Zobrazeno 1 - 10
of 31
pro vyhledávání: '"P A, Santolucito"'
Code generation with Large Language Models (LLMs) has helped to increase software developer productivity in coding tasks, but has yet to have significant impact on the tasks of software developers that surround this code. In particular, the challenge
Externí odkaz:
http://arxiv.org/abs/2411.19043
Autor:
Murphy, William, Holzer, Nikolaus, Qiao, Feitong, Cui, Leyi, Rothkopf, Raven, Koenig, Nathan, Santolucito, Mark
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 and verifi
Externí odkaz:
http://arxiv.org/abs/2410.19736
Autor:
Zhang, William, Leon, Maria, Xu, Ryan, Cardenas, Adrian, Wissink, Amelia, Martin, Hanna, Srikanth, Maya, Dorogi, Kaya, Valadez, Christian, Perez, Pedro, Grijalva, Citlalli, Zhang, Corey, Santolucito, Mark
Node-based programming languages are increasingly popular in media arts coding domains. These languages are designed to be accessible to users with limited coding experience, allowing them to achieve creative output without an extensive programming b
Externí odkaz:
http://arxiv.org/abs/2409.00856
Autor:
Murphy, William, Holzer, Nikolaus, Koenig, Nathan, Cui, Leyi, Rothkopf, Raven, Qiao, Feitong, Santolucito, Mark
Temporal logics are powerful tools that are widely used for the synthesis and verification of reactive systems. The recent progress on Large Language Models (LLMs) has the potential to make the process of writing such specifications more accessible.
Externí odkaz:
http://arxiv.org/abs/2406.07400
The surge in popularity of large language models (LLMs) has opened doors for new approaches to the creation of interactive agents. However, managing and interpreting the temporal behavior of such agents over the course of a potentially infinite inter
Externí odkaz:
http://arxiv.org/abs/2402.16905
Infrastructure as Code (IaC) has enabled cloud customers to have more agility in creating and modifying complex deployments of cloud-provisioned resources. By writing a configuration in IaC languages such as CloudFormation, users can declaratively sp
Externí odkaz:
http://arxiv.org/abs/2402.15632
Autor:
Berman, Shmuel, Santolucito, Mark
Program synthesis has seen many new applications in recent years, in large part thanks to the introduction of SyGuS. However, no existing SyGuS solvers have support for synthesizing recursive functions. We introduce an multi-phase algorithm for the s
Externí odkaz:
http://arxiv.org/abs/2108.08724
The decision tree is one of the most popular and classical machine learning models from the 1980s. However, in many practical applications, decision trees tend to generate decision paths with excessive depth. Long decision paths often cause overfitti
Externí odkaz:
http://arxiv.org/abs/2010.06631
Programming-by-example (PBE) is a synthesis paradigm that allows users to generate functions by simply providing input-output examples. While a promising interaction paradigm, synthesis is still too slow for realtime interaction and more widespread a
Externí odkaz:
http://arxiv.org/abs/2002.02884
Functional Reactive Programming (FRP) is a paradigm that has simplified the construction of reactive programs. There are many libraries that implement incarnations of FRP, using abstractions such as Applicative, Monads, and Arrows. However, finding a
Externí odkaz:
http://arxiv.org/abs/1905.09825