SOURCE-LINKED INTELLIGENCE

InfluenceField: A Differentiable Field with Interventionally Identifiable Causal Structure for Multimodal World Modeling

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Multimodal large language models often capture visual-linguistic correlations but struggle to predict how local visual interventions propagate and affect downstream answers. We introduce InfluenceField, an intervention-aware latent field inserted between the visual encoder and language decoder. It lifts patch features into a continuous spatial representation, propagates directed influence over multiple steps, and predicts local intervention effects through a shared transition operator. Training jointly optimizes language modeling, cross-environment invariance, counterfactual rollout supervisio

Read original source ↗ Open in workspace

recordType

paper

region

Global