Author

Lei Lei

h-index 1 View on Semantic Scholar

We have 1 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking

The Modality Masking Mechanism (M3), an embarrassingly simple, training-only strategy that requires no architectural changes or large-scale robot pretraining, is introduced to improve robustness of query-based VLA policies for bimanual manipulation.

Dong-Zhou Cheng, Ziang Li, Yixiao Zhou et al. · 0 citations