TACO: TActile World Model as a Self-COrrector forScalable VLA Post-Training

• URL: http://arxiv.org/abs/2607.02840v1
• Date: Fri, 03 Jul 2026 00:23:30 GMT
• Title: TACO: TActile World Model as a Self-COrrector forScalable VLA Post-Training
• Abstract summary: We introduce TACO, a tactile-aware world-model-driven framework for scalable VLA post-training in contact-rich manipulation.<n>To incorporate tactile corrective supervision into VLA post-training, TACO combines knowledge-insulated tactile adaptation with advantage-conditioned training.
• Score: 79.94818813802682
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have shown promising generalization in robotic manipulation, but they still struggle with contact-rich tasks, where minor contact perturbations can cause unrecoverable failures that are hard to detect from vision alone. Since these failures are localized rather than task-level semantic errors, tactile-aware corrective post-training offers an efficient way to improve recovery. However, scaling such supervision through human intervention is costly. Recent works have explored world models to synthesize imagined rollouts for policy improvement, but vision-only world models may produce visually plausible yet contact-inconsistent trajectories. We therefore introduce TACO, a tactile-aware world-model-driven framework for scalable VLA post-training in contact-rich manipulation. Given real robot rollouts, TACO follows a Recognize-Imagine-Label loop with a tactile-aware world model: a unified progress-action model recognizes failure-adjacent states using progress estimates, a visuo-tactile generation model imagines local correction segments, and the progress-action model labels them with executable corrective actions. To incorporate tactile corrective supervision into VLA post-training, TACO combines knowledge-insulated tactile adaptation with advantage-conditioned training, enabling the policy to learn from imagined corrections without degrading pretrained visual-language priors. These components enable TACO to convert real-world failures into imagined visuo-tactile corrections for iterative VLA post-training. Experiments on real-world contact-rich manipulation tasks show that TACO achieves 44% absolute success rate improvement over the base policy and 32% over the policy without knowledge-insulated tactile adaptation.

Related papers

• $N_0$-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens [0.0]
  We present a vision-tactile-language-action (VTLA) foundation model capable of fine-grained contact-rich manipulation with tactile perception and tactile-feedback control.<n>We propose a training recipe for tactile integration consisting of visuo-tactile pre-training, staged tactile-pathway integration, and advantage-conditioned offline policy improvement.
  arXiv  Detail & Related papers  (2026-07-26T17:58:47Z)
• TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models [12.700838638661047]
  We propose a simple framework that supplies tactile feedback through visual augmentation rather than architectural change.<n>Because the architecture is untouched, the approach requires no tactile pre-training, adds negligible compute, and stays close to the pre-training distribution.<n>Across four contact-rich tasks, TAP-VLA succeeds on 78% of trials, compared to under 50% for vision-only fine-tuning and alternative tactile-fusion baselines.
  arXiv  Detail & Related papers  (2026-06-27T21:06:06Z)
• TacCoRL: Integrating Tactile Feedback into VLA via Simulation [38.963250081631834]
  Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation.<n>We present TacCoRL, a scalable framework that injects Tactile feedback into VLA policies.<n>We use a real-aligned simulator as a closed-loop training environment for contact interaction.
  arXiv  Detail & Related papers  (2026-06-10T07:20:36Z)
• EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models [84.73890225707264]
  We present EXPO-FT, a system for stable, sample-efficient RL finetuning of pretrained VLA policies.<n>Our system achieves perfect task performance (30/30 successes) across all evaluated tasks within an average of 19.1 minutes of online robot data.<n>We release an open-source robustness with the aim of facilitating broader adoption of RL finetuning of VLA models in robotics.
  arXiv  Detail & Related papers  (2026-05-25T06:31:03Z)
• Reinforcing VLAs in Task-Agnostic World Models [15.056103368344596]
  Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) have emerged as an effective strategy to adapt to new tasks without costly real-world interactions.<n>We argue that world and reward models should capture transferable physical priors that enable zero-shot inference.<n>We propose RAW-Dream, a new paradigm that completely disentangles world model learning from downstream task dependencies.
  arXiv  Detail & Related papers  (2026-05-12T16:16:15Z)
• VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs [47.982092015932444]
  Video-Action Models (VAMs) have emerged as a promising framework for embodied intelligence.<n>We introduce the Video-Tactile Action Model (VTAM), a multimodal world modeling framework that incorporates tactile perception as a grounding signal.<n>VTAM augments a pretrained video transformer with tactile streams via a lightweight modality transfer finetuning.
  arXiv  Detail & Related papers  (2026-03-24T17:45:06Z)
• Tactile Modality Fusion for Vision-Language-Action Models [22.788833830429766]
  We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models.<n>Results show consistent improvements in success rate, direct insertion performance, completion time, and force stability across both in-distribution and out-of-distribution tasks.
  arXiv  Detail & Related papers  (2026-03-15T20:57:51Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.