Jiwen Lu

Evaluator quality for robotic policies hinges more on long-horizon consistency than on short-term visual fidelity, reshaping our approach to world model design.

IBRSteG enables the undetectable embedding of secret 3D scenes with superior capacity and security, all while eliminating the need for scene-specific optimization.

ViQ achieves a groundbreaking balance between semantic richness and detail in visual representations, enabling efficient multimodal training without sacrificing quality.

PCDiff achieves unprecedented accuracy in detecting subtle 3D anomalies, outperforming traditional methods by effectively addressing reconstruction challenges in both foreground defects and background biases.

R2RDreamer achieves spatial generalization improvements in manipulation tasks by leveraging 3D-aware data augmentation without the pitfalls of complex scene setups or sim-to-real gaps.

Treating raw visual images as action representations revolutionizes embodied control, outperforming traditional methods in accuracy and generalization.