activity
20242026
collaborators

11 papers

cs.CV2026

GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs

Zichuan Fu, Shirong Wang, Wenlin Zhang +10

GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, densely populated inter…

cs.LG2026

Attention Needs to Focus: A Unified Perspective on Attention Allocation

Zichuan Fu, Wentao Song, Guojing Li +6

The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanis…

cs.CL2025

A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs

Yimin Deng, Yuxia Wu, Yejing Wang +9

Temporal knowledge graph reasoning aims to predict future events with knowledge of existing facts and plays a key role in various downstream tasks. Previous methods focused on eith…

cs.AI2025

Model Merging for Knowledge Editing

Zichuan Fu, Xian Wu, Guojing Li +6

Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various s…

cs.CL2025

Training-free LLM Merging for Multi-task Learning

Zichuan Fu, Xian Wu, Yejing Wang +6

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing (NLP) tasks. The release of open-source LLMs like LLaMA and Qwen…

cs.CL2025

Sliding Window Attention Training for Efficient Large Language Models

Zichuan Fu, Wentao Song, Yejing Wang +7

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity…