FOCAL‑VLA is a framework that improves vision‑language‑action models by combining subtask‑guided geometry distillation with implicit world modeling. It transfers geometric knowledge from VGGT to focus on subtask‑relevant image regions and uses Track4World features to capture future 3D evolution, guiding action generation without running these models at inference time. Experiments demonstrate that FOCAL‑VLA outperforms baselines on both simulation benchmarks and real‑world manipulation tasks.
arXiv:2606. 17046v1 Announce Type: cross Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world.
arXiv:2607. 05468v1 Announce Type: cross Abstract: World Action Models (WAMs) have shown strong potential for robotic manipulation by jointly modeling visual future dynamics and executable action sequences.
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
The paper introduces a metric interaction framework for robotic manipulation that explicitly models object- and scene-level interactions in Cartesian space. It uses Interaction‑Centric Tokens (ICTs) to represent end‑effector trajectories relative to objects and a Metric Action Interaction Field (MAIF) to attend to scene point‑cloud features for geometry‑conditioned action corrections. Experiments show modest but consistent improvements across several benchmarks, including LIBERO, RoboTwin 2.0, and real‑world tasks.
GeoLAM is a framework that learns geometry‑grounded latent actions from unlabeled human videos. It uses future‑frame reconstruction with a frozen geometric feature hierarchy and motion supervision from a 4D geometry teacher to capture 3D displacement, image‑plane motion, and surface‑orientation changes. After pretraining, the representation serves as transition targets for a world‑action model trained on robot demonstrations, enabling denoised latent actions and executable action chunks without requiring hand‑pose annotations or future‑video generation during deployment.
Vision-Language-Action models and World-Action Models have advanced language-conditioned robotic manipulation, yet often leave metric relations among actions, objects, and scene geometry implicit. Hum...
arXiv:2606. 12217v1 Announce Type: cross Abstract: World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions.
arXiv:2606. 08530v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot embodiments.
arXiv:2607. 04714v1 Announce Type: cross Abstract: Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations.
World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions. However, our empirical observations reveal a phenomenon: generating plausible visual futures does not always guarantee the extraction of accurate actions.
arXiv:2606. 24472v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras -- a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images.
arXiv:2606. 13769v1 Announce Type: cross Abstract: World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels.