Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable dataset construction. Prior instruction generators assume discrete viewpoint graphs with panoramic observations, where trajectory structure is explicit; i...
Hao-Lin Yang, Yu-Xing Long, Zi-Han Yang et al.· 0 citations
Contextualization, the core operation of language modeling, transmits information across words to build sentence-specific word representations. Prior works mainly study contextualization, focusing on individual words and attention heads as a growing discrete dictionary, lacking a global view of their general behavior....
Hakaze Cho, Hao-Lin Yang, Zhun Sun et al.· 0 citations
NeSyS alternates training between the two models using trajectories inadequately explained by the other, and prioritizes transitions that are weakly covered by symbolic rules, using 35--60% of the training pairs while outperforming full-data supervised fine-tuning in five of six settings.
Hongyu Zhao, Siyuan Zhou, Hao-Lin Yang et al.· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.