6 papers · 1 filter
HITCH: Teaching a Vision-Language Model to Operate a Humanoid through a Whole-Body Harness
Qingzhou Lu, Chenxin Liu, Xinming Wang +4
Enabling vision-language models (VLMs) to control humanoid robots requires both reliable whole-body interfaces and knowledge of how to use the body that carries over across tasks.…
HiLo-WAM: Decoupling Long-Horizon Task Evolution and Local Dynamics in World Action Models
Xingyu Wang, Yanjiang Guo, Zhijing Ding +7
World Action Models (WAMs) improve robotic manipulation by jointly modeling visual dynamics and robot actions. However, most existing WAMs model dense short-horizon visual dynamics…
BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries
Jiaxin Fang, Ruitong Liu, Zeyu Lai +6
World Action Models (WAMs) commonly couple video and action experts through dense, layer-wise Mixture-of-Transformers (MoT) attention, exposing action prediction to irrelevant visu…
Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions
Liu Cao, Xingze Wu, Jingzhi Cui +4
Learning humanoid-object interaction requires coordinating whole-body balance, locomotion, and dexterous hand contact to control both robot and object motion. Human demonstrations…
R2S-Eval: Robot Evaluation with Real-to-Sim Calibration via Vision-Language Models
Yidi Wang, Feixiang Ruan, Ruoqu Chen +4
Evaluating robot manipulation policies is becoming increasingly important as generalist models, particularly vision-language-action (VLA) models, are deployed on physical robots. H…
Operational digital twin clinics enable task-based evaluation of embodied AI
Xinyuan Wu, Jingrao Zhang, Mengdi Xu +3
Embodied artificial intelligence (AI) must be tested in the clinical environments where it will operate, but building realistic, robot-testable settings is costly and difficult to…