Chi-Min Chan

Experimental results demonstrate the proposed $\mathcal{M}^2$Tok-based VLA achieves superior reconstruction fidelity but also significantly boosts the success rate of VLA models, and comprehensive ablation studies further confirm the effectiveness of the multi-head and multi-codebook mechanisms.

Augmenting images from a model's own failures can lead to substantial performance boosts in multimodal tasks, outperforming conventional augmentation techniques.

Expressiveness preservation in speech-to-speech translation remains a significant hurdle, with systems scoring poorly on emotional and nonverbal fidelity despite achieving high translation accuracy.

Speech QA performance peaks at 4.17 Hz, challenging the assumption that higher frame rates always yield better reasoning outcomes.