arXiv:2610.36535v1 Announce Type: new Abstract: Differences in musculoskeletal morphology challenge policy reuse across individual models. Here we present MyoAcross, a…
arXiv:2610.36430v1 Announce Type: new Abstract: A track fitting pipeline is presented that converts a measured racetrack point cloud into a closed, $C^4$ differentiable…
arXiv:2611.08827v1 Announce Type: new Abstract: Vision-language-action (VLA) models perform versatile manipulation tasks from language instructions, but their inference…
arXiv:2611.17775v1 Announce Type: new Abstract: World models that support planning, control, and interpretable reasoning require latent representations that genuinely…
arXiv:2611.05776v1 Announce Type: new Abstract: Adaptive sampling can substantially improve the value of sparse ocean observations by directing mobile robots toward…
arXiv:2611.23803v1 Announce Type: new Abstract: General robot manipulation requires both semantic competence and physical foresight. World action models (WAMs) acquire…
Eka Robotics is building a vision-force-action, or VFA, model to develop an intuition of physics through reinforcement learning at scale. The post Eka Robotics raises…
arXiv:2611.18123v1 Announce Type: new Abstract: Semantic exploration methods for object-goal navigation use large language models (LLMs) to score how strongly a target…
arXiv:2610.33685v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are bottlenecked by the scarcity of robot data. Egocentric human manipulation videos…
arXiv:2611.23714v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become a powerful paradigm for robotic manipulation and show strong promise for…
arXiv:2611.13592v1 Announce Type: new Abstract: Pretrained latent world models can support visual planning and control, but their predictions may fail when physical…
arXiv:2606.23641v2 Announce Type: replace Abstract: Vision-language-action (VLA) models have the potential for open-world generalization by leveraging pretrained…
arXiv:2610.31779v1 Announce Type: new Abstract: The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for…
arXiv:2610.32271v1 Announce Type: new Abstract: Vision-language-action (VLA) models are typically pretrained on broad, diverse datasets and subsequently fine-tuned on a…
arXiv:2611.25134v1 Announce Type: new Abstract: Visual world models enable effective short-horizon goal-conditioned planning, such as reaching nearby targets and pushing…
arXiv:2611.13204v1 Announce Type: new Abstract: Many rehabilitation robots execute prescribed motions using reactive tracking controllers that do not explicitly…
Helm.ai trained its foundation models using its unsupervised 'deep teaching' methodology to master the structure of the physical world itself. The post Helm.ai reaches…
Rhoda AI offers a direct video action model, which it recently extended with mobile DVA, to enable robots to understand the physical world. The post How Rhoda AI is…
arXiv:2611.23620v1 Announce Type: new Abstract: A frozen latent world model combined with sampling-based model predictive control is a visual planner. At deployment, the…
arXiv:2611.13229v1 Announce Type: new Abstract: Efficient robotic 3D reconstruction requires selecting views that contribute new surface measurements with few physical…