LingBot-Touch: open-source tactile foundation model pretrained on ~5,000 hours of real data
alifcoder · x · 2026-11-10
Robbyant released LingBot-Touch, an open-source tactile foundation model for dexterous manipulation, pretrained on nearly 5,000 hours of real tactile data using a JEPA-style objective.
- Unlike text, images and video, touch data must be physically recorded rather than scraped, yet the self-supervised learning pattern still holds
- Unified heterogeneous tactile modeling enables transfer across sensors, dexterous hands, tasks, and action models
- The reposter reads this as confirmation that self-supervised learning extends from text → images → video → touch
Related event: Ant's Robbyant Open-Sources LingBot-Touch Tactile Foundation Model(30 posts)→
More from Embodied
- Long-horizon mobile manipulation called the standout demo at CoRL — JasonMa2020 · 2026-11-11
- UCLA's TRIMI turns the data glove itself into the robot hand — DennisHongRobot · 2026-11-11
- Supersplat XR update: Quest 3 streamed scenes jump from 9.7 to 30+ fps, Vision Pro gets WebGPU — willeastcott · 2026-11-11
- Cartwheel releases three open motion-tracking policies for humanoid robots on Hugging Face — andrew_n_carr · 2026-11-11
- Claude Fable 5.2 designs a humanoid robot overnight with CAD, sim and reel — davidpattersonx · 2026-11-11
- Russ Tedrake's CoRL talk: deploy robots early, train on intervention data to scale — DominiqueCAPaul · 2026-11-11