mlsanityData to 14 Oct 2026

OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies

arXiv 2607.03723 ↗First posted 4 Jul 2026cs.RO cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Visual policies learned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail in contact-rich manipulation, where success significantly depends on local force and contact geometry. Tactile sensing provides these complementary signals, yet tactile data remain costly to collect and hard to generalize across sensors, robots, and tasks. We introduce OmniTacTune, a policy-agnostic real-world RL pipeline that adapts tactile feedback to pretrained visual policies through residual correction. OmniTacTune uses a two-stage design: it first bootstraps tactile-aware learning from autonomous base-policy rollouts, then learns a lightweight tactile residual policy through online interaction. Extensive experiments show that OmniTacTune generalizes across diverse contact-rich tasks, visual base policies, and tactile representations. Across four real-world contact-rich tasks, it improves visual base policies from 5-40% success to 85-100% within 40-80 minutes, demonstrating an efficient path for adapting tactile feedback to scalable visual robot policies. Project page: https://colinyu1.github.io/omnitactune-site/

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 61 of its 69 references that are in the map. First posted on arXiv 4 Jul 2026.

Builds on

61 of 69 references.

References · 61

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  3. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  4. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  5. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  6. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  7. 2023Learning Interactive Real-World Simulatorscited by 458
  8. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 372
  9. 2023Efficient Online Reinforcement Learning with Offline Datacited by 363
  10. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
  11. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 266
  12. 2023Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuningcited by 237
38 more
  1. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 211
  2. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learningcited by 189
  3. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 175
  4. 2020DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulationcited by 167
  5. 2022Human-to-Robot Imitation in the Wildcited by 161
  6. 2024Flow as the Cross-Domain Manipulation Interfacecited by 132
  7. 2024CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videoscited by 128
  8. 2025Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulationcited by 108
  9. 2026EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Datacited by 94
  10. 2024From Imitation to Refinement -- Residual RL for Precise Assemblycited by 90
  11. 2023Rotating without Seeing: Towards In-hand Dexterity through Touchcited by 84
  12. 2025Self-Improving Vision-Language-Action Models with Data Generation via Residual RLcited by 78
  13. 2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 75
  14. 20243D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensingcited by 72
  15. 2024OPEN TEACH: A Versatile Teleoperation System for Robotic Manipulationcited by 71
  16. 2024A Touch, Vision, and Language Dataset for Multimodal Alignmentcited by 69
  17. 2024Sparsh: Self-supervised touch representations for vision-based tactile sensingcited by 64
  18. 2024Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Datacited by 63
  19. 2023Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Playcited by 62
  20. 2026EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the Worldcited by 57
  21. 2026RL Token: Bootstrapping Online RL with Vision-Language-Action Modelscited by 49
  22. 2024Transferable Tactile Transformers for Representation Learning Across Diverse Sensors and Taskscited by 45
  23. 2023The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objectscited by 41
  24. 2026VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Modelcited by 41
  25. 2024ViViDex: Learning Vision-based Dexterous Manipulation from Human Videoscited by 35
  26. 2023MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulationcited by 34
  27. 2025Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Correctionscited by 29
  28. 2025Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Grippercited by 29
  29. 2024Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewardscited by 28
  30. 2025X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Realcited by 28
  31. 2023The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learningcited by 26
  32. 2024Tactile-Augmented Radiance Fieldscited by 26
  33. 2024AnySkin: Plug-and-play Skin Sensing for Robotic Touchcited by 23
  34. 2025ViTaMIn: Learning Contact-Rich Tasks Through Robot-Free Visuo-Tactile Manipulation Interfacecited by 23
  35. 2025EMMA: Scaling Mobile Manipulation via Egocentric Human Datacited by 21
  36. 2025ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolationcited by 20
  37. 2021Active Extrinsic Contact Sensing: Application to General Peg-in-Hole Insertioncited by 19
  38. 2025SAIL: Faster-than-Demonstration Execution of Imitation Learning Policiescited by 18

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ForceDelta-VLA: Distilling Force-Conditioned ActionCorrections for Contact-Rich Manipulationcited by 0