activity
20242026
collaborators

7 papers

cs.CV2026

FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking

Yueyang Cang, Xiaoteng Zhang, Zhiyuan Ning +2

Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechani…

cs.CV2026

Intelligent Pathological Diagnosis of Gestational Trophoblastic Diseases via Visual-Language Deep Learning Model

Yuhang Liu, Yueyang Cang, Wenge Que +12

The pathological diagnosis of gestational trophoblastic disease(GTD) takes a long time, relies heavily on the experience of pathologists, and the consistency of initial diagnosis i…

cs.CL2026

Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization

Yueyang Cang, Xiaoteng Zhang, Erlu Zhao +7

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize…

cs.LG2025

Shared DIFF Transformer

Yueyang Cang, Yuhang Liu, Xiaoteng Zhang +2

DIFF Transformer improves attention allocation by enhancing focus on relevant context while suppressing noise. It introduces a differential attention mechanism that calculates the…

q-bio.NC2025

The Role of Excitatory Parvalbumin-positive Neurons in the Tectofugal Pathway of Pigeon (Columba livia) Hierarchical Visual Processing

Shan Lu, Xiaoteng Zhang, Yueyang Cang +6

The visual systems of birds and mammals exhibit remarkable organizational similarities: the dorsal ventricular ridge (DVR) demonstrates a columnar microcircuitry that parallels the…

cs.CL2025

DINT Transformer

Yueyang Cang, Yuhang Liu, Xiaoteng Zhang +2

DIFF Transformer addresses the issue of irrelevant context interference by introducing a differential attention mechanism that enhances the robustness of local attention. However,…