SOURCE-LINKED INTELLIGENCE

DeicticVLA: Unifying Instruction Modes Based on Language and Deictic Gestures in a Single VLA

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Vision-Language-Action models (VLAs) allow users to specify manipulation tasks in natural language, but distinguishing a target or placement goal among objects of the same category or similar appearance requires detailed expressions that VLAs may not use reliably. We propose DeicticVLA, which canonicalizes Language Instruction (LI), Vision-Language Instruction (VLI), and Visual Instruction (VI) into a text prompt and deictic masks through text-prompt completion and deictic gesture grounding, enabling a single pretrained VLA to handle all three instruction modes. With a shared backbone, demonst

Read original source ↗ Open in workspace

recordType

paper

region

Global