collaborators

5 papers

cs.IR2026

KuaiLive-M3: A Multi-Modal, Multi-Domain, and Multi-Feedback Dataset for Live Streaming Recommendation

Ke Guo, Changle Qu, Jiayaqi Cheng +7

Existing public live streaming datasets suffer from three major limitations: they provide limited access to temporally evolving multimodal live content, overlook users' cross-domai…

cs.IR2026

KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation

Changle Qu, Sunhao Dai, Ke Guo +7

Live streaming platforms have become a dominant form of online content consumption, offering dynamically evolving content, real-time interactions, and highly engaging user experien…

cs.LG2025

Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity

Zhiyuan Su, Sunhao Dai, Xiao Zhang

Clustering of Bandits (CB) methods enhance sequential decision-making by grouping bandits into clusters based on similarity and incorporating cluster-level contextual information,…

cs.CL2025

Length-Induced Embedding Collapse in PLM-based Models

Yuqi Zhou, Sunhao Dai, Zhanshuo Cao +2

Text embeddings from PLM-based models enable a wide range of applications, yet their performance often degrades on longer texts. In this paper, we introduce a phenomenon we call Le…

cs.CL2025

Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents

Haoyu Wang, Sunhao Dai, Haiyuan Zhao +6

Previous studies have found that PLM-based retrieval models exhibit a preference for LLM-generated content, assigning higher relevance scores to these documents even when their sem…