Touch-JEPA is a framework that learns tactile representations from hand‑object videos using limited tactile supervision. It first trains a self‑supervised model that predicts masked visual features at hand‑surface locations, capturing latent contact dynamics. The model is then jointly fine‑tuned on a small labeled subset, improving contact discrimination and tactile magnitude estimation on human‑hand benchmarks and transferring to robotic hands without robot tactile data.
arXiv:2610.10288v1 Announce Type: new Abstract: Large-scale egocentric human interaction data is becoming an important source of physical supervision for embodied learning, yet video alone leaves the...
TouchSight is a monocular egocentric vision framework that predicts dense full-hand contact forces without tactile sensors. It uses 500 hours of pressure-glove data and a 20-hour TwinTouch-20H dataset where generative models render gloved recordings as bare-hand videos, bridging the appearance gap. The system outperforms previous methods on OakInk2, generalizes to unseen natural bare-hand egocentric videos, and improves as glove supervision increases.
TouchSight is a monocular egocentric vision framework that predicts dense full-hand contact forces from video. It uses 500 hours of pressure‑glove recordings and hand‑object interaction data, and introduces TwinTouch‑20H, a dataset of 20 hours of paired visual data where generative models render gloved recordings as bare‑hand observations while preserving tactile labels. The system outperforms prior methods on OakInk2, generalizes qualitatively to natural bare‑hand egocentric videos from unseen datasets, and improves consistently as glove supervision scales.
arXiv:2608.15060v2 Announce Type: replace Abstract: Touch is fundamental to dexterous manipulation, yet most egocentric human data increasingly used for robot learning lacks tactile information. Dire...
arXiv:2610.27995v1 Announce Type: cross Abstract: Tactile representation learning for dexterous manipulation often requires substantial robot-side data collection, limiting its scalability across dif...
arXiv:2606. 09243v1 Announce Type: cross Abstract: Estimating full-hand grasp pressure from egocentric video is critical for immersive VR and robotic manipulation, yet dense tactile sensing often relies on intrusive hardware.
arXiv:2610.09455v1 Announce Type: new Abstract: Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand track...
arXiv:2610.10283v1 Announce Type: cross Abstract: Humans can grasp everyday objects with almost perfect success rates using fingertip tactile feedback, yet much of the robotic grasping literature emp...
Tactile-JEPA is a self‑supervised pre‑training method for distributed tactile sensors that leverages the sensors’ spatial topology to learn topology‑aware representations. It predicts embeddings of masked sensing elements using a sensor connectivity graph and dual‑scale masking to capture both local contact details and the global tactile surface state. Evaluated on three diverse datasets, it improves force estimation by 6.3 % and in‑hand orientation error by 20.8 % over previous state‑of‑the‑art methods, and yields consistent gains in downstream tasks such as policy learning.
arXiv:2609.23352v1 Announce Type: new Abstract: Bimanual interaction produces complementary tactile views of the same physical process, yet existing tactile representation learning largely models the...
arXiv:2609.24976v1 Announce Type: cross Abstract: Dexterous manipulation depends on contact dynamics that are often only partially observable from vision. Recent World-Action Models (WAMs) couple pre...
DreamTacVLA is a Vision‑Language‑Action framework that incorporates high‑resolution tactile images alongside wrist‑camera and third‑person vision to enable robots to anticipate and react to contact dynamics. It uses a Hierarchical Spatial Alignment loss to align tactile tokens with visual counterparts and a tactile world model to predict future tactile signals, trained on a hybrid dataset from digital twins and real experiments. The approach achieves up to 95% success on contact‑rich manipulation tasks, outperforming existing VLA baselines.