8 papers
T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
Chenyuan Zhou, Yining Hong, Huang Huang +9
Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitl…
SeeSE3: Emergence of 3D Space in Vision Features
Caroline Chen, Sayna Ebrahimi, Fedor Kitashov +4
In this paper, we ask whether vision foundation models construct representations that reflect the intrinsic properties of 3D Euclidean space. Unlike previous works that probe 3D aw…
Planning with the Views
Kangrui Wang, Linjie Li, Zhengyuan Yang +7
Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transf…
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
Theo Uscidda, Marta Tintore Gazulla, Maks Ovsjanikov +2
Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a kno…
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
Yining Hong, Jiageng Liu, Han Yin +5
Spatial intelligence unfolds through a perception-action loop: agents act to acquire observations, and reason about how observations vary as a function of action. Rather than passi…
SceneTeract: Probing and Improving Agent-Aware Activity Reasoning in 3D Indoor Scenes
Léopold Maillard, Francis Engelmann, Tom Durand +5
Indoor 3D scenes are ultimately meant to be used: an embodied agent should be able to navigate, reach objects, and complete diverse activities. Yet whether a given scene actually s…
HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild
Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno +2
Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively h…
Dynamic Reflections: Probing Video Representations with Text Alignment
Tyler Zhu, Tengda Han, Leonidas Guibas +2
The alignment of representations from different modalities has recently been shown to provide insights on the structural similarities and downstream capabilities of different encod…