Weirui Ye
YOU?
Author Swipe
View article: Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance
Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance Open
Defining reward functions for skill learning has been a long-standing challenge in robotics. Recently, vision-language models (VLMs) have shown promise in defining reward signals for teaching robots manipulation skills. However, existing w…
View article: Simultaneous Learning of Pivots and Representations for Cross-Domain Sentiment Classification
Simultaneous Learning of Pivots and Representations for Cross-Domain Sentiment Classification Open
Cross-domain sentiment classification aims to leverage useful knowledge from a source domain to mitigate the supervision sparsity in a target domain. A series of approaches depend on the pivot features that behave similarly for polarity pr…
View article: Transferable Attention for Domain Adaptation
Transferable Attention for Domain Adaptation Open
Recent work in domain adaptation bridges different domains by adversarially learning a domain-invariant representation that cannot be distinguished by a domain discriminator. Existing methods of adversarial domain adaptation mainly align t…