GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation
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 ac
Record details
Published: 7 June 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
arXiv · 7 June 2026
Instrumental convergence and power-seeking
arXiv · 7 June 2026
Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Artificial Hivemind in Autonomous Agents
arXiv · 8 June 2026
Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions
arXiv · 6 June 2026
IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment
arXiv · 6 June 2026
Accounting for Context: Shaping Moral Credences for Value Alignment
arXiv · 5 June 2026
How to cite this record
ethics.ai (7 June 2026), “GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation,” evidence record 1299, https://ethics.ai/record/1299 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.