Embodied-Reasoner Outperforms OpenAI o1 in Embodied AI Tasks
A joint team from Zhejiang University, Chinese Academy of Sciences, and Alibaba Damo Academy has open-sourced Embodied-Reasoner, a multimodal embodied reasoning model. This model achieved an 80.96% task success rate in the AI2-THOR simulator, surpassing OpenAI o1 (71.73%), o3-mini (56.55%), and Claude-3.7 (67.70%). Its superior performance is attributed to an innovative three-stage training pipeline involving imitation learning, self-exploration, and self-correction.
Embodied-Reasoner's open-source release and demonstrated superior performance offer a significant advancement in embodied AI, enabling more robust and capable agents for interactive physical tasks, including real-world object search.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free