Project Grant 2506134

Award Date 11/1/24
Completion Date 9/30/25
Dollars Obligated $719K
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
La Jolla, CA 92093, USA
Similar Awards
This $875,000 Project Grant was awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) to the University of California, San Diego (UCSD). The project aims to develop new techniques for aligning large language models (LLMs) with formal specifications in order to generate high-quality computer code that provably matches user intent. Specifically, the project will: (1) develop grammar-aligned decoding...
The National Science Foundation awarded a $275,000 Project Grant to the University of Texas at Austin under the Computer and Information Science and Engineering program (CFDA 47.070). The three-year award will support the development of program synthesis techniques to help software developers manage schema changes to databases. The project aims to simplify the schema modification process through automated techniques for migrating data between formats and updating code to reflect schema...
The National Science Foundation awarded a $800,000 Project Grant to the University of Texas at Austin under the Computer and Information Science and Engineering program (CFDA 47.070). The three-year award will support the development of a neurosymbolic program-synthesis framework that closely couples deep learning and classical symbolic methods for program synthesis. Researchers will explore new learning algorithms exposing neural models of code to explicit knowledge about program semantics....
This $256,710 National Science Foundation award under the Computer and Information Science and Engineering (CFDA 47.070) program supports a collaborative research project led by the University of Texas at Austin. The project investigates full-stack implementation methodologies for developing expressive programming systems that bridge the gap between high-level specifications and high-performance implementations of complex reasoning tasks at scale. Key focus areas include extending declarative...
The University of California, San Diego (UCSD) was awarded a 5-year, $165,000 Project Grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070). The goal of this project is to develop algorithms, software, and systems that can automatically generate high-quality labeled data to mitigate the lack of labeled training data in specialized domains such as healthcare, legislation, and environmental sciences. The proposed approaches...
The National Science Foundation (NSF) awarded a $599,578 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the University of California, San Diego (UCSD) to develop a direct manipulation programming system that integrates visual and textual representations of computer code. The 3-year project seeks to transform the nature of programming by making it more intuitive and accessible, especially for beginners, by allowing programmers to directly...
This National Science Foundation Project Grant of $250,000 supports research at the University of California, San Diego to develop automated techniques for lemma synthesis in interactive theorem provers. The goal is to reduce the manual proof effort required when using interactive theorem provers to prove correctness and security properties of software. The project will explore multiple formulations of reducing the lemma synthesis problem to data-driven program synthesis, where the objective...
The National Science Foundation (NSF) awarded a $359,615 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the University of California, San Diego (UCSD) for the "COLLABORATIVE RESEARCH: FRAMEWORKS: HPCGPT: ENHANCING COMPUTING CENTER USER SUPPORT WITH HPC-ENRICHED GENERATIVE AI" project. This 3-year effort, starting August 1, 2024, aims to develop HPCGPT, a question answering service that leverages generative AI and integrates real-time...
This $300,000 federal Project Grant award from the National Science Foundation's (NSF) STEM Education (CFDA 47.076) program aims to develop a course that teaches computer science students how to work with and comprehend large code bases. The project, awarded to the University of California, San Diego (UC San Diego), is designed to address the "academia-industry gap" where new computer science graduates are often underprepared for contributing to large, existing software code bases in...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $1,164,216 to Washington State University to investigate full-stack implementation methodologies for expressive programming systems. The goal is to effectively bridge the gap between human-level specification and high-performance implementation of complex reasoning tasks at scale. The project aims to scale declarative reasoning to...

This Project Grant award from the National Science Foundation (CFDA 47.070 - Computer and Information Science and Engineering) provides $719,494 to the University of California, San Diego (UCSD) to advance the field of program synthesis through the development of more scalable and general synthesis algorithms. The goal is to extend program synthesis capabilities to larger-scale software systems, making synthesis more usable and programmable for a wider range of users. The project builds on the Semantics-Guided Synthesis (SemGuS) framework to enable modular, compositional program synthesis that can create larger programs from smaller components. This research aims to address the scalability and expressibility challenges currently limiting the widespread adoption of program synthesis technology. No sub-awards are planned under this grant, which has an award date of November 1, 2024 and an ultimate completion date of September 30, 2025.

Generated 8/5/25, 6:31 AM