Research

DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies

Single source1 source8 Oct 2026

arXiv:2610.09144v1 Announce Type: new Abstract: Vision-language-action (VLA) policies typically feed dense visual patch tokens into a language-action backbone, preserving scene context but offering no explicit mechanism to regulate how strongly different visua

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.09144

← Back to all developments · Signals are a development reported by more than one source. See the methodology.