cs.RONov 18, 2026

CoRA-VTLA: Contact-Guided Attention and Queryable Response Memory for Tactile Post-Training

Authors: Chengye Song, Rui Song, Shengqi Wang, Jiawei Zhang, Hongzhou Wang, Xueyang Guo, Yang Liu

Organizations: Dalian University of Technology · Jilin University · Enomind Technology · Tsinghua University

Abstract

In precision manipulation, small errors in alignment or force can cause jamming or deformation, making contact feedback essential for adapting pretrained vision-language-action (VLA) models to these tasks. A single tactile observation leaves the response to recent actions ambiguous. Direct tactile fusion during post-training can also disperse the action expert's visual attention and reduce the share it allocates to contact regions. To address these challenges, CoRA-VTLA augments pretrained VLAs with lightweight tactile modules. A queryable action-response memory retrieves recent contact responses so that the action expert can combine them with immediate tactile feedback. Contact-guided gaze supervision concentrates the visual attention of the tactile semantic token on image regions corresponding to fingertip contact. CoRA-VTLA achieves 73.33% mean success across three MuJoCo tasks, compared with 50% for direct tactile fusion with the same sensor inputs. It also achieves 67% success on an optical-tactile task from the public UniVTAC benchmark and 66.7% mean success across three real-robot tasks. These results show that tactile post-training helps pretrained VLAs adjust to changing contact.

Figures & tables

Explore similar work

CardsList
  1. TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models

    Jun 27, 2026Mark Van der Merwe, Mohamad Louai Shehab, Jayjun Lee +4Vision-Language-Action ModelsTactile Sensing for Robotic Manipulation

  2. TACO: TActile World Model as a Self-COrrector for Scalable Robot Policy Post-Training

    Jul 3, 2026Shengbang Liu, Yueru Jia, Yuyang Yan +7Robot Skill LearningWorld Models for Robotics