Search Results for author:
Found 3 papers, 2 papers with code
AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability
In the pre-training stage, instead of treating all image-text pairs equally, we assign different levels of alignment capabilities to different image-text pairs.
Knowledge-aware Dual-side Attribute-enhanced Recommendation
Specifically, we build \textit{user preference representations} and \textit{attribute fusion representations} upon the attribute information in knowledge graphs, which are utilized to enhance \textit{collaborative filtering} (CF) based user and item representations, respectively.
Dynamic Demonstrations Controller for In-Context Learning
Previous studies have revealed that ICL is sensitive to the selection and the ordering of demonstrations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
