Xingyang He

According to our database, Xingyang He authored at least 6 papers between 2014 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

2-D Transformer: Extending Large Language Models to Long-Context With Few Memory.

Xingyang He, Jie Liu, Yutai Duan

IEEE Trans. Neural Networks Learn. Syst., August, 2025

UGD-IML: A Unified Generative Diffusion-based Framework for Constrained and Unconstrained Image Manipulation Localization.

Yachun Mi, Xingyang He, Shixin Sun, Yu Li, Yanting Li, Zhixuan Li, Jian Jin, Chen Hui, Shaohui Liu

CoRR, August, 2025

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control.

Xingyang He, Xiao Ling, Jie Liu

CoRR, July, 2025

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

Xingyang He, Jie Liu, Shaowei Chen

CoRR, January, 2025

Learning global dependencies via parallelized graph transformer with hybrid attention.

Yutai Duan, Jie Liu, Xingyang He, Yi Lv

Knowl. Based Syst., 2025

2014

A Clustering-Based Privacy-Preserving Method for Uncertain Trajectory Data.

Fucai Zhu, Xingyang He, Shuang Wang, Jian Xu, Mingwei Wang, Lina Wu

Proceedings of the 13th IEEE International Conference on Trust, 2014