FO2 groundings can require 2^Ω(n) DNNF size, but a type-based compiler with residual caching often yields smaller circuits and faster runtimes than naive grounding.
Advances in neural information processing systems , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
DeepLog is a universal PyTorch backend that compiles diverse neurosymbolic languages into arithmetic circuits to integrate logic with deep learning.
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.
Neurosymbolic framework grounds skeleton motion in learnable pose and dynamics concepts then reasons over them with differentiable logic to recognize actions interpretably on NTU and NW-UCLA benchmarks.
citing papers explorer
-
On Knowledge Compilation For Two-Variable First-Order Logic
FO2 groundings can require 2^Ω(n) DNNF size, but a type-based compiler with residual caching often yields smaller circuits and faster runtimes than naive grounding.
-
DeepLog: A Software Framework for Modular Neurosymbolic AI
DeepLog is a universal PyTorch backend that compiles diverse neurosymbolic languages into arithmetic circuits to integrate logic with deep learning.
-
Probabilistic Programs of Thought
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.
-
Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition
Neurosymbolic framework grounds skeleton motion in learnable pose and dynamics concepts then reasons over them with differentiable logic to recognize actions interpretably on NTU and NW-UCLA benchmarks.