9 papers
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
Xiaomi Robotics Team, Jun Guo, Piaopiao Jin +31
We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulatio…
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
Xinghang Li, Jun Guo, Qiwei Li +21
Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements f…
Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation
Yutong Zhang, Jiaxin Chen, Honglin Chen +5
Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient b…
Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA
Xin Lu, Rui Li, Xun Huang +6
Embodied Question Answering (EQA) has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. However, in dynamic, human-p…
From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence
Zixing Lei, Genjia Liu, Yuanshuo Zhang +11
The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this s…
MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
Xun Huang, Shijia Zhao, Yunxiang Wang +6
Embodied navigation is a fundamental capability for robotic agents operating. Real-world deployment requires open vocabulary generalization and low training overhead, motivating ze…
EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making
Zixing Lei, Sheng Yin, Yichen Xiong +8
Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of ge…
PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization
Zixing Lei, Zibo Zhou, Sheng Yin +7
Humanoid whole-body control (WBC) policies trained in simulation often suffer from the sim-to-real gap, which fundamentally arises from simulator inductive bias, the inherent assum…
Leveraging Predicate and Triplet Learning for Scene Graph Generation
Jiankai Li, Yunhong Wang, Xiefan Guo +2
Scene Graph Generation (SGG) aims to identify entities and predict the relationship triplets \textit{\textless subject, predicate, object\textgreater } in visual scenes. Given the…