DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning Paper • 2508.05405 • Published Aug 7, 2025 • 64
DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware Planning Paper • 2506.16012 • Published Jun 19, 2025 • 22
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics Paper • 2506.04308 • Published Jun 4, 2025 • 43