As Vision-Language-Action (VLA) models scale toward real-world deployment, contact-rich manipulation exposes a critical blind spot: these policies encode broad visual-semantic priors yet remain unaware of local contact events, producing identical actions whether contact is established, lost, or destabilized. Existing remedies either modify VLA internals, risking catastrophic forgetting, or demand online reinforcement under near-failure contact conditions. Both grant tactile unbounded influence over action generation, conflicting with the priors that make VLAs generalizable. We introduce ViTaR, which reframes tactile feedback from an action-generating perceptual input to an execution modulator that selects and scales bounded residual corrections atop a frozen VLA, preserving pretrained capabilities by construction. ViTaR decomposes adaptation into two stages: Effect-Guided Modeling determines whether and which correction is locally justified via outcome-grounded preference evidence, and Residual Action Modulation converts this evidence into a residual choice with continuously scaled gain from real-time visuotactile observations. On the UniVTAC benchmark spanning seven contact-rich tasks, ViTaR achieves 61.3% average success, a 30.6 percentage-point improvement over its frozen VLA base that also surpasses purpose-built tactile baselines. Physical-robot experiments confirm that bounded tactile modulation transfers to real sensor noise and dynamics.
This folder is the complete, dependency-free ViTaR GitHub Pages source. To preview it locally, run the following command from this folder and open the printed local URL:
python3 -m http.server 8000To publish it in the icr-lab repository, copy the contents of this folder—including index.html and assets/—to that repository’s root. Then select Settings → Pages → Deploy from a branch, choose the deployment branch, and select /(root).
Before release, update the remaining placeholder arXiv and Video links at the top of this README, together with the corresponding Paper and Code links in index.html.
The real-world videos are web-optimized H.264/AAC MP4 files with fast-start metadata and lightweight poster images, so they can begin loading promptly in GitHub Pages and common browsers.
The overview section also includes the four-minute project video at assets/videos/vitar-overview.mp4.