Pelican-VLA 0.5: Attending Before Acting Benefits Generalization

2026-07-07

AI Summary

This work addresses the challenge of enabling vision-language-action (VLA) models to attend to instruction-relevant objects and contact regions in unseen environments and robot morphologies, without object annotations, segmentation masks, or task-specific fine-tuning. The authors propose a unified VLA architecture that integrates visual-language understanding, future frame prediction, and action generation, featuring learnable reasoning slots that serve as a compact information bottleneck between perception and action to efficiently route task-relevant signals. During pretraining, the model develops an operation-centric attention hierarchy that generalizes across tasks, allowing it to adapt to diverse policy structures without additional supervision. Experiments demonstrate that the method significantly outperforms existing open-source VLA baselines in zero-shot settings, exhibiting strong cross-scenario and cross-morphology generalization as well as precise attention to manipulation-relevant regions.

Abstract

In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language understanding, future-frame generation, and action prediction within a single architecture. Pelican-VLA 0.5 achieves attention-level generalization: without object annotations, segmentation masks, attention supervision, or task-specific fine-tuning, its action pathway already focuses on the instruction-relevant object and contact region. This behavior persists across unseen scenes and unseen robot embodiments, and is substantially stronger than in other open-source VLA baselines. We verify that this ability originates from the learnable Reasoning Slots inserted between perception and action: by routing task-relevant visual information through a compact bottleneck, the slot interface induces manipulation-centric attention during pre-training and remains effective across different policy structures, including a MoT-style architecture.

Problem

• vision-language-action
• attention generalization
• robot manipulation
• zero-shot transfer
• embodied AI

Innovation

• Reasoning Slots
• attention-level generalization
• vision-language-action model
• manipulation-centric attention
• bottleneck routing