Jingjing Chen

Experiments demonstrate that MoWAM achieves strong in-distribution performance, improved out-of-distribution robustness, and higher average real-world success than representative WAM baselines, demonstrating that explicit future motion provides an effective and efficient basis for inference-time scaling.

Results show that robust visuomotor learning benefits from structuring, rather than removing, visual embodiment information, and embodiment canonicalization in 3D point clouds substantially improves human-to-robot policy transfer without robot demonstrations.

Achieving seamless identity replacement in videos, Vorch-IR can handle multiple subjects and backgrounds without requiring precise pose matching.

Even with stable feature representations, AI detectors can still fail due to drifting decision boundaries, leading to a new failure mode called Dual Degradation.