Actra: Optimized Transformer Architecture for Vision-Language-Action Models in Robot Learning

Yueen Ma, DaFeng Chi, Shiguang Wu, Yuecheng Liu, Yuzheng Zhuang, Jianye HAO, Irwin King

Keywords: Robotics, Embodied AI, Transformer, Multimodality, Contrastive Learning, Dynamics Learning, Multimodal Alignment

TL;DR: An optimized Transformer architecture for vision-language-action models, designed to process multimodal trajectories in robot learning, complemented by a contrastive dynamics learning approach.

Abstract: Vision-language-action models have gained significant attention for their ability to model trajectories in robot learning. However, most existing models rely on Transformer models with vanilla causal attention, which we find suboptimal for processing segmented multi-modal sequences. Additionally, the autoregressive generation approach falls short in generating multi-dimensional actions. In this paper, we introduce Actra, an optimized Transformer architecture featuring trajectory attention and learnable action queries, designed to efficiently process segmented multi-modal trajectories in language-conditioned robot imitation learning. Furthermore, we propose a contrastive dynamics learning objective to enhance its understanding of environment dynamics and multi-modal alignment, complementing the primary behavior cloning objective. Through extensive experiments on three large-scale robot manipulation benchmarks, Actra exhibits substantial performance improvements over state-of-the-art models.

Primary Area: applications to robotics, autonomy, planning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2106