Jul 2026
CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation
This work proposes the method, a model-agnostic framework for long-horizon recommendation, which uses a frozen multimodal language model to convert item content and feedback into evidence-grounded semantic atoms, then maintains separate short-term, long-term, and exposure memories.
Gengyu Zhan
· arXiv.org · 0 citations