Vision-Language-Action (VLA) models aim to predict robotic actions based on visual observations and language instructions. Existing approaches require fine-tuning pre-trained visionlanguage models (VLMs) as visual and language features are independently fed into downstream policies, degrading the pre-trained semantic alignments. We propose OTTER, a novel VLA architecture that leverages these existing alignments through explicit, text-aware visual feature extraction. Instead of processing all visual features, OTTER selectively extracts and passes only task-relevant visual features that are semantically aligned with the language instruction to the policy transformer. This allows OTTER to keep the pre-trained vision-language encoders frozen. Thereby, OTTER preserves and utilizes the rich semantic understanding learned from large-scale pre-training, enabling strong zero-shot generalization capabilities. In simulation and real-world experiments, OTTER significantly outperforms existing VLA models, demonstrating strong zeroshot generalization to novel objects and environments. Video, code, checkpoints, and dataset:this https URL.
View on arXiv@article{huang2025_2503.03734,
title={ OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction },
author={ Huang Huang and Fangchen Liu and Letian Fu and Tingfan Wu and Mustafa Mukadam and Jitendra Malik and Ken Goldberg and Pieter Abbeel },
journal={arXiv preprint arXiv:2503.03734},
year={ 2025 }
}