The paper introduces Segment‑Snap, a method that jointly models movable parts, their motion, and the regions they operate on in 3D scenes. It uses learned predictors to identify part surfaces and handles, a geometric decoder to constrain motion with planar and upright priors, and a joint part‑and‑handle predictor to refine motion classes. Experiments on Articulate3D show that handle guidance boosts motion‑gated AP from 13.74% to 40.98%, while additional handle candidates and part‑based corrections further improve performance.
arXiv:2609.38466v1 Announce Type: new Abstract: Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input te...
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:2609.19119v1 Announce Type: new Abstract: Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes...
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.
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.
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.
Text-conditioned 3D generation has progressed rapidly for images and isolated objects, but producing a hand-object mesh remains challenging: the output must preserve language semantics, cross-view consistency, object geometry, articulated hand shape, and physically plausible contact. We present TextHOI-3D, a staged framework that uses generated multi-view observations as an explicit interface between text-conditioned visual generation and geometry-aware hand-object recovery.
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. 11805v1 Announce Type: cross Abstract: Text-conditioned 3D generation has progressed rapidly for images and isolated objects, but producing a hand-object mesh remains challenging: the output must preserve language semantics, cross-view consistency, object geometry, articulated hand shape, and physically plausible contact.
FunArt is a framework that builds articulation‑aware functional 3D scene graphs from a single static RGB‑D observation. It reconstructs object instances, converts their geometry into the O‑Voxel representation of TRELLIS.2, and uses a frozen sparse‑compression VAE as a structural prior. A lightweight query‑based decoder jointly segments movable parts and functional interactive elements while estimating motion type, axis, origin, and range, achieving state‑of‑the‑art results on the Articulate3D dataset.
arXiv:2609.27675v2 Announce Type: replace Abstract: Understanding articulated objects is fundamental for robotic interaction, requiring accurate rigid-part discovery and the recovery of their kinemat...