北京通用人工智能研究院BIGAI

论文索引

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

PrimHOI: Compositional Human-Object Interaction via Reusable Primitives

Learning Unified Force and Position Control for Legged Loco-Manipulation

CLONE: Holistic Closed-Loop Whole-Body Teleoperation for Long-Horizon Humanoid Control

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

Probing and Inducing Combinational Creativity in Vision-Language Models