Youngjune Lee

	Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval Jonghyun Song, Youngjune Lee, Gyu-Hwung Cho, Ilhyeon Song, Saehun Kim and Yohan Jo CIKM 2025 - Short Research Paper Track Joint training of sparse and dense text-image retriever
	IRA: Adaptive Interest-aware Representation and Alignment for Personalized Multi-interest Retrieval Youngjune Lee, Haeyu Jeong, Changgeon Lim, Jeong Choi, Hongjun Lim, Hangon Kim, Jiyoon Kwon, Saehun Kim SIGIR 2025 - Industry Track Personalization with text-based multiple user-vector retrieval
	RRADistill: Distilling LLMs' Passage Ranking Ability for Long-Tail Queries Document Re-Ranking on a Search Engine Nayoung Choi, Youngjune Lee, Gyu-Hwung Cho, Haeyu Jeong, Jungmin Kong, Saehun Kim, Keunchan Park, Sarah Cho, Inchang Jeong, Gyohee Nam, Sunghoon Han, Wonil Yang and Jaeho Choi EMNLP 2024 - Industry Track Reranking for long-tail queries
	MvFS: Multi-view Feature Selection for Recommender System Youngjune Lee, Yeongjong Jeong, Keunchan Park and SeongKu Kang CIKM 2023 - Short Research Paper Track Optimize key features from each data instance in Recommender System
	Learning to Embed Multi-Modal Contexts for Situated Conversational Agents Haeju Lee, Oh Joon Kwon, Yunseon Choi, Minho Park, Ran Han, Yoonhyung Kim, Jinhyeon Kim, Youngjune Lee, Haebin Shin, Kangwook Lee, and Kee-Eung Kim NAACL 2022 - Findings* Improving transformer's joint-training architecture for Multi-Modal Dialogue system using VR-based shopping dataset
	Tackling Situated Multi-Modal Task-Oriented Dialogs with a Single Transformer Model Haeju Lee, Oh Joon Kwon, Yunseon Choi, Jinhyeon Kim, Youngjune Lee, Ran Han, Yoonhyung Kim, Minho Park, Kangwook Lee, Haebin Shin and Kee-Eung Kim DSTC10 Workshop at AAAI 2022* MIulti-Modal Dialogue system
	Dual Correction Strategy for Ranking Distillation in Top-N Recommender System Youngjune Lee and Kee-Eung Kim CIKM 2021 - Short Research Paper Track Distillation focused on the parts that are particularly difficult to follow using discrepancy on both the user side and the item side of the teacher model and the student model
	Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI Youngjune Lee, Oh Joon Kwon, Haeju Lee, Joonyoung Kim, Kangwook Lee and Kee-Eung Kim Data Centric AI Workshop at NeurIPS 2021. Development of a data quality improvement pipeline, that utilizes augmentation and hard negative dataset extraction and modification, to improve image classification performance with only a small dataset