Neurosymbolic Finite and Pushdown Automata: Improved Multimodal Reasoning versus Vision Language Models (VLMs) (bibtex)

by Samuel Sasaki, Diego Manzanas Lopez and Taylor T. Johnson

Reference:

Samuel Sasaki, Diego Manzanas Lopez and Taylor T. Johnson, "Neurosymbolic Finite and Pushdown Automata: Improved Multimodal Reasoning versus Vision Language Models (VLMs)", In 2nd International Conference on Neuro-symbolic Systems (NeuS'25), PMLR, 2025.

Bibtex Entry:

@inproceedings{sasaki2025neus,
  title = {Neurosymbolic Finite and Pushdown Automata: Improved Multimodal Reasoning versus Vision Language Models (VLMs)},
  author = {Samuel Sasaki and Diego Manzanas Lopez and Taylor T. Johnson},
  year = {2025},
  month = may,
  booktitle = {2nd International Conference on Neuro-symbolic Systems (NeuS'25)},
  publisher = {PMLR},
  keywords = {neurosymbolic artificial intelligence, automata, multimodal reasoning},
  publabel = {C55},
  pubtype = {C},
  pdf = "research/sasaki2025neus.pdf",
}