Spatial Grafting is proposed, a versatile, lightweight spatial module that binds frozen reconstruction features to metric, robot-relative geometry and injects them into the flow-matching action expert through cross-attention without modifying the host's perceptual pathway, so the host retains the full benefit of its pretraining.
Abstract
Pretrained robot manipulation policies such as vision-language-action models (VLAs) or world-action models (WAMs) leave interaction-relevant metric geometry implicit. Recent breakthroughs in spatial reconstruction can supply the necessary geometry reliably, but their features describe local shape without stating where it lies with respect to the robot. How best to deliver these features to a pretrained policy remains unresolved. We propose Spatial Grafting, a versatile, lightweight spatial module that binds frozen reconstruction features to metric, robot-relative geometry. Spatial Grafting constructs metric-grounded spatial tokens and injects them into the flow-matching action expert through cross-attention, without modifying the host's perceptual pathway, so the host retains the full benefit of its pretraining. We evaluate it more broadly than any geometry-aware policy we compare against: one graft architecture, with no per-host redesign, on two VLAs and two WAMs, across four simulation benchmarks that span short-horizon manipulation, visual robustness, clutter and long-horizon mobile manipulation, and on three real-robot platforms with single- and dual-arm configurations. On RoboTwin 2.0, a dual-arm manipulation benchmark, the graft improves every host across VLAs and WAMs. Grafted $\pi_{0.5}$ gains 11.3% and 15.6% on clean and randomized scenes, reaching 94.0% and 92.4%, above the strongest published 3D-conditioned policy, WAM4D (93.8% and 89.9%). The margin widens as the horizon lengthens: on tasks from BEHAVIOR-1K, a dual-arm mobile manipulation challenge scored by average task progress, it surpasses the 2025 challenge winner on five of six tasks,by up to 0.47 Q-score, and exceeds a map-conditioned spatial policy on average across the three tasks both report.
GaussVLA is proposed, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, and Depth-Aware Chain-of-Thought (DA-CoT) that performs structured, non-autoregressive geometric reasoning under language and flow-ti...
MD SELIM SAROWAR, Md Tanvir Islam, Sungho Kim et al.· 1 citation
Robots need to anticipate how their actions will change the world, since manipulation success hinges on the resulting contacts and object motions. However, existing Vision-Language-Action (VLA) policies that predict future observations from shared features leave the forecast decoupled from the actions the policy will a...
Zhe Tao, Fei-Ran Wang, Gao-Wen Liu et al.· 0 citations
Predicting 3D consistent waypoints (3DWay) from multi-view images as generating multi-view consistent 2D waypoints followed by geometric triangulation enables explicit 3D motion specification while preserving the strong priors of pretrained VLMs.
Zi-Qin Huang, Ying-Yue Li, Chenyangguang Zhang et al.· 0 citations
We introduce BIND, a new action representation for visuomotor robot policies that binds 3D robot actions to their corresponding 2D image features, yielding strong data efficiency gains and robustness to out-of-distribution object positions and camera viewpoints. The action heads of current robot policies are typically...
C. Smith, Arsh Tangri, V. Guizilini et al.· 0 citations
Spa-Bench is introduced, a real-robot benchmark that evaluates spatial grounding across six tabletop tasks covering Object State, Relative Size, Referential Description, Relational Placement, Ordinal Position, and Counting, and shows that the evaluated VLAs can often execute the required manipulations but lack robust s...
Justin Tien-Smith, Matthew Pidden, Rolandos Alexandros Potamias· 1 citation
Grounded Action Models (GAMs), a new paradigm of robot foundation models built with 3D grounding, are proposed, which can be run autonomously and serve as a low-level controller that a high-level planner controls using its various input modalities, allowing for long-horizon and memory-dependent manipulation.
Ge-Hao Zhang, Weikai Huang, S. Shailesh et al.· 0 citations
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.