VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
Objaverse: A universe of annotated 3d objects
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
dataset 1
citation-polarity summary
representative citing papers
CADBench is a multimodal benchmark for CAD program generation that shows specialized mesh-to-CAD models outperform general vision-language models but degrade with complexity and modality shifts.
DVD treats voxel occupancy as a discrete variable in a diffusion framework to generate, assess, and edit sparse 3D voxels without continuous thresholding.
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.
DA3 recovers consistent visual geometry from arbitrary views via a vanilla DINO transformer and depth-ray target, setting new SOTA on a visual geometry benchmark while outperforming DA2 on monocular depth.
citing papers explorer
-
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
-
CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation
CADBench is a multimodal benchmark for CAD program generation that shows specialized mesh-to-CAD models outperform general vision-language models but degrade with complexity and modality shifts.
-
DVD: Discrete Voxel Diffusion for 3D Generation and Editing
DVD treats voxel occupancy as a discrete variable in a diffusion framework to generate, assess, and edit sparse 3D voxels without continuous thresholding.
-
Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.
-
Depth Anything 3: Recovering the Visual Space from Any Views
DA3 recovers consistent visual geometry from arbitrary views via a vanilla DINO transformer and depth-ray target, setting new SOTA on a visual geometry benchmark while outperforming DA2 on monocular depth.