VLMs possess a latent 3D scene topology subspace corresponding to Laplacian eigenmaps that can be causally shaped via Dirichlet energy regularization to improve spatial task performance by up to 12.1%.
Causal abstractions of neural networks.Advances in neural information processing systems, 34:9574–9586, 2021
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
The paper argues that agent security is best addressed as a systems problem by applying principles from operating systems, networks, and formal methods rather than relying solely on model robustness improvements.
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
citing papers explorer
-
Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
VLMs possess a latent 3D scene topology subspace corresponding to Laplacian eigenmaps that can be causally shaped via Dirichlet energy regularization to improve spatial task performance by up to 12.1%.
-
Agent Security is a Systems Problem
The paper argues that agent security is best addressed as a systems problem by applying principles from operating systems, networks, and formal methods rather than relying solely on model robustness improvements.
-
Responsible Agentic AI Requires Explicit Provenance
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.