COLOSSEUM

COLOSSEUM is a benchmark used to evaluate the performance of robotic manipulation tasks, specifically assessing the effectiveness of 3D-aware visual pretraining methods.

Papers using COLOSSEUM (7)

TGM-VLA: Task-Guided Mixup for Sampling-Efficient and Robust Robotic Manipulation2026Hyperbolic Multiview Pretraining for Robotic Manipulation2026Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation2026DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models2025RoboPearls: Editable Video Simulation for Robot Manipulation2025SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation2025