{"ID":2861334,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01711","arxiv_id":"2510.01711","title":"Contrastive Representation Regularization for Vision-Language-Action Models","abstract":"Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap between VLM representations and robotic signals. In particular, RS-CL aligns the representations more closely with the robot's proprioceptive states by using relative distances between the states as soft supervision. Complementing the original action prediction objective, RS-CL enhances control-relevant representation learning, while being lightweight and fully compatible with standard VLA training pipelines. Our empirical results demonstrate that RS-CL substantially improves the performance of state-of-the-art VLA models; it pushes the prior art to 69.7% achieving the state-of-the-art performance on the RoboCasa-Kitchen benchmark, and boosts success rates from 45.0% to 58.3% on challenging real-robot manipulation tasks.","short_abstract":"Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive informa...","url_abs":"https://arxiv.org/abs/2510.01711","url_pdf":"https://arxiv.org/pdf/2510.01711v3","authors":"[\"Taeyoung Kim\",\"Jimin Lee\",\"Myungkyu Koo\",\"Dongyoung Kim\",\"Kyungmin Lee\",\"Changyeon Kim\",\"Younggyo Seo\",\"Jinwoo Shin\"]","published":"2025-10-02T06:41:22Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}