Researchers have introduced KuaiLive-M3, a new dataset designed to improve live streaming recommendation systems. This dataset, collected from Kuaishou, a major platform in China, addresses limitations in existing benchmarks by including temporally evolving multimodal content, cross-domain user interactions between live streams and short videos, and explicit user feedback. KuaiLive-M3 encompasses data from over 21,000 users, featuring millions of interactions and detailed content embeddings, aiming to facilitate more realistic research in live streaming recommendation. AI
IMPACT This dataset could lead to more sophisticated and personalized live streaming recommendation systems by enabling research into temporally evolving content and cross-domain user preferences.
RANK_REASON The cluster contains an academic paper introducing a new dataset for a specific AI task. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
