Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
A survey of deep learning techniques for autonomous driving
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
Reachability for neural networks is NP-hard for single-hidden-layer networks with output dimension 1 and weights restricted to {-1,0,1}.
Introduces agentic vehicles (AgVs) as conceptually distinct from but synergistic with autonomous vehicles (AuVs), emphasizing agency for goal handling and social contexts in human-centered mobility.
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.
citing papers explorer
-
On the Decompositionality of Neural Networks
Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
-
Reachability In Simple Neural Networks
Reachability for neural networks is NP-hard for single-hidden-layer networks with output dimension 1 and weights restricted to {-1,0,1}.
-
Agentic Vehicles for Human-Centered Mobility: Definition, Prospects, and Synergistic Co-Development with Vehicle Autonomy
Introduces agentic vehicles (AgVs) as conceptually distinct from but synergistic with autonomous vehicles (AuVs), emphasizing agency for goal handling and social contexts in human-centered mobility.
-
A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.