Jie-Zhang Cao

Training an agent to learn from an oracle's future actions, not just its initial decision, unlocks significantly deeper and more robust long-horizon reinforcement learning.

Achieving state-of-the-art performance in real-world image super-resolution while maintaining a rapid single-step processing time and minimal computational overhead.

Current video generation models fail to maintain embodiment consistency and functional interaction in human-to-robot manipulation, revealing significant gaps in their transfer capabilities.

Current vision-language models struggle with process understanding in robotic manipulation, but targeted post-training can yield significant improvements.

LLMs maintain a positive attitude even when losing in adversarial board games, yet their gameplay reveals surprising instability in skill execution.