Related papers: The CoCompiler: DSL Lifting via Relational Compila…

This paper addresses the problem of specifying and parsing the syntax of domain-specific languages (DSLs) in a modular, user-friendly way. That is, we want to enable the design of composable DSLs that combine the natural syntax of external…

In a high-tech country products are becoming rapidly more complex. To manage the development process as well as to encounter unforeseen challenges, the understanding and thus the explicit modeling of organizational workflows is more…

To address the challenges associated with data processing at scale, we propose Dataverse, a unified open-source Extract-Transform-Load (ETL) pipeline for large language models (LLMs) with a user-friendly design at its core. Easy addition of…

We describe a new approach to domain specific languages (DSLs), called Quoted DSLs (QDSLs), that resurrects two old ideas: quotation, from McCarthy's Lisp of 1960, and the subformula property, from Gentzen's natural deduction of 1935.…

Constrained decoding with lookahead heuristics (CDLH) is a highly effective method for aligning LLM generations to human preferences. However, the extensive lookahead roll-out operations for each generated token makes CDLH prohibitively…

Multitier programming languages reduce the complexity of developing distributed systems by developing the distributed system in a single coherent code base. The compiler or the runtime separate the code for the components of the distributed…

Classical machine learning (CML) occupies nearly half of machine learning pipelines in production applications. Unfortunately, it fails to utilize the state-of-the-practice devices fully and performs poorly. Without a unified framework, the…

MLIR is an emerging compiler infrastructure for modern hardware, but existing programs cannot take advantage of MLIR's high-performance compilation if they are described in lower-level general purpose languages. Consequently, to avoid…

Although Large Language Models (LLMs) demonstrate proficiency in knowledge-intensive tasks, current interfaces frequently precipitate cognitive misalignment by failing to externalize users' underlying reasoning structures. Existing tools…

Translating SQL dialects across different relational database management systems (RDBMSs) is crucial for migrating RDBMS-based applications to the cloud. Traditional SQL dialect translation tools rely on manually-crafted rules,…

Structured LLM workflows, where specialized LLM sub-agents execute according to a predefined graph, have become a powerful abstraction for solving complex tasks. Optimizing such workflows, i.e., selecting configurations for each sub-agent…

Lifting is an efficient technique to scale up graphical models generalized to relational domains by exploiting the underlying symmetries. Concurrently, neural models are continuously expanding from grid-like tensor data into structured…

As the number of computing devices embedded into engineered systems continues to rise, there is a widening gap between the needs of the user to control aggregates of devices and the complex technology of individual devices. Spatial…

State-of-the-art sequential reasoning in Large Language Models (LLMs) has expanded the capabilities of Copilots beyond conversational tasks to complex function calling, managing thousands of API calls. However, the tendency of compositional…

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…

This paper reports on initial experiments using J Moore's Codewalker to reason about programs compiled to the Low-Level Virtual Machine (LLVM) intermediate form. Previously, we reported on a translator from LLVM to the applicative subset of…

Software languages evolve over time for reasons such as feature additions. When grammars evolve, textual instances that originally conformed to them may become outdated. While model-driven engineering provides many techniques for…

Binary decompilation plays a vital role in various cybersecurity and software engineering tasks. Recently, end-to-end decompilation methods powered by large language models (LLMs) have garnered significant attention due to their ability to…

A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another. Transcompilers are primarily used for interoperability, and to port…

Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to lower-level programming languages, such as assembly. We propose a synthetic data generation method named C-ing Clearly,…