Embodied vision-language models must answer questions from partial, evolving observations. Their success depends on both the reasoning capability selected and the evidence available to it. Expert routers adapt internal computation, while tool-augmented systems acquire external evidence; choosing these independently can...
Wei-Lin Ruan, Ying-Jie Xu, Yang Wei et al.· 0 citations
Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-relevant forms. Yet joint training can conflate the knowledge needed at different stages because supervision is fragmented across incompatible geometric...
Wei-Lin Ruan, Bo-Han Zhou, Jing-Hao Li et al.· 0 citations
Generating high-quality UV textures for 3D meshes remains challenging. Multi-view projection pipelines suffer from occlusion and view inconsistency, and recent methods that generate textures directly in UV space still rely on auxiliary modules to supply 3D information, leaving the attention mechanism tied to UV-grid po...
Jian-Tao Lin, Ying-Jie Xu, Ming Sheng et al.· 0 citations
A robot generalist must interpret a scene, act on it, and satisfy every condition of a task. How far do frontier vision-language models (VLMs) meet these demands? We introduce Embodied Agent Arena, evaluating ten VLM agents across Geometry, Spatial Reasoning, Affordance, Task Planning, and Manipulation. Its 1,000 cases...
Hao-Jian Huang, Pu-Kun Zhao, Ze-Xi Li et al.· 1 citation
A literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution.
Robo-Harness K1 is introduced, a robot-use agent (RUA) framework that exposes perception as tools that makes 3D geometry accessible without changing the VLM architecture or training a depth encoder, and suggests that perception-augmented RUAs offer a promising route to sample-efficient, generalizable robotic policies t...
Ze-Xi Li, Ye-Hang Zhang, Wen-Qian Li et al.· 6 citations· ⚡2
World Action Agent is presented, a multi-agent harness through which VLMs pilot robots with basic tools, making every decision within a visual action workspace, outperforming end-to-end VLAs, code-as-policy agents, and a visual-harness baseline with the same backbone.
Ye-Hang Zhang, Hao-Jian Huang, Yi-Fan Chang et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.