4 papers
PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
Lin Huang, Yujuan Tan, Weisheng Li +4
We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Response (PTFR) as a QoE objective and minimizes it under quality/…
Climber-Pilot: A Non-Myopic Generative Recommendation Model Towards Better Instruction-Following
Da Guo, Shijia Wang, Qiang Xiao +7
Generative retrieval has emerged as a promising paradigm in recommender systems, offering superior sequence modeling capabilities over traditional dual-tower architectures. However…
YOLO-DS: Fine-Grained Feature Decoupling via Dual-Statistic Synergy Operator for Object Detection
Lin Huang, Yujuan Tan, Weisheng Li +6
One-stage object detection, particularly the YOLO series, strikes a favorable balance between accuracy and efficiency. However, existing YOLO detectors lack explicit modeling of he…
YOLO-PRO: Enhancing Instance-Specific Object Detection with Full-Channel Global Self-Attention
Lin Huang, Yujuan Tan, Weisheng Li +5
This paper addresses the inherent limitations of conventional bottleneck structures (diminished instance discriminability due to overemphasis on batch statistics) and decoupled hea…