3 papers
cs.IR2026
LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation
Yu Xia, Zihan Lin, Wei Yang +4
Large Language Models (LLMs) have shown great promise in recommendation due to superior reasoning abilities. However, existing methods mainly rely on explicit Chain-of-Thought (CoT…
cs.AI2026
Action-Aware Generative Sequence Modeling for Short Video Recommendation
Wenhao Li, Zihan Lin, Zhengxiao Guo +7
The paper proposes a new recommendation model, A2Gen, that treats user actions on short videos as temporal sequences and uses attention and hierarchical encoding to predict future…
cs.IR2026
TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
Wei Yang, Rui Zhong, Zihan Lin +4
Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user interests evolve over time and exh…