Search Results for author:
Found 8 papers, 5 papers with code
Learning Better Representations From Less Data For Propositional Satisfiability
By combining certificate-driven training and expert iteration, our model learns better representations than models trained for classification only, with a much higher data efficiency -- requiring orders of magnitude less training data.
NeuroSynt: A Neuro-symbolic Portfolio Solver for Reactive Synthesis
At the core of the solver lies a seamless integration of neural and symbolic approaches to solving the reactive synthesis problem.
nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models
A rigorous formalization of desired system requirements is indispensable when performing any verification task.
Iterative Circuit Repair Against Formal Specifications
We propose a separated hierarchical Transformer for multimodal representation learning of the formal specification and the circuit.
Formal Specifications from Natural Language
We study the generalization abilities of language models when translating natural language into formal specifications with complex semantics.
Attention Flows for General Transformers
In this paper, we study the computation of how much an input token in a Transformer model influences its prediction.
Neural Circuit Synthesis from Specification Patterns
We train hierarchical Transformers on the task of synthesizing hardware circuits directly out of high-level logical specifications in linear-time temporal logic (LTL).
Teaching Temporal Logics to Neural Networks
We study two fundamental questions in neuro-symbolic computing: can deep learning tackle challenging problems in logics end-to-end, and can neural networks learn the semantics of logics.
