Ego-to-World (E-2W) benchmark

The Ego-to-World (E2W) benchmark evaluates a vision-language model's ability to fuse heterogeneous viewpoints across three tasks: global counting, relational location reasoning, and action-oriented grasping.

Papers using Ego-to-World (E-2W) benchmark (2)

Ego To World: Collaborative Spatial Reasoning In Embodied Systems Via Reinforcement Learning2026Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning2026