Ruiming Tang
3 papers · Latest:
Artificial Intelligence
Action-Aware Generative Sequence Modeling for Short Video Recommendation
A2Gen improves short video recommendations by modeling user actions as temporal sequences, leading to significant engagement boosts.
2604.25834
Natural Language ProcessingKwai Summary Attention Technical Report
Kwai Summary Attention (KSA) reduces LLM long-context modeling costs by compressing historical contexts into learnable summary tokens.
2604.24432
Information RetrievalModular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
MARC compresses LLM representations for recommendation systems by addressing mid-layer advantage, improving efficiency and effectiveness.
2604.18146
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.