Records found: 3
RoboBrain 2.0 from BAAI integrates vision and language understanding to advance embodied AI in robotics, offering scalable models and superior reasoning for complex tasks.
Mirage introduces a new method for vision-language models to integrate visual reasoning without generating images, significantly enhancing their ability to solve spatial and multimodal tasks.
Meta AI presents Multi-SpatialMLLM, a new model improving multi-frame spatial understanding in multi-modal large language models, supported by the extensive MultiSPA dataset and benchmark.