Ran Zheng

A lightweight latent world model directly conditions VLA action generation on predicted future consequences, boosting real-world robotic success rates from 38.3% to 73.3% without pixel-level video prediction.

Shifting the focus from marginal probabilities to joint trajectory probabilities, dVLA-RL achieves unprecedented success rates in robotic manipulation tasks.

AHA-WAM achieves a remarkable 92.80% success rate on RoboTwin while executing actions at 24.17 Hz, all without the need for prior robot-data training.

Forget purely data-driven voltage control – this LLM-RL collaboration uses grid knowledge to slash training time and boost performance in active distribution networks.