3 papers
cs.CL2025
Mem-α: Learning Memory Construction via Reinforcement Learning
Yu Wang, Ryuichi Takanobu, Zhiqi Liang +4
Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmente…
cs.AI2025
LaViC: Adapting Large Vision-Language Models to Visually-Aware Conversational Recommendation
Hyunsik Jeon, Satoshi Koide, Yu Wang +2
Conversational recommender systems engage users in dialogues to refine their needs and provide more personalized suggestions. Although textual information suffices for many domains…
cs.IR2024
A Fashion Item Recommendation Model in Hyperbolic Space
Ryotaro Shimizu, Yu Wang, Masanari Kimura +4
In this work, we propose a fashion item recommendation model that incorporates hyperbolic geometry into user and item representations. Using hyperbolic space, our model aims to cap…