# Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention

arXiv: https://arxiv.org/abs/2606.26663 · HTML: https://mlsanity.com/paper/2606.26663/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 11 of 11)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.02881/) (2025)
- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [Prediction with Action: Visual Policy Learning via Joint Denoising Process](https://mlsanity.com/paper/2411.18179/) (2024)
- [Sparsh: Self-supervised touch representations for vision-based tactile sensing](https://mlsanity.com/paper/2410.24090/) (2024)
- [Visuo-Tactile World Models](https://mlsanity.com/paper/2602.06001/) (2026)
- [UniT: Data Efficient Tactile Representation with Generalization to Unseen Objects](https://mlsanity.com/paper/2408.06481/) (2024)
- [ManiFeel: Benchmarking and Understanding Visuotactile Manipulation Policy Learning](https://mlsanity.com/paper/2505.18472/) (2025)

## Built on by (most cited first, 10 of 10)

- [TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction](https://mlsanity.com/paper/2607.28391/) (2026)
- [N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2607.23783/) (2026)
- [Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning](https://mlsanity.com/paper/2608.07558/) (2026)
- [Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control](https://mlsanity.com/paper/2609.20761/) (2026)
- [Disentangling Visuo-Tactile Foresight: Oracle-Guided Interface Discovery for World Action Models](https://mlsanity.com/paper/2608.00547/) (2026)
- [ViTaR: Visuo-Tactile Residual Adaptation for Foundation VLA Manipulation](https://mlsanity.com/paper/2608.15816/) (2026)
- [VT-MUSE: Multimodal Unified Sequential Visuotactile Representation Learning for Manipulation](https://mlsanity.com/paper/2608.21290/) (2026)
- [HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing](https://mlsanity.com/paper/2609.23888/) (2026)
- [Uni-VLaT: Whole-Body Tactile Adaptation of VLA Policies for Humanoid Loco-Manipulation](https://mlsanity.com/paper/2609.35450/) (2026)
- [TacDyn-WAM: Learning Implicit Tactile Dynamics in a Heterogeneous Visuo-Tactile World Action Model](https://mlsanity.com/paper/2610.00638/) (2026)

## Abstract (arXiv)

World Action Models (WAMs) jointly predict future visual observations and actions, but visual futures alone often miss slip, jamming, contact-direction changes, and subtle misalign- ment in contact-rich manipulation. Tactile signals reveal these hidden physical states, yet naive tactile-token injection can disrupt visual dynamics modeling due to the limited scale of tactile data, a phenomenon we term tactile pollution. We in- troduce Tactile-WAM, which uses asymmetric attention to block video queries from tactile keys while preserving tac- tile access for action queries. A contact-change-aware bias further strengthens action attention to touch. Because tactile pixel changes do not reliably reflect contact changes, we derive Observed proxy changes drive the attention bias, while future- proxy supervision preserves action-relevant contact dynamics in predicted tactile representations. On ManiFeel, visual-path isolation reduces deviation from the RGB-only trajectory by 21.8% in MSE at the step-matched 20K checkpoint without a statistically detectable change in ground-truth video qual- ity. The full model improves average success from 15.6% to 32.7%, with VideoClean providing the largest gain. On five real-robot tasks, Tactile-WAM achieves 49.2% success.