Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inherently prioritizes visual fidelity and creativity over computational efficiency and physical realism. In this work, we present LingBot-Video, a DiT-based video pretraining paradigm specifically tailored for embodied intelligence. From the architecture perspective, we adopt the Mixture-of-Experts (MoE), instead of dense, framework to achieve a better trade-off between modeling capacity and inference efficiency, and manage to scale it up from scratch. From the data perspective, we construct a data profiling engine that augments standard internet videos with extensive robot-oriented footage, encompassing manipulation, navigation, and egocentric perspectives, to equip the base model with an intrinsic understanding of actions and world dynamics. From the training perspective, we develop a multi-dimensional reward system to enforce the alignment regarding physical rationality and task completion, going beyond standard criteria such as aesthetics, prompt-following, and motion consistency. Comprehensive evaluations validate its performance and efficiency as a video foundation model. We contribute LingBot-Video as the inaugural large-scale, open-source MoE video foundation model to the community, in a pioneering effort to bridge digital creativity and physical actuation.
Embodied Image Quality Assessment for Robotic Intelligence
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University（图像通信与网络工程研究所，上海交通大学）；College of Information Science and Technology, Beijing University of Chemical Technology（信息科学与技术学院，北京化工大学）；USC-SJTU Institute of Cultural and Creative Industry, Shanghai Jiao Tong University（USC-SJTU文化产业与创意产业研究所，上海交通大学）
AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration
Beijing University of Posts and Telecommunications（北京邮电大学）；QiYuanLab（启元实验室）；Tsinghua University（清华大学）；University of Electronic Science and Technology of China（电子科技大学）
Meta AI Research（Meta人工智能研究院）；Georgia Institute of Technology（佐治亚理工学院）
How should we learn visual representations for embodied agents that must see and move? The status quo is tabula rasa in vivo, i.e. learning visual representations from scratch while also learning to move, potentially augmented with auxiliary tasks (e.g. predicting the action taken between two successive observations). In this paper, we show that an alternative 2-stage strategy is far more effective: (1) offline pretraining of visual representations with self-supervised learning (SSL) using large-scale pre-rendered images of indoor environments (Omnidata), and (2) online finetuning of visuomoto…
Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing（计算机科学与技术系，北京信息科学与技术国家研究中心，清华大学，北京）
MIT（麻省理工学院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in photographic datasets. Yet to build truly intelligent agents, we must construct representation learning algorithms that can learn not only from datasets but also learn from environments. An agent in a natural environment will not typically be fed curated data. Instead, it must explore its environment to acquire the data it will learn from. We propose a framework,…
EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
Beijing Innovation Center of Humanoid Robotics（北京人形机器人创新中心）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong University of Science and Technology（香港科技大学）；University of Technology Sydney（悉尼科技大学）
XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
Tsinghua University（清华大学）；Automotive and Robotics, Xiaomi Corporation（小鹏汽车与机器人部，小鹏科技）；National University of Singapore（新加坡国立大学）；McGill University（麦吉尔大学）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室）；Peng Cheng Laboratory（鹏城实验室）；Institute of Digital Media, Peking University（北京大学数字媒体研究院）
