2 papers
cs.IR2026
Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training
Oseong Choi, Hoeinn Kim, Jihoon Lee +2
Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foundation model is often adapted…
cs.IR2026
LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation
Eugene Lee, Oseong Choi, Byungsoo Kang +1
Multi-armed bandit algorithms, especially Thompson sampling, are widely used in online recommendation. Despite their ability to adapt from online feedback, these methods often suff…