E3VS-Bench supplies 99 3D Gaussian Splatting scenes and 2,014 episodes to test whether embodied agents can use unrestricted 5-DoF viewpoint control to answer questions that depend on fine-grained visual details visible only from specific angles.
arXiv preprint arXiv:2511.20351 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
Imagining in 360° decouples visual search into a single-step probabilistic semantic layout predictor and an actor, removing the need for multi-turn CoT reasoning and trajectory annotations while improving efficiency in 360° environments.
citing papers explorer
-
E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
E3VS-Bench supplies 99 3D Gaussian Splatting scenes and 2,014 episodes to test whether embodied agents can use unrestricted 5-DoF viewpoint control to answer questions that depend on fine-grained visual details visible only from specific angles.
-
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
-
Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search
Imagining in 360° decouples visual search into a single-step probabilistic semantic layout predictor and an actor, removing the need for multi-turn CoT reasoning and trajectory annotations while improving efficiency in 360° environments.
- ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop