62 citations · 120 across the 5 of their papers we have counts for
6 papers
On-Demand Attention: Language Models Know When to Recall
Haibo Feng, Ruiqi Liang, Hanyang Peng +2
Reasoning and agentic workloads increasingly demand efficient long-context inference. Yet full-attention decoding reads the growing history at every step, although the benefit of g…
RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases
Jinyu Yang, Cheng Yang, Junze Chen +4
Relational databases (RDBs) remain the cornerstone of modern data systems and support diverse predictive tasks. Recent relational deep learning (RDL) methods enable end-to-end pred…
IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference
Wanli Zhong, Haibo Feng, Zirui Zhou +2
Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multiplications, it expose…
A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization
Hanyang Peng, Shiqi Yu
Four-variable-independent-regression localization losses, such as Smooth- Loss, are used by default in modern detectors. Nevertheless, this kind of loss is oversimplified s…
Detect Faces Efficiently: A Survey and Evaluations
Yuantao Feng, Shiqi Yu, Hanyang Peng +2
Face detection is to search all the possible regions for faces in images and locate the faces if there are any. Many applications including face recognition, facial expression reco…
Direct l_(2,p)-Norm Learning for Feature Selection
Hanyang Peng, Yong Fan
In this paper, we propose a novel sparse learning based feature selection method that directly optimizes a large margin linear classification model sparsity with l_(2,p)-norm (0 <…