Embodied AI

Embodied-Reasoner: Integrates visual search, reasoning, and action for interactive tasks, outperforming existing models in embodied environments.

AlphaSpace enables robotic actions via semantic tokenization and symbolic reasoning, enhancing spatial intelligence in LLMs.

Cosmos-Reason1: Physical AI models that reason and act in the real world, bridging the gap between perception and embodied decision-making.

FreeGrasp: enabling robots to grasp by interpreting instructions and reasoning about object spatial relationships.

Being-0: A humanoid robot agent achieves complex tasks by integrating a vision-language model with modular skills, enhancing efficiency and real-time performance.

D2PO: World modeling enhances embodied task planning by jointly optimizing state prediction and action selection, leading to more efficient execution.

UniGoal: A novel framework for universal zero-shot goal-oriented navigation, outperforming task-specific methods with a unified approach.

CLEA: Enhancing task execution in dynamic environments with a closed-loop embodied agent.

PC-Agent: A new hierarchical framework that significantly improves complex task automation on PCs by 32%!

Magma: a new foundation model for multimodal AI agents excels at bridging verbal and spatial intelligence, achieving state-of-the-art performance across various tasks, including UI navigation and robo…

GenEx generates explorable 3D worlds from a single image, enabling embodied AI agents to explore and learn.