World Labs acquires robotics simulator SceniX - 2026-07-21 - Article - The deal connects Marble’s generated 3D worlds with robot-data creation, policy training, evaluation and deployment.
The Humanoid Bottleneck Is Leaving the Cage - 2026-06-22 - Article - NVIDIA's Halos launch puts safety infrastructure around physical AI deployment. Agility's Digit is the first humanoid in the system, and the reason why matters more than the platform itself.
xperception -- Making Robotic Grasping Easier - 2026-07-14 - Research Publication - However, conventional vision systems remain a bottleneck, requiring extensive data collection and model retraining whenever a new object is introduced to the production line. DINOv2, GeDi), xperception achieves… - source: arxiv.org
FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand - 2026-05-25 - Research Publication - The authors present the first approach to build hierarchical task-driven 3D scene graphs of arbitrary indoor or outdoor environments using an uncalibrated monocular camera in real-time. In addition to achieving 79% higher… - source: arxiv.org
2.5-D Decomposition for LLM-Based Spatial Construction - 2026-05-08 - Research Publication - The authors present a neuro-symbolic pipeline based on 2.5-D decomposition: the LLM plans in the two-dimensional horizontal plane while a deterministic executor computes all vertical placements from column occupancy… - source: arxiv.org
Shallow-π: Knowledge Distillation for Flow-based VLAs - 2026-01-28 - Research Publication - The authors propose Shallow-pi, a principled knowledge distillation framework that aggressively reduces the transformer depth of both the VLM backbone and the flow-based action head, compressing the model from 18 to 6… - source: arxiv.org
VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction - 2026-01-27 - Research Publication - The authors present VGGT-SLAM 2.0, a real-time RGB feed-forward SLAM system which substantially improves upon VGGT-SLAM for incrementally aligning submaps created from VGGT. Finally, the authors conduct a suite of… - source: arxiv.org