CAST improves sequential recommendation by modeling fine-grained semantic transitions and using LLM priors to capture true item complementarity, reporting up to 17.6% Recall and 16.0% NDCG gains over prior methods.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SG-URInit builds semantically enriched initial user representations for multimodal recommenders by fusing local item modality features with global cluster semantics, closing the gap with item representations without extra training.
citing papers explorer
-
CAST: Modeling Semantic-Level Transitions for Complementary-Aware Sequential Recommendation
CAST improves sequential recommendation by modeling fine-grained semantic transitions and using LLM priors to capture true item complementarity, reporting up to 17.6% Recall and 16.0% NDCG gains over prior methods.
-
Well Begun is Half Done: Training-Free and Model-Agnostic Semantically Guaranteed User Representation Initialization for Multimodal Recommendation
SG-URInit builds semantically enriched initial user representations for multimodal recommenders by fusing local item modality features with global cluster semantics, closing the gap with item representations without extra training.