Search Results for author: Mark Santolucito

Found 4 papers, 1 papers with code

Enforcing Temporal Constraints on Generative Agent Behavior with Reactive Synthesis

no code implementations24 Feb 2024 Raven Rothkopf, Hannah Tongxin Zeng, Mark Santolucito

Our approach uses Temporal Stream Logic (TSL) to generate an automaton that enforces a temporal structure on an agent and leaves the details of each action for a moment in time to an LLM.

Formal Logic Program Synthesis

Succinct Explanations With Cascading Decision Trees

no code implementations13 Oct 2020 Jialu Zhang, Yitan Wang, Mark Santolucito, Ruzica Piskac

The decision tree is one of the most popular and classical machine learning models from the 1980s.

Classification General Classification

Grammar Filtering For Syntax-Guided Synthesis

no code implementations7 Feb 2020 Kairo Morton, William Hallahan, Elven Shum, Ruzica Piskac, Mark Santolucito

By preprocessing SyGuS PBE problems with a neural network, we can use a data driven approach to reduce the size of the search space, then allow automated reasoning-based solvers to more quickly find a solution analytically.

BIG-bench Machine Learning

Temporal Stream Logic: Synthesis beyond the Bools

2 code implementations1 Dec 2017 Bernd Finkbeiner, Felix Klein, Ruzica Piskac, Mark Santolucito

On the other hand, however, synthesis from TSL is scalable, because it is independent of the complexity of the handled data.

Logic in Computer Science

Cannot find the paper you are looking for? You can Submit a new open access paper.