments. While…

Modern computer programming languages are governed by complex syntactic rules. They are unlike natural languages; they require extensive manual work and a significant amount of learning and practicing for an individual to become skilled at…

Software configurations play a crucial role in determining the behavior of software systems. In order to ensure safe and error-free operation, it is necessary to identify the correct configuration, along with their valid bounds and rules,…

Language model-based code generation and completion tools have been widely adopted, but they may sometimes produce code that does not meet necessary constraints, such as syntactic correctness or API existence. Constrained decoding…

Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating high-quality and reliable code remains a formidable task because of LLMs' lack of…

Intelligent assistants powered by Large Language Models (LLMs) can generate program and test code with high accuracy, boosting developers' and testers' productivity. However, there is a lack of studies exploring LLMs for testing Web APIs,…

Writing specifications for computer programs is not easy since one has to take into account the disparate conceptual worlds of the application domain and of software development. To bridge this conceptual gap we propose controlled natural…

In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle with accuracy and are unsuitable for high-risk applications without additional oversight…

Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fall short in capturing deep procedural logic on complex tasks.…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Model Predictive Control (MPC) is a powerful control strategy widely utilized in domains like energy management, building control, and autonomous systems. However, its effectiveness in real-world settings is challenged by the need to…

Automated vehicles (AV) heavily depend on robust perception systems. Current methods for evaluating vision systems focus mainly on frame-by-frame performance. Such evaluation methods appear to be inadequate in assessing the performance of a…

Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data. This paper…

Code completion is an essential feature of IDEs, yet current autocompleters are restricted to either grammar-based or NLP-based single token completions. Both approaches have significant drawbacks: grammar-based autocompletion is restricted…

Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for…