aiqbench analysis
GEAR-VLA addresses critical deployment limitations in Vision-Language-Action models by introducing a unified, geometry-aware action representation that decouples high-level semantics from low-level trajectory supervision. The framework achieves state-of-the-art generalization across unseen objects and diverse robot embodiments through a coarse-to-fine learning strategy and embodiment canonicalization. This approach offers a robust pathway for scaling robotic manipulation systems beyond current benchmarks into real-world environments with varying physical configurations.
GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation
arXiv:2606.08530v1 Announce Type: new 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. We argue that this stems from the lack of a unified geometry-aware manipulation representation, leaving existing VLAs vulnerable to low-level trajectory supervision, misaligned 3D features, and embodiment differences. To address this, we propose GEAR-VLA, a VLA framework for learning unified geometry-aware action representations for generalizable robotic manipulation. GEAR-VLA adopts coarse-to-fine action learning, where multi-source embodied pretraining equips the VLM with embodied reasoning and discrete action understanding before latent action tokens connect action semantics to a gradient-decoupled DiT continuous action expert. It further performs semantic-aligned 3D integration by aligning a trainable 3D spatial backbone with the VLA representation while freezing the original VLM-aligned visual pathway. To share this representation across robots, GEAR-VLA uses embodiment canonicalization, where embodiment-aware states and embodiment-invariant actions confine robot differences to the low-level interface. Extensive simulation and real-world experiments demonstrate strong generalization: GEAR-VLA achieves state-of-the-art performance on LIBERO, zero-shot LIBERO-Plus, and RoboTwin 2.0, reaches 85.9% success on AgileX and 81.0% on the pretraining-unseen LDT-01 embodiment, and obtains 90.1% success on a 6,360-trial universal grasping benchmark with 212 unseen objects. Code and models will be released at https://github.com/babynabeauty/GEAR-VLA.
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. We argue that this stems from the lack of a unified geometry-aware manipulation representation, leaving existing VLAs vulnerable to low-level trajectory supervision, misaligned 3D features, and embodiment differences. To address this, we propose GEAR-VLA, a VLA framework for learning unified geometry-aware action representations for generalizable robotic manipulation. GEAR-VLA adopts coarse-to-fine action learning, where multi-source embodied pretraining equips the VLM with embodied reasoning and discrete action understanding before latent action tokens connect action semantics to a gradient-decoupled DiT continuous action expert. It further performs semantic-aligned 3D integration by aligning a trainable 3D spatial backbone with the VLA representation while freezing the original VLM-aligned visual pathway. To share this representation across robots, GEAR-VLA uses embodiment canonicalization, where embodiment-aware states and embodiment-invariant actions confine robot differences to the low-level interface. Extensive simulation and real-world experiments demonstrate strong generalization: GEAR-VLA achieves state-of-the-art performance on LIBERO, zero-shot LIBERO-Plus, and RoboTwin 2.0, reaches 85.9% success on AgileX and 81.0% on the pretraining-unseen LDT-01 embodiment, and obtains 90.1% success on a 6,360-trial universal grasping benchmark with 212 unseen objects. Code and models will be released at this https URL.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2606.08530 [cs.RO]
(or arXiv:2606.08530v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.08530 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 224 words
Related coverage
GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation
arXiv · Jun 11, 2026
GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments
arXiv · Sep 21, 2026
Beyond Relative Geometry: Metric-Aware Geometry Perception for Robotics
arXiv · Aug 31, 2026
SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space
arXiv · Aug 4, 2026