3 papers
cs.IR2026
LASER: An Efficient Target-Aware Segmented Attention Framework for End-to-End Long Sequence Modeling
Tianhe Lin, Ziwei Xiong, Baoyuan Ou +8
Modeling ultra-long user behavior sequences is pivotal for capturing evolving and lifelong interests in modern recommendation systems. However, deploying such models in real-time i…
cs.LG2025
HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
Haoran Li, Yingjie Qin, Baoyuan Ou +2
Vision-Language Models (VLMs) have made significant progress in multimodal tasks. However, their performance often deteriorates in long-context scenarios, particularly long videos.…
cs.AI2025
GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation
Wei Xu, Haoran Li, Baoyuan Ou +4
Cross-domain Click-Through Rate prediction aims to tackle the data sparsity and the cold start problems in online advertising systems by transferring knowledge from source domains…