2 papers
cs.RO2025
LAOF: Robust Latent Action Learning with Optical Flow Constraints
Xizhou Bu, Jiexi Lyu, Fulei Sun +3
Learning latent actions from large-scale videos is crucial for the pre-training of scalable embodied foundation models, yet existing methods often struggle with action-irrelevant d…
cs.CL2018
The USTC-NEL Speech Translation system at IWSLT 2018
Dan Liu, Junhua Liu, Wu Guo +5
This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech…