2 papers
cs.AI2026
ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation
Siyuan Ma, Yutian Zhang, Boshi Zhang +4
Manipulating moving objects requires a policy to anticipate contact events, yet vision-language-action (VLA) policies are commonly fine-tuned from the current observation alone. Wo…
cs.AI2026
Attributing Preprocessing Invariance in Spectral Foundation Models
Dongjun Wei, Hongyi Wu, Yinuo Zou
Preprocessing invariance is an appealing goal for spectral foundation models: a frozen model should remain useful when laboratories preprocess spectra differently. It is usually me…