2 papers
cs.CV2026
Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
Weilin Ruan, Bohan Zhou, Jinghao Li +12
Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-relevant form…
cs.RO2026
Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena
Haojian Huang, Pukun Zhao, Zexi Li +7
Frontier vision-language models (VLMs) increasingly estimate scenes, ground interactions, and generate executable actions. How far these native capabilities support embodied genera…