9 papers
-EVA: Envision, Verify, and Act with Latent Interactive World Models
Zhenguo Sun, Yu Sun, Hande Huang +1
Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit. World models provide predictive supervision, representatio…
GUIDE: Goal-Initialized Directional Understanding for End-to-End Legged Navigation
Liang Wang, Jin Jin, KanZhong Yao +6
End-to-end reinforcement learning (RL) has shown strong potential for legged robot navigation, yet existing approaches commonly rely on continuously updated robot-to-goal states fr…
ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
Yanghao Zhou, Jingyu Ma, Yibo Peng +3
Humanoid control systems have made significant progress in recent years, yet modeling fluent interaction-rich behavior between a robot, its surrounding environment, and task-releva…
MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation
Zhenguo Sun, Bo-Sheng Huang, Yibo Peng +9
Generalist humanoid motion trackers have recently achieved strong simulation metrics by scaling data and training, yet often remain brittle on hardware during sustained teleoperati…
DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter
Xukun Li, Yu Sun, Lei Zhang +10
Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we…
Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control
Zhe Li, Cheng Chi, Yangyang Wei +9
Humans intuitively move to sound, but current humanoid robots lack expressive improvisational capabilities, confined to predefined motions or sparse commands. Generating motion fro…
Robotic Ultra-Long-Horizon Manipulation Skills via Human-guided Lifelong Code Generation
Yuan Meng, Zhenguo Sun, Max Fest +4
Large language models (LLMs) can translate natural-language instructions for robotic manipulation into executable code, but ambiguity, noisy generations, and limited context window…
RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking
Zhenguo Sun, Yibo Peng, Yuan Meng +5
Long-horizon, high-dynamic motion tracking on humanoids remains brittle: retargeted reference motions are typically kinematically plausible but dynamically inconsistent with the ro…
Robotic Long-Horizon Manipulation with Progressive In-Context Code Generation and Episodic Feedback
Yuan Meng, Xiangtong Yao, Haihui Ye +6
Robotic long-horizon manipulation requires robots to compose perception, reasoning, and action over extended task sequences, yet existing language-conditioned frameworks often rely…