OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies
Summary
OmniTacTune introduces a two-stage reinforcement learning pipeline for adapting tactile feedback to pretrained visual robot policies, achieving 85-100% success on contact-rich manipulation tasks within 40-80 minutes.
View Cached Full Text
Cached at: 07/09/26, 07:40 PM
Paper page - OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies
Source: https://huggingface.co/papers/2607.03723
Abstract
OmniTacTune enables efficient adaptation of tactile feedback to visual robot policies through a two-stage reinforcement learning approach that improves success rates in contact-rich manipulation tasks.
Visual policieslearned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail incontact-rich manipulation, where success significantly depends on local force and contact geometry.Tactile sensingprovides these complementary signals, yet tactile data remain costly to collect and hard to generalize across sensors, robots, and tasks. We introduce OmniTacTune, apolicy-agnosticreal-world RLpipeline that adaptstactile feedbackto pretrainedvisual policiesthroughresidual correction. OmniTacTune uses a two-stage design: it first bootstrapstactile-aware learningfrom autonomousbase-policy rollouts, then learns a lightweighttactile residual policythrough 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 adaptingtactile feedbackto scalable visual robot policies. Project page: https://colinyu1.github.io/omnitactune-site/
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2607\.03723
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.03723 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.03723 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.03723 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Warp RL: Reshaping Base Policy Distributions for Dynamics Adaptation
Warp RL replaces additive residual corrections in reinforcement learning with an invertible, state-conditioned transformation of the base policy's action distribution using monotonic rational-quadratic spline flows, enabling adaptation of distribution shape, scale, and geometry under dynamics shifts. It matches or outperforms residual correction in ManiSkill3 manipulation tasks and achieves 30% faster task completion in a real robot peg-insertion task.
Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time
This paper introduces a retrieval-augmented vision-language-action policy that eliminates per-task fine-tuning by using pre-trained models with indexed demonstrations, enabling efficient cross-embodiment generalization and task adaptation at test time.
RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures
RoboTALES introduces a two-stage framework combining LLM-based planning and VLM-based criticism to improve task-aligned video generation and robotic policy training, significantly outperforming existing methods on long-horizon manipulation tasks.
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
This paper introduces Retention-aware Policy Optimization (RaPO) to mitigate catastrophic forgetting in visual continual learning using reinforcement fine-tuning. RaPO uses trajectory-level reward shaping and cross-task advantage normalization to close the gap between reinforcement and supervised fine-tuning in class- and domain-incremental learning.
Robotic Policy Adaptation via Weight-Space Meta-Learning
Introduces WIZARD, a weight-space meta-learning framework that generates task-specific LoRA parameters for frozen VLA policies from language instructions and demonstration videos, enabling efficient task adaptation without fine-tuning.