VTAM is a visuo‑tactile world‑action model that enables efficient contact‑rich manipulation without requiring tactile or action pretraining. It shares a frozen video VAE and pretrained transformer between RGB and tactile inputs, then fine‑tunes a randomly initialized action expert to predict actions, proprioception, and a flow‑force proxy derived from tactile optical flow. Trained solely on task demonstrations, VTAM outperforms baselines on real‑robot and simulation tasks, runs significantly faster than comparable models, and transfers zero‑shot across different tactile sensors.
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...
Agile-WAM is a tactile World Action Model that jointly predicts future visual and tactile states and robot actions for contact‑rich manipulation. It encodes visual and tactile observations into a shared latent space and uses a vision‑tactile‑to‑action flow‑matching process to generate action chunks and future latents. The model introduces multi‑horizon multimodal prediction, leveraging the different timescales of vision and touch, and achieves a 29.4 % improvement in real‑world success rates with 11.9 ms inference latency across nine simulated and five real‑world tasks.
arXiv:2606. 11743v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation, but visual observations alone often miss the local contact state required for contact-rich tasks.
arXiv:2608.29601v2 Announce Type: replace-cross Abstract: We present $N_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale mul...
arXiv:2603. 14604v2 Announce Type: replace-cross Abstract: We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models.
arXiv:2608.29601v1 Announce Type: cross Abstract: We present $\mathcal{N}_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale m...
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...
arXiv:2609.15726v1 Announce Type: cross Abstract: Tactile sensing provides contact information that can be difficult to infer from vision alone, but tactile hardware for dexterous hands has not conve...
arXiv:2606. 14981v1 Announce Type: cross Abstract: Inference-time steering adapts pre-trained generative robot policies during deployment by verifying candidate actions before execution.
arXiv:2609.34182v2 Announce Type: replace-cross Abstract: Dexterous manipulation requires tactile feedback. However, robot tactile demonstrations are difficult to scale,because dexterous-hand teleope...
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.
arXiv:2609.21449v1 Announce Type: new Abstract: World Action Models bring the predictive capabilities of video models into robot action generation, providing a rich foundation for modeling future vis...