Optimus Gen
Optimus Gen refers to a family of advanced AI models and systems, primarily focused on developing and optimizing humanoid robots and large multimodal language models (MLLMs). Current research emphasizes improving the efficiency of MLLM training through techniques like bubble exploitation and communication compression, as well as enhancing the capabilities of humanoid robots for complex tasks via hybrid multimodal memory modules and knowledge-guided planning. This work is significant for accelerating the development of both powerful AI agents and practical robotic applications across diverse fields, from manufacturing to consumer electronics.
Papers
Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
Zhihao He, Hang Yu, Zi Gong, Shizhan Liu, Jianguo Li, Weiyao Lin
OPTIMA: Optimized Policy for Intelligent Multi-Agent Systems Enables Coordination-Aware Autonomous Vehicles
Rui Du, Kai Zhao, Jinlong Hou, Qiang Zhang, Peter Zhang
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
Zaijing Li, Yuquan Xie, Rui Shao, Gongwei Chen, Dongmei Jiang, Liqiang Nie
Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation
Weiqi Feng, Yangrui Chen, Shaoyu Wang, Yanghua Peng, Haibin Lin, Minlan Yu