mlsanityData to 14 Oct 2026

ViTaR: Visuo-Tactile Residual Adaptation for Foundation VLA Manipulation

arXiv 2608.15816 ↗First posted 16 Aug 2026cs.ROcited by 0

On the map: Vision-language-action models → Tactile, force-aware and humanoid VLA

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tactile, force-aware and humanoid VLA, one of 13 directions in Vision-language-action models. Builds on 28 of its 33 references that are in the map. First posted on arXiv 16 Aug 2026.

Builds on

28 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026TacCoRL: Integrating Tactile Feedback into VLA via Simulation10 Jun
  2. 2026TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation8 Jun

Other references · 26

  1. 2017Deep reinforcement learning from human preferencescited by 3,912
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  5. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 394
  6. 2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 302
  7. 2018Residual Reinforcement Learning for Robot Controlcited by 274
  8. 2023Controlling Text-to-Image Diffusion by Orthogonal Finetuningcited by 208
  9. 2018Residual Policy Learningcited by 164
  10. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 148
  11. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 145
  12. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 112
14 more
  1. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 108
  2. 2024Sparsh: Self-supervised touch representations for vision-based tactile sensingcited by 64
  3. 2024Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedbackcited by 21
  4. 2026UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarkingcited by 18
  5. 20239DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimationcited by 17
  6. 2024VITaL Pretraining: Visuo-Tactile Pretraining for Tactile and Non-Tactile Manipulation Policiescited by 15
  7. 2026Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attentioncited by 10
  8. 2026Learning Versatile Humanoid Manipulation with Touch Dreamingcited by 4
  9. 2026TactiDex: A Real-World Tactile-Guided Benchmark for Human-Like Dexterous Manipulationcited by 3
  10. 2026VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulationcited by 2
  11. 2026Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigmscited by 2
  12. 2026Feeling the Unexpected: ResTacVLA for Contact-Rich Manipulation via Residual Tactile Representationcited by 2
  13. 2026PrefMoE: Robust Preference Modeling with Mixture-of-Experts Reward Learningcited by 1
  14. 2026Risk-Aware Preference Learning for Stochastic Outcomescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026VT-Bridge: Bridging Pretrained Foundation VLAs to VTLAs via Lightweight Residual Adaptation
  2. 2026AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models
  3. 2025VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback
  4. 2026TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models
  5. 2026UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models
  6. 2026τ: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision
  7. 2026N0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens
  8. 2026HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing