Xiang-Yu Li

TADreamer is presented, a zero-shot framework that grounds video-imagined navigation in measured geometry without task-specific training or fine-tuning, and reduces mean absolute depth error and mean absolute relative depth error compared with NavDreamer.

Monolithic federated updates are a fundamental bottleneck for embodied AI: decoupling vision, language, and action streams cuts uplink payloads by 96% and beats standard FedAvg by 22 percentage points under real-world wireless interference.

Swapping network traffic features in the frequency domain preserves critical structural signatures while generating diverse, out-of-distribution variations that standard time-domain augmentations fail to synthesize.

Robots can now autonomously evolve their manipulation skills in real-time, leveraging past interactions without needing to update their underlying policy models.

Prior maps, even when flawed, can significantly boost UAV exploration efficiency, achieving over 34% better performance in complex environments.