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

[2606.26663] Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention Skip to main content Search Submit Donate Log in Computer Science > Robotics arXiv:2606.26663 (cs) [Submitted on 25 Jun 2026 ( v1 ), last revised 27 Aug 2026 (this version, v3)] Title: Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention Authors: Siyu Wu , Linjing You , Junjie Zhu , Yaozu Liu , Huang Kaixiang , Chen Yonghang , Jituo Li , Changhao Zhang , Jian Liu , Hengshuo Chu , Qi Li , Hengshuang Zhao View PDF HTML (experimental) Abstract: 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. Comments: Submitted to RSS2026 WorkShop Tactile for FM Subjects: Robotics (cs.RO) Cite as: arXiv:2606.26663 [cs.RO] (or arXiv:2606.26663v3 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2606.26663 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Linjing You [ view email ] [v1] Thu, 25 Jun 2026 06:54:56 UTC (16,013 KB) [v2] Thu, 6 Aug 2026 04:25:27 UTC (19,641 KB) [v3] Thu, 27 Aug 2026 07:42:24 UTC (19,641 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.RO < prev | next > new | recent | 2026-06 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention#677654
• TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation#972202
• AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation#1037015
• TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation#677639
• TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation#674438