Hyun-Soo Kang
2 papers · Latest:
Information Retrieval
HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval
HIVE is an LLM framework that injects explicit visual-text reasoning into multimodal retrieval, achieving SOTA on reasoning-intensive queries.
2604.07220
Information RetrievalBRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment
BRIDGE improves multimodal-to-text retrieval by using a reinforcement-learned query aligner (FORGE) and a reasoning-enhanced retriever (LENS).
2604.07201
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.