Main Personal Website: bonwoo-koo9.github.io
Date
Key Points
Enhanced the framework to seamlessly incorporate multi-modal data like item images. Instead of a single item encoder trained by matching loss with item text description encoder, I have implemented cross attention mechanism and contrastive learning to effectively integrate the multi-modality between item embeddings and meta data embeddings.
Multi-A-LLMRec Progress Report
Key Notes to conduct research on Multi-modal LLMRec
Investigated LLM-based Recommender Systems, encompassing both Vision Language Model and Multi-Modal LLMRec
Explored advancements in Large Language Models, including Computer Vision, Vision Language Model, and Secure Large Language Model alleviating hallucination
Attention is All You Need Paper Review
Explored advancements in Recommender Systems from Collaborative Filtering to Side Information-based Filtering
Explored advancements in Graph based Recommender Systems and Knowledge Graphs
Based on these paper reviews, I wrote a survey paper on Recommender Systems spanning from collaborative filtering to LLM-based RecSys.