Zongwei Wang
4 papers · Latest:
Information Retrieval
Disagreement as Signals: Dual-view Calibration for Sequential Recommendation Denoising
DC4SR denoises sequential recommendations by calibrating semantic priors from LLMs with model learning dynamics to handle evolving user interests.
2604.24048
Information RetrievalPrompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems
This paper introduces PUDA, a novel black-box attack framework that promotes items in LLM-based sequential recommenders without knowing the model or prompt.
2604.23640
Natural Language ProcessingAFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce
AFMRL uses MLLMs to extract attributes for fine-grained multimodal representation learning, achieving SOTA in e-commerce retrieval.
2604.20135
Information RetrievalMulti-LLM Token Filtering and Routing for Sequential Recommendation
MLTFR improves sequential recommendation by filtering and routing token embeddings from multiple LLMs without external textual input.
2604.18200
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.